Academic Project Recommendations

Abstract

The present invention discloses academic project recommendation. Related operations include recommending and presenting academic projects to students. The academic project recommendation model generates recommendations based on the specific characteristics of the target student. If the characteristics of the target student match those of other students who have successfully completed an academic project, then that academic project is recommended to the target student. If the characteristics of the target student match those of other students who have failed to complete the academic project after a certain threshold period, then that academic project is not recommended to the target student. The system presents an interface for comparing multiple academic projects that have been evaluated taking into account the specific characteristics of the target student. The interface simultaneously lists each academic project in the academic project set and the corresponding likelihood of success determined for the target student.

Description

Technical Field

[0001] The present disclosure relates to higher education. In particular, the present disclosure relates to recommending academic programs for students. Background Art

[0002] An academic program is a course of study associated with an academic subject. Academic programs are common in institutions of higher education. Typically, in order to receive a degree or certificate in a particular academic subject, a student must complete the requirements associated with the corresponding academic program. Academic programs can include, for example, majors, minors, degree programs, and certificate programs. Examples of majors include biology, English, and health sciences. Academic programs can be associated with a particular degree (such as a Bachelor of Science or Master of Fine Arts degree).

[0003] A student can enroll in or declare an academic program, thereby committing to complete the requirements associated with that academic program. Prior to enrolling in an academic program, a student can have an undeclared status. By allowing a student to have an undeclared status, an institution gives the student the flexibility to choose an academic path as the student matures and is exposed to different subjects. However, if a student completes many academic cycles without choosing an academic program, then the student will likely choose courses that will not be used towards a degree or certificate. Timely selection of an academic program can reduce costs for the student.

[0004] The methods described in this section are methods that can be pursued, but are not necessarily methods that have been previously contemplated or pursued. Thus, unless otherwise indicated, no method described in this section should be assumed to be prior art merely because they are included in this section. Summary of the Invention

[0005] According to one aspect of the present disclosure, a non-transitory computer-readable medium is provided. The non-transitory computer-readable medium contains instructions that, when executed by one or more hardware processors, cause the execution of operations that include: identifying a set of characteristics associated with a target student; selecting, from a plurality of students enrolled in a particular academic program, a subset of students that share one or more characteristics from the set of characteristics associated with the target student; determining for each student in the subset of students whether the student has (a) changed to a different academic program, (b) withdrawn from the particular academic program, or (c) completed the particular academic program; calculating, based on the determining operation, a recommendation score for the particular academic program with respect to the target student; and at least one of the following: at least in response to determining that the recommendation score meets or exceeds a threshold, recommending the particular academic program for the target student; at least in response to determining that the recommendation score does not exceed the threshold, refraining from recommending the particular academic program for the target student.

[0006] This application claims the benefit of U.S. Provisional Patent Application No. 62 / 573,351, filed Oct. 17, 2017, U.S. Provisional Patent Application No. 62 / 633,187, filed Feb. 21, 2018, and U.S. Non-Provisional Patent Application No. 15 / 991,244, filed May 29, 2018, which are hereby incorporated by reference in their entirety. BRIEF DESCRIPTION OF THE DRAWINGS

[0007] The embodiments are illustrated by way of example and not limitation in the figures of the accompanying drawings. It should be noted that references to "one" or "an" embodiment in this disclosure are not necessarily to the same embodiment, and they mean at least one. In the drawings:

[0008] Figure 1 illustrates a system according to one or more embodiments;

[0009] Figure 2A illustrates a comparison view of an academic program recommendation interface according to one or more embodiments;

[0010] Figure 2B illustrates a requirements view of an academic program recommendation interface according to one or more embodiments;

[0011] Figure 2C illustrates a success factors view of an academic program recommendation interface according to one or more embodiments;

[0012] Figure 3 illustrates an example operation for recommending an academic program for a target student according to one or more embodiments;

[0013] Figure 4 illustrates an example operation for displaying a recommended program via academic program recommendation according to one or more embodiments; and

[0014] Figure 5 shows a block diagram of an illustrative computer system according to one or more embodiments. DETAILED DESCRIPTION

[0015] In the following description, for purposes of explanation, numerous specific details are set forth in order to provide a thorough understanding. One or more embodiments may be practiced without these specific details. Features described in one embodiment may be combined with features described in a different embodiment. In some instances, well-known structures and devices are described in block diagram form in order to avoid unnecessarily obscuring the present invention.

[0016] 1. OVERALL OVERVIEW

[0017] 2. SYSTEM ARCHITECTURE

[0018] 3. Academic Program Recommendation Interface

[0019] 4. Select Recommended Academic Programs

[0020] 5. Display Recommended Academic Programs

[0021] 6. Others; Extensions

[0022] 7. Hardware Overview

[0023] 1. General Overview

[0024] Academic programs can include, for example, majors, degree programs, minors, and certificate programs. Some embodiments recommend and present academic programs to students. The academic program recommendation model generates recommendations based on the specific characteristics of the target student. If the characteristics of the target student match the characteristics of other students who have successfully completed an academic program, then that academic program is recommended to the target student. If the characteristics of the target student match the characteristics of other students who have failed to complete an academic program after a certain threshold period, then that academic program is not recommended to the target student.

[0025] Some embodiments present an interface for comparing multiple academic programs that have been evaluated taking into account the specific characteristics of the target student. The interface simultaneously lists each academic program in the set of academic programs and the corresponding likelihood of success determined for the target student. The likelihood of success can correspond to the likelihood that the target student will complete the academic program within a specific amount of time or with a specific grade point average (GPA). The likelihood of success can correspond to the likelihood that the target student will obtain employment upon completion of the academic program. Additionally, the interface can simultaneously list, for each academic program in the set of academic programs, the specific student-specific goals that still need to be completed by the target student. As an example, for each academic program in the set of academic programs, the interface can simultaneously list the number of courses, the number of credits, the estimated cost, or the estimated amount of time necessary for the target student to complete.

[0026] Some embodiments described in this specification and / or recited in the claims may not be included in the General Overview section.

[0027] 2. System Architecture

[0028] Figure 1 Illustrate an academic program recommendation system 100 according to one or more embodiments. As Figure 1 illustrated, system 100 includes a student information repository 112, an academic program recommendation engine 114, and an academic program recommendation interface 120. In one or more embodiments, system 100 can include more or fewer components than Figure 1 illustrated. Figure 1 The components illustrated can be local or remote from each other.Figure 1 The components illustrated in Figure 1 can be implemented in software and / or hardware. Each component can be distributed across multiple applications and / or machines. Multiple components can be combined into one application and / or machine. Operations described with respect to one component can instead be performed by another component.

[0029] Academic programs recommended by system 100 can include academic programs at institutions of higher education. As an example, an academic program can be a major or a minor, such as mathematics, English, or chemistry. Alternatively, or in addition, an academic program can correspond to a degree program, such as an Associate of Arts (A.A.) English program or a Master of Science (M.S.) Biology program. As another example, an academic program can be a field of study for continuing education, such as a certificate program in software development or accounting.

[0030] In an embodiment, student information repository 112 is any type of storage unit and / or device for storing data (e.g., a file system, a collection of tables, or any other storage mechanism). Additionally, student information repository 112 can include multiple different storage units and / or devices. The multiple different storage units and / or devices can or can not have the same type or be or not be located at the same physical location. Additionally, student information repository 112 can be implemented or executed on the same computing system as academic program recommendation engine 114 and academic program recommendation interface 120. Alternatively, or in addition, student information repository 112 can be implemented or executed on a computing system separate from academic program recommendation engine 114 and academic program recommendation interface 120. Student information repository 112 can be communicatively coupled to academic program recommendation engine 114 and academic program recommendation interface 120 via a direct connection or via a network.

[0031] In an embodiment, student information repository 112 is populated with student information from various sources and / or systems. Student information repository 112 can be populated with student data such as academic data 102, financial data 104, admissions and enrollment data 106, personal data 108, and employment data 110. Student data can be structured (e.g., a table). Alternatively, or in addition, student data can be unstructured (e.g., text or a social media post).

[0032] In some embodiments, the academic data 102 includes records from a student's previous and / or current educational institutions. The academic data may be collected by the university from the student. The academic data may be collected from the student's current or previous educational institutions. As an example, the student information repository 112 may be connected to the university's archives department. The student information repository may be populated with academic data 102 from the archives department. The academic data 102 may include the student's college records, such as completed courses and received grades. The academic data 102 may include academic records from other higher education institutions. The academic data 102 may also include the student's standardized test scores. The academic data 102 may include any information about the student's previous or current courses, such as grades, enrollment status, class size, feedback, evaluations, attendance, professors, and participation scores.

[0033] In some embodiments, the financial data 104 may include information about the amount of tuition fees that the student has paid and / or is scheduled to pay. The financial data 104 may include the amount paid by the student to date. The financial data 104 may include the cost of attending each academic unit (e.g., the cost of each course or course unit). The financial data 104 may include the cost of attending each academic cycle (e.g., the cost of each semester). The financial data 104 may include financial aid awarded to and / or available to the student. The student information repository may be populated with financial data 104 from the university's finance department.

[0034] In some embodiments, the student information repository may be populated with admissions and enrollment data 106 from the university's admissions and / or enrollment department. The admissions and enrollment data 106 may include information obtained by admissions personnel, such as schools that the prospective student is interested in. The admissions and enrollment data 106 may include information submitted by the student as part of a formal application. The admissions and enrollment data 106 may include demographic information provided by the student in an admissions application. The admissions and enrollment data 106 may include essays submitted by the student as part of an admissions application. The admissions and enrollment data 106 may include interests specified in the application, such as housing interests and sports interests.

[0035] In some embodiments, the employment data 110 may include statistics about employment related to one or more academic programs. The employment data 110 may include employment statistics for students who have completed a particular academic program. The employment data 110 may include salary data for students who have completed a particular academic program. The student information repository may be populated with employment data 110 from the university's career services department. The employment data 110 may be obtained from alumni surveys. Alternatively, or in addition, the employment data 110 may be obtained from the human resources departments of various companies. Alternatively, or in addition, the employment data 110 may be obtained from employment-related websites or databases.

[0036] In one or more embodiments, personal data 108 may include information about any activity performed by a student. As an example, personal data 108 may include a browser history indicating that the student has visited the university's website. Personal data 108 may also include a browser history indicating third-party websites that the student has visited. As another example, personal data 108 may include information about the student winning first place in an engineering competition. As another example, personal data 108 may include a social media post made by the student indicating an interest in sculpture. Personal data 108 may also include biometric data, such as the race that the student self-reported in a survey. As another example, personal data 108 may indicate that the student is a first-generation college attendee. Personal data 108 may include student information obtained from a third-party database.

[0037] In an embodiment, the academic program recommendation engine 114 is hardware and / or software configured to identify academic programs recommended for a target student. The academic program recommendation engine 114 may identify academic programs for recommendation based on student information stored in the student information repository 112.

[0038] In an embodiment, the academic program recommendation engine 114 determines a recommendation score 118 for an academic program with respect to a target student. The recommendation score 118 may be a numerical value indicating whether the academic program should be recommended for the target student. As an example, the recommendation score 118 may be a number from one to ten.

[0039] The academic program recommendation engine 114 may use one or more models to calculate a recommendation score 118 for a particular academic program with respect to a target student. Based on the recommendation score, the academic program recommendation engine 114 selects the academic program to recommend to the target. The system may organize data into a tabular form, categories, and / or classifications to enable data analysis via the models.

[0040] The academic program recommendation engine 114 may cause the recommendation score 118 to be based on a comparison of (a) student data associated with the target student and (b) historical data associated with previous students. As an example, previous students who have shown an interest in art and design have a high graduation rate in an architecture major. Based on the target student's interest in art and design and the correlation between the art and design interest and success in the architecture major, the system increases the recommendation score for the architecture major for the target student. The recommendation score 118 for the current student may be directly proportional to the number of attributes common with previous successful students. The academic program recommendation engine 114 may compare attributes based on any student data stored in the student information repository 112.

[0041] Alternatively, or in addition, the academic program recommendation engine 114 can determine a recommendation score 118 by comparing (a) student data associated with a target student and (b) the completion requirements for the target student based on the requirements of an academic program. The completion requirements for the target student can include the number of course credits or hours obtained by the target student that are suitable for the requirements of a particular academic program. The completion requirements for the target student can include a set of courses completed by the target student that meet the requirements of a particular academic program. The completion requirements for the target student can include non-course requirements that meet the requirements of a particular academic program. Non-course requirements can include mandatory internships and / or extracurricular activities. Non-course requirements can include major events, such as a thesis or a final project.

[0042] In addition, the academic program recommendation engine 114 can determine a likelihood of success 116 for the target student relative to one or more academic programs. The likelihood of success 116 can correspond to the likelihood that the student will complete an academic program within a particular amount of time. Alternatively, or in addition, the likelihood of success 116 can correspond to the likelihood that the student will complete an academic program with a particular grade point average (GPA). Alternatively, or in addition, the likelihood of success 116 can correspond to the likelihood that the student will obtain employment upon graduation. The likelihood of success 116 for the target student with respect to an academic program can be identified by comparing the characteristics of the target student and the characteristics associated with previous students who have been successful in the academic program. The recommendation score 118 can be based in whole or in part on the likelihood of success 116. As an example, the system calculates the likelihood of success 116 based on the shared characteristics of the target student and graduates with a Bachelor of Science (B.S.) in Psychology. The system increments the likelihood of success 116 based on the completed courses of the target student that count towards the Psychology B.S. to calculate the recommendation score 118.

[0043] In some embodiments, the academic program recommendation engine 114 can determine whether to recommend, or avoid recommending, an academic program. The academic program recommendation engine 114 determines whether to recommend a particular academic program based on the recommendation score for the particular academic program. The academic program recommendation engine can compare the recommendation score and a threshold to determine whether to recommend the academic program corresponding to the recommendation score. The system can store different thresholds for recommending academic programs. For example, the threshold can be set to fifty for liberal arts programs and to sixty for engineering programs.

[0044] In an embodiment, the academic project recommendation interface 120 is a graphical user interface (GUI) configured to display a list of academic projects. As an example, the academic project recommendation interface 120 can display information to students to assist them in selecting academic projects. The academic project recommendation interface 120 can simultaneously identify multiple recommended academic projects and respective information about each project. As another example, the academic project recommendation interface 120 can display information to an academic advisor. The information can allow the academic advisor to better assist students in selecting academic projects. The academic project recommendation interface 120 can display student data for each academic project in a set of recommended academic projects that are simultaneously displayed. The academic project recommendation interface 120 can obtain student data from the student information repository 112 or from the academic project recommendation engine 114.

[0045] Different components of the academic project recommendation interface 120 can be specified in different languages. The behavior of user interface elements can be specified in a dynamic programming language, such as JavaScript. The content of user interface elements can be specified in a markup language, such as Hypertext Markup Language (HTML) or Extensible Markup Language (XML) User Interface Language (XUL). The layout of user interface elements can be specified in a style sheet language, such as Cascading Style Sheets (CSS). Alternatively, the academic project recommendation interface 120 can be specified in one or more other languages, such as Java, C, or C++.

[0046] The academic project recommendation interface 120 can be implemented on one or more digital devices. The term "digital device" generally refers to any hardware device that includes a processor. A digital device can refer to a physical device that executes an application or a virtual machine. Examples of digital devices include computers, tablets, laptops, desktops, netbooks, mobile handheld terminals, smartphones, personal digital assistants ("PDAs"), and / or client devices.

[0047] In an embodiment, the academic program recommendation interface 120 includes a virtual assistant (not shown) that is triggered or managed by the virtual assistant. The virtual assistant presents information reactively (in response to a request for information) or proactively (in the absence of a specific request for information). The virtual assistant can periodically identify a set of students who have not signed up for an academic program. As an alternative, or in addition, the virtual assistant can periodically identify (a) students who are signed up for an academic program different from a particular academic program and (b) a set of students who are not performing according to minimum performance criteria. As an example, the virtual assistant can identify students with a low GPA. A low GPA can indicate that the student should choose a different academic program in which the student may be more successful. In response to identifying students who should choose an academic program, the virtual assistant can present a notification. The virtual assistant can present the notification using a link to the academic program recommendation interface 120. As an alternative, or in addition, the virtual assistant can directly present a list of recommended academic programs.

[0048] 3. Academic Program Recommendation Interface

[0049] Figures 2A - 2C Illustrates an example of the academic program recommendation interface 120 according to one or more embodiments. Operations described with respect to one component may instead be performed by another component. As Figure 2A illustrated, the academic program recommendation interface 120 includes a comparison view 122, a requirements view 124, and a success factors view 126. The academic program recommendation interface 120 can display information at various levels of granularity. The academic program recommendation interface 120 can switch views in response to user input to allow the user to explore in depth the statistics regarding the selected academic program.

[0050] A. Comparison View

[0051] An example of the comparison view 122 is shown in Figure 2A . The comparison view 122 can include data regarding each academic program in the set of recommended academic programs 200 that are displayed simultaneously. The comparison view can include, for example, multiple course or non-course requirements that are completed by the student and are necessary for the recommended academic program. As Figure 2A illustrated, the comparison view 122 presents the number 202 of completed courses that are suitable for completion of each recommended program. The comparison view 122 can also present the number of courses completed by the student that do not count towards the recommended academic program. The comparison view can also include the number of course credits (e.g., completed units 204) of courses completed by the student that satisfy the course credit requirements of the recommended academic program.

[0052] The comparison view 122 may include the expected time 203 for a student to complete the requirements of an academic program. As an example, the comparison view 122 shows "Graduation time: 4 academic cycles". The comparison view 122 may include the expected cost 205 for a student to complete the remaining requirements of an academic program. As an example, the comparison view 122 shows "Graduation investment: $10,840". The system may determine the expected time and / or cost based on an analysis of the student's academic data and / or financial data. As an example, the system calculates the expected cost for a student to complete the remaining requirements of an academic program by multiplying the number of academic cycles required to complete the remaining requirements of the academic program by the cost of attending each academic cycle.

[0053] The comparison view may include employment statistics information 206 corresponding to an academic program. As Figure 2B shown, the employment statistics information may include a job market rating 212, an employability rating 214, and / or an average salary 216. The job market rating 212 may qualitatively or quantitatively evaluate the demand for employees who have completed the associated academic program. For example, the job market rating 212 may be "hot" or "medium". The employability rating 214 may qualitatively or quantitatively evaluate the percentage of people who are employed within a certain period after completing the academic program. As an example, if 85% of the graduates from an academic program are employed within six months of graduation, then the employability rating 214 is "high". The comparison view may display salary statistics information for students who have completed an academic program, such as the average salary 216. Additional salary statistics information that the comparison view may display includes salary percentiles. For example, the interface displays the ninetieth percentile salary, the fiftieth percentile salary, and the twentieth percentile salary for recent graduates of a Bachelor of Science in Health Sciences program.

[0054] Referring Figure 2A , the comparison view 122 may include student data 208 corresponding to the target student for whom the academic program is being recommended. As an example, the comparison view shows the student's name, the student's academic year (e.g., freshman or sophomore in college), and the academic program that the student has declared (if any).

[0055] If a student enrolls in an academic program, then the comparison view may display information 210 about the target student's progress in that academic program. As Figure 2AAs shown in [Figure], the comparison view 122 shows the progress units (seventeen) of the student in the student's current nursing major. The comparison view also includes the completed units of the student (completed twenty-four / total of one hundred and twenty) compared to the total units required for the nursing major. The comparison view 122 can also display financial information based on the student's current academic program. The financial information based on the student's current academic program can include the projected cost for the student to complete the requirements of the academic program. The comparison view 122 can also include employment information of students who have completed the student's current academic program, such as employability and average salary.

[0056] The comparison view 122 can include the likelihood of success 116 for each academic program in the recommended academic program set. The likelihood of success 116 can be displayed qualitatively. As an example, for each academic program in the recommended academic program, the interface displays: Likelihood of success: High / Medium / Low. As an alternative, or additionally, the likelihood of success 116 can be displayed quantitatively. As an example, for the recommended academic program, the interface displays: Likelihood of success: 0.3. The likelihood of success 116 can be color-coded. As an example, high is displayed in green, medium is displayed in yellow, and low is displayed in red.

[0057] B. Requirements View

[0058] An example of the requirements view 124 is shown in Figure 2B In response to the user activating a button or link 211 labeled "Admission Requirements", the academic program recommendation interface can transition to the requirements view 124. The requirements view 124 can include some or all of the information in the comparison view 122, along with detailed information about the admission requirements 218 of the selected academic program. The displayed admission requirements 218 can include the courses required for admission to the associated academic program. As an example, to be admitted to the Health Sciences major, a student must complete two courses in English writing, one course in mathematics, and a total of ten semester units. Additionally, the displayed admission requirements 218 can include the courses completed by the student related to the academic program requirements. For example, the interface displays "6 / 10 units completed", indicating that the target student has completed six of the ten semester units required to start the academic program. The requirements view 124 can be presented as a pop-up window on the comparison view 122.

[0059] C. Success Factors View

[0060] An example of the success factors view 126 is shown in Figure 2CShown in. In response to the user activating the button or link 222 labeled "Likelihood of Success", the academic program recommendation interface can transition to the success factors view 126. The success factors view 126 can include some or all of the information in the comparison view 122, along with detailed information about the likelihood of success 116 of the student in the selected academic program.

[0061] The success factors view 126 includes a student-specific value for each likelihood factor 224 in the set of likelihood factors used to determine the likelihood of success of the target student in a particular academic program. The likelihood factors 224 can correspond to characteristics of the target student that are associated with previously successful students in that academic program. The academic program recommendation interface can display a subset of the factors used to determine the likelihood of success of the target student in the academic program, which are the most decisive in the calculation of the likelihood of success. Alternatively, the academic program recommendation interface displays all of the factors used to determine the likelihood of success of the target student in the academic program.

[0062] The success factors view can include qualitative or quantitative values corresponding to each likelihood factor 224. The success factors view can include a color code. As an example, the system can use green to indicate a very positive impact, yellow to indicate a positive impact, and red to indicate a negative impact. The GPA of the student is highly correlated with the GPA of students who have successfully completed the Health Science B.S. program. Therefore, the academic program recommendation interface displays a green icon next to "GPA", thus indicating that GPA is a factor that strongly influences the recommendation for the Health Science B.S. program. The high school (HS) subjects completed by the target student are not similar to the high school subjects completed by students who have successfully completed the Health Science B.S. program. Therefore, the academic program recommendation interface displays a red icon next to "HS Subjects", thus indicating that the high school subjects have a negative impact on the likelihood of success. Alternatively, or additionally, the academic program recommendation interface can display quantitative values corresponding to each factor. As an example, the academic program recommendation interface displays "60% similarity" next to "Interest Survey", thus indicating a 60% similarity between the interests of the student and the interests of previously successful students.

[0063] The academic program recommendation interface can also include a button labeled "View Plan". In response to the user's interaction with the "View Plan" button, the academic program recommendation interface can display a course planner corresponding to the respective academic program. The display of the course planner is described in U.S. Provisional Patent Application No. 62 / 566,394, Event Management System, which is incorporated herein by reference.

[0064] In an embodiment, the academic program recommendation interface includes elements that accept user input to sort or filter the recommended academic programs. As an example, in response to detecting user interaction with a button displayed above the salary data, the system sorts the set of recommended academic programs. The system displays the academic programs in order from the academic program with the highest average salary to the academic program with the lowest average salary. As another example, in response to detecting user interaction with a slider button, the system filters the set of recommended academic programs. The system only displays the recommended academic programs that a student can complete the required coursework while paying less than $50,000.

[0065] 4. Select a recommended academic program

[0066] Figure 3 Illustrative set of example operations for identifying academic programs to recommend to a target student according to one or more embodiments. One or more of the operations illustrated Figure 3 may be modified, rearranged, or omitted entirely. Accordingly, Figure 3 the particular sequence of operations illustrated

[0067] In some embodiments, the academic program recommendation engine identifies a set of characteristics associated with the target student (operation 302). The academic program recommendation engine may identify the set of characteristics associated with the target student by querying the student information repository. The system may identify characteristics based on one or more of academic data, financial data, admissions and enrollment data, personal data, and employment data related to the target student.

[0068] In some embodiments, the academic program recommendation engine identifies a set of students who are enrolled in an academic program and share one or more of the characteristics associated with the target student (operation 304). The academic program recommendation engine may identify the set of students by querying the student information repository. As an example, the target student is a first-generation college student. The academic program recommendation engine queries the student information repository to identify the set of students known to be first-generation college students. The academic program recommendation engine selects a subset of the set of first-generation college students who have declared a major in legal studies. The academic program recommendation engine may identify the set of students based on a range or category corresponding to the characteristics associated with the target student. As an example, the target student has a GPA of 3.1. The academic program recommendation engine queries the student information repository to identify other students with a GPA in the range of 3.0 to 3.2.

[0069] The academic program recommendation engine may group the students based on the results. As an example, the academic program recommendation engine identifies previous students who have completed an academic program, changed an academic program, or dropped out.

[0070] In some embodiments, the academic program recommendation engine determines whether a previous student in the selected set of students has changed to a different academic program (operation 306). The academic program recommendation engine can determine whether a particular student has changed to a different academic program by querying a student information repository. Students who have changed to a different academic program can include, for example, students who have changed from a biology major to a psychology major. As another example, students who have changed to a different academic program can include students who have changed from a B.S. chemistry degree program to a B.S. chemical engineering degree program.

[0071] In some embodiments, the academic program recommendation engine determines whether a previous student in the selected set of students has completed an academic program (operation 308). The academic program recommendation engine can query the student information repository to identify students who have completed an academic program by graduating or obtaining a certificate. Alternatively, or additionally, the academic program recommendation engine can identify students who have completed an academic program within a threshold time period. As an example, the academic program recommendation engine determines whether a previous student graduated with an English degree within six years.

[0072] In some embodiments, the academic program recommendation engine determines whether a previous student in the selected set of students has withdrawn (operation 310). The academic program recommendation engine can determine that a previous student has withdrawn from an academic institution by querying the student information repository.

[0073] When determining whether a previous student has completed an academic program, changed an academic program, withdrawn, or none of the above, the academic program recommendation engine can assign a weight to the previous student. The weight can represent the suitability of the previous student for an academic program and / or the likelihood of success in the academic program.

[0074] In some embodiments, if a previous student has changed an academic program, then the academic program recommendation engine assigns a low weight to the previous student (operation 312). When a student changes from a first academic program to a second academic program, the change can indicate low suitability for the first academic program. Thus, a low weight can be appropriate for a student who has changed an academic program. The low weight can be used to adjust the model so that when a previous student who shares characteristics associated with a target student has changed to a different academic program, the model is less likely to recommend the academic program to those target students.

[0075] In some embodiments, if a previous student completed an academic program, then the academic program recommendation engine assigns the maximum weight to the previous student (operation 314). When a student completes an academic program, the completion highly indicates a successful outcome and a good fit. Thus, the maximum weight can be suitable for the student who changed the academic program. The maximum weight can be used to adjust the model to be more likely to recommend an academic program to a target student when a previous student sharing characteristics associated with the target student completed the academic program.

[0076] In some embodiments, if a previous student dropped out, then the academic program recommendation engine discards the previous student (operation 318). The system can avoid using dropouts in the model because dropping out may be more highly correlated with other factors (such as financial difficulties and personal problems) compared to whether a student signed up for an appropriate academic program.

[0077] In some embodiments, if a previous student did not change the academic program, did not complete the academic program, and did not drop out, then the academic program recommendation engine assigns a medium weight to the previous student (operation 316). Students who did not change the academic program, did not complete the academic program, and did not drop out can include, for example, students who are still enrolled in the academic program and / or students who completed the academic program outside of a threshold time period. Students who did not change the academic program, did not complete the academic program, and did not drop out can also include students who transferred to a different academic institution.

[0078] In some embodiments, the academic program recommendation engine calculates a recommendation score for an academic program with respect to a target student (operation 320). The recommendation score is based on the weighted previous students. The academic program recommendation engine can use the weighted previous students to generate a mathematical model that produces the recommendation score. As an example, for each student who (a) shares one or more characteristics with the target student and (b) completed a communication degree program, the recommendation score for the communication degree program of the target student is incremented by five. For each student who (a) shares one or more characteristics with the target student and (b) changed from a communication degree to another academic program, the recommendation score for that particular academic program of the target student is incremented by one.

[0079] As an alternative, or in addition, the academic program recommendation engine can weight the specific characteristics shared by the target student with a set of students who have been successful in an academic program. Attributes that are more strongly correlated with success can be weighted more heavily than other attributes. As an example, the academic program recommendation engine determines that the courses completed by a student and the student's GPA are strongly correlated with completing a particular academic program within five years. The high school subjects completed by the student and the student's interests are weakly correlated with completing an academic program within five years. Thus, the academic program recommendation engine weights the courses completed at the institution and the GPA more heavily than the high school subjects completed and the student's interests for recommendation score calculation.

[0080] In some embodiments, the academic program recommendation engine may update the recommendation score based on employment data associated with the academic program. As an example, the academic program recommendation engine determines that the employment rate and average salary are higher for graduates with a kinesiology degree than for graduates with a health administration degree. Thus, the academic program recommendation engine assigns a higher recommendation score to kinesiology than to health administration.

[0081] Alternatively, or in addition, the academic program recommendation engine may increment or decrement the recommendation score based on the completion requirements for the target student. The system may determine whether the target student has met the completion requirements by analyzing the data stored in the student information repository. As an example, the academic program recommendation engine may determine, based on the student data, that for academic program A, the student has completed sixteen required course credits. For academic program B, the student has completed forty required course credits. The system determines that the student has met a greater number of completion requirements for academic program B than for academic program A. Thus, the system increments the recommendation score for academic program B. As another example, the academic program recommendation engine updates the recommendation score based on the predetermined amount of time it will take the target student to complete the academic program. The system may assign a relatively high recommendation score for a program that has one year remaining for the target student. The system may assign a relatively low recommendation score for an academic program that has two years remaining for the target student.

[0082] Alternatively, or in addition, the academic program recommendation engine may increment or decrement the recommendation score based on the financial information associated with the target student's completion of the academic program. As an example, the system may update the recommendation score based on the predetermined cost for the target student to complete the academic program. As another example, the system may update the recommendation score based on the debt that the target student will incur in completing the academic program. If the predetermined debt exceeds a threshold debt value, the system may decrement the recommendation score.

[0083] In some embodiments, the academic program recommendation engine updates the model used to calculate the recommendation score based on refreshed data. As an example, the academic program recommendation engine may update the model based on the results of the target student in the academic program. After recommending an academic program for the target student, the system may determine that the target student has enrolled in the academic program. If the target student drops out of the academic program or changes to a different academic program, the system may modify the model. The system may decrement the recommendation score for that academic program for other students who share characteristics with the target student. If the target student completes the academic program, the system may increment the recommendation score for that academic program for other students who share characteristics with the target student.

[0084] The recommended score can be based in whole or in part on the likelihood of success of the target student in an academic program. A measure representing the likelihood of success can be determined using a model similar to those described above for the recommended score. The system can increment or decrement the likelihood of success measure to compute the recommended score. As an example, the system computes a likelihood of success measure of fifty for a target student for a Biology M.S. program. Based on coursework completed by the target student that counts towards the Biology M.S. program, the system increments the likelihood of success measure by twenty-five to compute a recommended score of seventy-five. As an alternative, the recommended score can directly correspond to the likelihood of success measure. As an example, the likelihood of success measure equals the recommended score equals forty.

[0085] In some embodiments, the academic program recommendation engine determines whether the recommended score meets or exceeds a threshold (operation 322). The academic program recommendation engine can identify the stored threshold. The academic program recommendation engine compares the recommended score and the threshold.

[0086] In some embodiments, if the recommended score meets or exceeds the threshold, then the academic program recommendation engine recommends the academic program to the target student (operation 324). As detailed, the system can recommend the academic program to the student or advisor via the academic program recommendation interface. As an alternative, or in addition, the system can display the recommended program via a virtual assistant. As an alternative, or in addition, the system can recommend the academic program by transmitting a notification, such as an email, text message, or voice message. Figure 4 As detailed, the system can recommend the academic program to the student or advisor via the academic program recommendation interface. As an alternative, or in addition, the system can display the recommended program via a virtual assistant. As an alternative, or in addition, the system can recommend the academic program by transmitting a notification, such as an email, text message, or voice message.

[0087] In some embodiments, if the recommended score does not meet or exceed the threshold, then the academic program recommendation engine refrains from recommending the academic program to the target student (operation 326). The system can refrain from displaying any academic programs not recommended for the target student.

[0088] The following detailed example illustrates operations in accordance with one or more embodiments. The following detailed example should not be construed as limiting the scope of any of the claims. The system identifies that target student Chris Sanchez has a low GPA in Chris's current major of Chemical Engineering. Accordingly, the system prepares to identify other majors in which Chris is more likely to succeed.

[0089] The academic program recommendation engine identifies the set of features associated with Chris. The identified features include academic statistics, financial information, personal information, and employment information. The features include GPA. Chris has a GPA of 2.8 at the current institution and a GPA of 3.9 in high school. The features include information related to the financial aid available to Chris. Chris has a scholarship that will expire after four years of enrollment, such that if Chris graduates within four years, his cost of attendance will be $5,000 per year. The features include the courses Chris has completed. The features also include the set of Chris's interests obtained from a voluntary interest survey submitted by Chris to his current college.

[0090] The academic program recommendation engine identifies the set of previous students who (a) share one or more of the identified features with Chris and (b) have enrolled in an academic program. The system identifies the students who have enrolled in the Chemistry B.S. program. The system identifies a set of one hundred and fifty previous students who share at least one of the identified features with Chris and have enrolled in the Chemistry B.S. program.

[0091] For each of the previous students, the system determines whether the student has changed academic programs, completed the academic program, or dropped out. Sixty-one previous students enrolled in the Chemistry B.S. program and completed the program. Nine previous students enrolled in the Chemistry B.S. program and dropped out. Forty-five previous students enrolled in the Chemistry B.S. program and changed to a different academic program. Thirty-five students enrolled in the Chemistry B.S. program and are either still enrolled in the Chemistry B.S. program or transferred to a different school with a similar field of study.

[0092] The academic program recommendation engine assigns weights to each of the previous students based on whether the student has changed academic programs, completed the academic program, dropped out, or none of the above. Students who have changed academic programs are assigned a relatively low weight of one. Students who have completed the academic program are assigned a relatively high weight of ten. Students who have dropped out are discarded. Students who have neither changed academic programs, completed the academic program, nor dropped out are assigned a medium weight of four.

[0093] The academic program recommendation engine calculates an initial recommendation score based on the weighted previous students. The score is equal to the sum of the number of students with a particular weight multiplied by that weight, normalized as follows:

[0094]

[0095] where S 1 is the initial recommendation score, N C is the number of students who have changed academic programs, N Gis the number of students who have completed an academic program, N O is the number of students who have neither changed, completed, nor withdrawn from the academic program, and N TOT is the total number of previous students in the set. The initial recommendation score is equal to:

[0096] (1×45 + 10×61 + 4×35) / 150 = 5.3.

[0097] Update the initial recommendation score based on the courses and non - course requirements completed by Chris that are suitable for the Chemistry B.S. program. Out of the total one hundred and seventy units required to complete the degree program, Chris has completed forty units that count towards the Chemistry B.S. program. Since Chris has completed many of the courses required for the Chemistry B.S. program, the initial recommendation score is incremented by 1.5 points, reaching the updated recommendation score of 6.8.

[0098] Increment the updated recommendation score based on the employment data associated with the Chemistry B.S. program. The system determines that within nine months of graduation, eighty percent of the graduates from the Chemistry B.S. program are employed in chemistry - related jobs. Therefore, the system increments the updated recommendation score by 1 point, calculating the final recommendation score as 7.8.

[0099] The system identifies the threshold for recommending an academic program. The threshold is 6.2. The system compares the final recommendation score of 7.8 for Chris with the threshold of 6.2. The system determines that the final recommendation score for Chris exceeds the threshold. Since the final recommendation score for Chris exceeds the threshold, the system recommends the Chemistry B.S. program to Chris. The system recommends the program by displaying the Chemistry B.S. program in the list of recommended academic programs in the academic program recommendation interface.

[0100] 5. Display the recommended academic program

[0101] Figure 4 Illustrates an example set of operations for displaying a recommended academic program according to one or more embodiments. One or more of the operations illustrated in Figure 4 may be modified, rearranged, or omitted entirely. Therefore, Figure 4 the specific sequence of operations illustrated in

[0102] should not be construed as limiting the scope of one or more embodiments. In some embodiments, the academic program recommendation engine groups the set of academic programs into recommended programs for the target student and non - recommended academic programs for the target student (operation 402). The academic program recommendation engine can identify the recommended and non - recommended programs as described above with respect to Figure 3 the description.

[0103] In some embodiments, the academic program recommendation interface displays the recommended programs for the target student, without simultaneously displaying the non-recommended academic programs for the target student (operation 404). As described above with respect to Figures 2A - 2C As described in detail, the academic program recommendation interface can display a list of the recommended academic programs for the target student.

[0104] In some embodiments, the academic program recommendation interface simultaneously displays the employment statistics associated with each of the recommended academic programs (operation 406). As described above with respect to Figures 2A - 2C As described in detail, the academic program recommendation interface can display employment statistics, including job market ratings, employability ratings, and average salaries. The academic program recommendation interface can display employment statistics such as the percentage of graduates of an academic program who are employed within a certain period after graduation. For example, the interface displays the statistic "forty percent employed within nine months" associated with the Communication A.A. degree program.

[0105] In some embodiments, the academic program recommendation interface simultaneously displays the likelihood of success associated with each of the recommended academic programs (operation 408). The academic program recommendation interface can display the likelihood of success qualitatively (e.g., likelihood of success = high) and / or quantitatively (e.g., likelihood of success = ninety) for each recommended academic program.

[0106] In some embodiments, the academic program recommendation interface receives user input selecting the likelihood of success (operation 410). As an example, the system can detect that the user clicks or hovers over text or a button representing the likelihood of success.

[0107] In some embodiments, the academic program recommendation interface displays the factors used to calculate the likelihood of success (operation 412). The system can identify the factors used to calculate the likelihood of success based on the model used to recommend academic programs for the student. As an example, the system identifies the four factors that are weighted most heavily in the model used to recommend the Health Science B.S. program to the target student. The system displays the four identified factors: "interest survey", "time to graduate", "GPA", and "completed courses".

[0108] In some embodiments, the academic program recommendation interface receives user input selecting an academic program (operation 414). As an example, the system can detect that the user clicks or hovers over text or a button representing the academic program.

[0109] In some embodiments, the academic program recommendation interface displays the specific course work required to begin an academic program (operation 416). The system can identify the prerequisite courses required for a student to declare a major. As an example, the system identifies the course requirements that are prerequisites for declaring a major in Health Sciences. The system displays the course requirements: "English Composition (two courses)" and "Mathematics (one course)". As another example, the system can identify the prerequisite courses required for a student to enroll in a certificate program.

[0110] The following detailed example illustrates operations in accordance with one or more embodiments. The following detailed example should not be construed as limiting the scope of any of the claims. The system identifies the target student Chris Sanchez. Chris has not declared a major. Based on characteristics associated with Chris, such as Chris's completed course work, grades, and personal interests, the system identifies a set of courses recommended for Chris. Chris has been taking health-related courses. Accordingly, the system recommends four health-related academic programs for Chris: Health Sciences, B.S.; Kinesiology, B.S.; Health Administration, Bachelor of Arts (B.A.); and Human Development, A.A.

[0111] The system displays the academic program recommendation interface to Chris in a comparison view. The system displays a list of the four academic programs recommended for Chris. Additionally, the system displays detailed information about each of the four academic programs recommended for Chris. This detailed information includes the completed units that Chris has earned towards the academic program. For the Health Sciences B.S. program, the system displays "17 / 120 units completed", indicating that Chris has completed seventeen of the one hundred and twenty course requirements for the Health Sciences B.S. program. Similarly, the system displays 12 / 120 units completed for Kinesiology B.S.; 11 / 120 units completed for Health Administration B.A., and 7 / 70 units completed for Human Development A.A.

[0112] In addition, the system displays employment statistics associated with each academic program in the recommended academic programs. The system displays a job market rating for each academic program in the recommended academic programs. The job market rating indicates the amount of available jobs associated with the academic program. For Health Science B.S., the system displays "Job Market: Medium". For Kinesiology B.S., the system displays "Job Market: Hot". For Health Administration B.A. and Human Development A.A., the system displays "Job Market: Medium". The system also displays an employability rating for each academic program in the recommended academic programs. The employability rating indicates the employment rate of the graduates of the academic program. For Health Science B.S. and Kinesiology B.S., the system displays "Employability: High". For Health Administration B.A. and Human Development A.A., the system displays "Employability: Medium". The system also displays the average salary for each academic program in the recommended academic programs. For Health Science B.S., the system displays "Average Salary: $50,000". For Kinesiology B.S., the system displays "Average Salary: $80,000". For Health Administration B.A., the system displays "Average Salary: $60,000". For Human Development A.A., the system displays "Average Salary: $60,000".

[0113] In addition, the system displays the likelihood of success associated with each academic program in the recommended academic programs. The likelihood of success represents the probability that Chris will complete the academic program within four years and obtain employment after completing the academic program. The system displays the likelihood of success for each academic program in the recommended academic programs. For Health Science B.S., the system displays "Likelihood of Success: High". For Kinesiology B.S., the system displays "Likelihood of Success: High". For Health Administration B.A., the system displays "Likelihood of Success: High". For Human Development A.A., the system displays "Likelihood of Success: Low".

[0114] Chris clicks on the "Likelihood of Success" in the Health Science B.S. entry. The academic program recommendation interface transitions to the success factors view. In the success factors view, a pop-up window is displayed that has information about the success factors that contributed to the determination that Chris has a high likelihood of success in the Health Science B.S. program. Factors that had a very positive impact on the determination are displayed in green: relevant courses, GPA, graduation cost, and interest survey. Factors that had a positive impact on the determination are displayed in yellow: courses used and progress. Factors that had a negative impact on the determination are displayed in red: high school subjects.

[0115] Chris clicks on "Admission Requirements" in the B.S. in Health Sciences entry. The academic program recommendations interface transitions to the requirements view. In the requirements view, a pop-up window is displayed that has information about the courses Chris must complete before declaring a Health Sciences major for the B.S. program. The interface displays a list of requirements: English Composition (two courses), Statistics (one course), and ten semester units.

[0116] 6. Other; Extensions

[0117] An embodiment is directed to a system having one or more devices, where the devices include a hardware processor and are configured to perform any of the operations described herein and / or recited in any of the following claims.

[0118] In an embodiment, a non-transitory computer-readable storage medium includes instructions that, when executed by one or more hardware processors, cause the performance of any of the operations described herein and / or recited in any of the claims.

[0119] According to one or more embodiments, any combination of the features and functionality described herein may be used. In the foregoing specification, embodiments have been described with reference to numerous specific details that may vary depending on the implementation. Accordingly, the specification and drawings are to be regarded in an illustrative rather than a restrictive sense. The sole and exclusive indicator of the scope of the invention intended by the applicant to be the scope of the invention is the literal and equivalent scope of the set of claims issued from this application, in the specific form in which such claims are issued, including any subsequent amendments.

[0120] 7. Hardware Overview

[0121] According to one embodiment, the techniques described herein are implemented by one or more special-purpose computing devices. The special-purpose computing devices can be hard-wired to perform the techniques, or can include digital electronic devices such as one or more application-specific integrated circuits (ASICs), field-programmable gate arrays (FPGAs), or network processing units (NPUs) that are permanently programmed to perform the techniques, or can include one or more general-purpose hardware processors programmed to perform the techniques according to program instructions in firmware, memory, other storage devices, or a combination. These special-purpose computing devices can also implement the techniques by combining custom hard-wired logic, ASICs, FPGAs, or NPUs with custom programming. The special-purpose computing devices can be a desktop computer system, a portable computer system, a handheld device, a networking device, or any other device that combines hard-wired and / or program logic to implement the techniques.

[0122] For example, Figure 5FIG. 0 is a block diagram showing a computer system 500 on which embodiments of the present invention may be implemented. Computer system 500 includes a bus 502 or other communication mechanism for transferring information, and a hardware processor 504 coupled to bus 502 for processing information. The hardware processor 504 may be, for example, a general-purpose microprocessor.

[0123] Computer system 500 also includes a main memory 506 coupled to bus 502 for storing information and instructions to be executed by processor 504, such as random access memory (RAM) or other dynamic storage device. Main memory 506 may also be used to store temporary variables or other intermediate information during execution of instructions to be executed by processor 504. When these instructions are stored in a non-transitory storage medium accessible to processor 504, they cause computer system 500 to become a special-purpose machine customized to perform the operations specified in the instructions.

[0124] Computer system 500 also includes a read-only memory (ROM) 508 or other static storage device coupled to bus 502 for storing static information and instructions for processor 504. A storage device 510, such as a magnetic disk or optical disk, is provided and storage device 510 is coupled to bus 502 for storing information and instructions.

[0125] Computer system 500 may be coupled via bus 502 to a display 512, such as a cathode ray tube (CRT), for displaying information to a computer user. An input device 514 (which includes alphanumeric and other keys) is coupled to bus 502 for communicating information and command selections to processor 504. Another type of user input device is a cursor control 516, such as a mouse, trackball, or cursor direction keys, for communicating direction information and command selections to processor 504 and for controlling movement of a cursor on display 512. Such input devices typically have two degrees of freedom in two axes (a first axis (e.g., x) and a second axis (e.g., y)), which allows the device to specify a position in a plane.

[0126] The computer system 500 can implement the techniques described herein using custom hardwired logic, one or more ASICs or FPGAs, firmware, and / or program logic that, in combination with the computer system, cause the computer system 500 to be or program the computer system 500 to be a special-purpose machine. According to one embodiment, the techniques herein are performed by the computer system 500 in response to one or more sequences of instructions contained in the main memory 506 being executed by the processor 504. These instructions can be read into the main memory 506 from another storage medium, such as the storage device 510. Execution of the sequence of instructions contained in the main memory 506 causes the processor 504 to perform the processing steps described herein. In an alternative embodiment, hardwired circuitry may be used in place of or in combination with software instructions.

[0127] As used herein, the term "storage medium" refers to any non-transitory medium that stores data and / or instructions that cause a machine to operate in a particular fashion. Such storage medium may include non-volatile media and / or volatile media. Non-volatile media includes, for example, optical or magnetic disks, such as the storage device 510. Volatile media includes dynamic memory, such as the main memory 506. Common forms of storage media include, for example, floppy disks, flexible disks, hard disk drives, solid state drives, magnetic tape, or any other magnetic data storage medium, CD-ROM, any other optical data storage medium, any physical medium with patterns of holes, RAM, PROM, and EPROM, FLASH-EPROM, NVRAM, any other memory chip or cartridge, content addressable memory (CAM), and ternary content addressable memory (TCAM).

[0128] Storage media is distinct from but can be used in conjunction with transmission media. Transmission media participates in transferring information between storage media. For example, transmission media includes coaxial cables, copper wire, and fiber optics, including the wires that comprise the bus 502. Transmission media can also take the form of acoustic or light waves, such as those generated during radio wave and infrared data communications.

[0129] A variety of forms of media can be involved in carrying one or more sequences of one or more instructions to the processor 504 for execution. For example, the instructions can initially be carried on a magnetic disk or solid state drive of a remote computer. The remote computer can load the instructions into its dynamic memory and send the instructions over a telephone line using a modem. A modem local to the computer system 500 can receive the data on the telephone line and convert the data into an infrared signal using an infrared transmitter. An infrared detector can receive the data carried in the infrared signal, and appropriate circuitry can place the data on the bus 502. The bus 502 carries the data to the main memory 506, from which the processor 504 retrieves and executes the instructions. The instructions received by the main memory 506 can optionally be stored on the storage device 510 before or after being executed by the processor 504.

[0130] The computer system 500 also includes a communication interface 518 coupled to the bus 502. The communication interface 518 provides two-way data communication coupled to a network link 520, where the network link 520 is connected to a local network 522. For example, the communication interface 518 can be an Integrated Services Digital Network (ISDN) card, a cable modem, a satellite modem, or a modem that provides a data communication connection to a corresponding type of telephone line. As another example, the communication interface 518 can be a LAN card that provides a data communication connection to a compatible local area network (LAN). A wireless link can also be implemented. In any such implementation, the communication interface 518 sends and receives electrical, electromagnetic, or optical signals that carry digital data streams representing various types of information.

[0131] The network link 520 typically provides data communication to other data devices through one or more networks. For example, the network link 520 can provide a connection to a main computer 524 or to a data device operated by an Internet service provider (ISP) 526 through the local network 522. The ISP 526 in turn provides data communication services through the worldwide packet data communication network now commonly referred to as the "Internet" 528. Both the local network 522 and the Internet 528 use electrical, electromagnetic, or optical signals that carry digital data streams. Signals through the various networks and signals on the network link 520 and through the communication interface 518 are example forms of transmission media, where information carries digital data to or from the computer system 500.

[0132] The computer system 500 can send messages and receive data, including program code, via one or more networks, network links 520, and communication interface 518. In an Internet example, server 530 can transmit request code for an application program via Internet 528, ISP 526, local network 522, and communication interface 518.

[0133] The received code can be executed by processor 504 as it is received, and / or stored in storage device 510 or other non-volatile memory for later execution.

[0134] In the foregoing specification, embodiments have been described with reference to numerous specific details that will vary depending on implementation. Accordingly, the specification and drawings are to be regarded as illustrative rather than restrictive. The sole and exclusive indication of the scope of the present invention, and what the applicant regards as the scope of the present invention, is the literal and equivalent scope of the set of claims that issue from this application, in the specific form in which such claims issue, including any subsequent corrections.

Claims

1. A non-transitory computer-readable medium containing instructions that, when executed by one or more hardware processors, cause the execution of operations, the operations including: Populating a student information repository with student information from multiple sources, at least one of the multiple sources containing academic data associated with multiple previous students who have separately enrolled in multiple academic programs; Based on a set of characteristics associated with a target student: Determine a first recommendation score associated with recommending a first academic program among the multiple academic programs to the target student, wherein determining the first recommendation score includes: (a) Identifying previous students among the multiple previous students who have enrolled in the first academic program, (b) Assigning a weight to the first academic program based at least in part on whether the previous student completed the first academic program, and (c) Calculating the first recommendation score based at least in part on the weight assigned to the first academic program; Determine a second recommendation score associated with recommending a second academic program among the multiple academic programs to the target student; Identify a first threshold associated with the first academic program; Compare the first recommendation score with the first threshold associated with the first academic program; In response to determining that the first recommendation score meets the first threshold: Group the first academic program into multiple recommended academic programs; Identify a second threshold associated with the second academic program; Compare the second recommendation score with the second threshold associated with the second academic program, wherein the first threshold and the second threshold are different; In response to determining that the second recommendation score does not meet the second threshold: Group the second academic program into multiple non-recommended academic programs; Simultaneously display for the target student in a first window of a graphical user interface: The multiple recommended academic programs, without simultaneously displaying the multiple non-recommended academic programs; In response to receiving user input selecting an interface element associated with the first academic program: Display in a pop-up window on the first window in the graphical user interface a set of factors used to calculate the first recommendation score.

2. The medium according to claim 1, wherein, The operations further include: Also simultaneously display in the first window in the graphical user interface the respective recommendation scores associated with recommending each of the multiple recommended academic programs to the target student.

3. The medium according to claim 1, wherein, The operations further include: Also simultaneously display in the first window in the graphical user interface employment statistics associated with each of the multiple recommended academic programs.

4. The medium according to claim 1, wherein, The corresponding employment statistics include the employability of the target student in the field associated with each of the multiple recommended academic programs.

5. The medium according to claim 1, wherein, The corresponding employment statistics information includes job market information corresponding to the fields associated with each of the plurality of recommended academic programs.

6. The medium according to claim 1, wherein, the operations further include simultaneously displaying, for each of the plurality of recommended academic programs, one or more of the following: the estimated graduation time of the target student for each of the plurality of recommended academic programs, based on a set of characteristics associated with the target student; the estimated financial investment of the target student to complete each of the plurality of recommended academic programs; the average time to complete each of the plurality of recommended academic programs; the number of units required to complete each of the plurality of recommended academic programs.

7. The medium as claimed in claim 1, wherein, the operations further include: in response to receiving user input selecting a specific academic program, displaying the specific coursework required for admission to the specific academic program.

8. The medium as claimed in claim 1, wherein: the operations further include: selecting the subset of students from among a plurality of students enrolled in a specific academic program based on the subset of students sharing one or more of the characteristics in the set of characteristics associated with the target student; determining corresponding outcomes associated with each student in the subset of students from among a plurality of possible outcomes, the plurality of possible outcomes including two or more of the following: (a) changing to a different academic program, (b) withdrawing from the academic institution, (c) completing the specific academic program; calculating a recommendation score for the specific academic program with respect to the target student based on the corresponding outcomes associated with each student in the subset of students; grouping the specific academic program into the plurality of recommended academic programs for the target student at least in response to determining that the recommendation score meets or exceeds a threshold; calculating the recommendation score for the specific academic program with respect to the target student is further based on: determining whether a student who has completed the specific academic program has obtained employment associated with the specific academic program; calculating the recommendation score is further based on one or more of the following: the debt that the target student will incur in completing the specific academic program; the amount of time that the target student will spend in completing the specific academic program; the progress that the target student has made in the specific academic program; the amount of financial aid that the target student can obtain; personal data associated with the target student; employment data associated with the specific academic program; the likelihood of success of the target student in the specific academic program; the operations further include: after recommending the specific academic program to the target student, determining (a) that the target student has enrolled in the specific academic program, and (b) that the target student has withdrawn from the academic institution or changed to a different academic program; At least in response to determining that the target student has withdrawn from the specific academic program or changed to a different academic program: modify the model used to calculate the recommendation score for the specific academic program; The first recommendation score is determined based on one or more of the following: Student Grade Point Average (GPA); The expected cost for the target student to complete the remaining requirements of the specific academic program; Student recruitment data; Salary data; Student graduation rate; Student browser history; The operation further includes: In response to determining that the target student (a) has enrolled in an academic program different from the specific academic program and (b) is not performing according to the minimum performance criteria: present a notification indicating that the specific academic program is recommended for the target student; Determine the set of academic units required to complete the specific academic program; Determine the number of academic units completed by the target student in the set of academic units required to complete the specific academic program; Wherein, the recommendation score is further based on the number of academic units completed by the target student in the set of academic units required to complete the specific academic program; The corresponding employment statistics include one or more of the following: salary statistics, the employability of the target student in the field associated with each of the multiple recommended academic programs, and the job market information corresponding to the field associated with each of the multiple recommended academic programs; The operation further includes: Simultaneously display in the graphical user interface the corresponding recommendation scores associated with each of the multiple recommended academic programs; For each of the multiple recommended academic programs, simultaneously display one or more of the following: Based on the set of characteristics associated with the target student, the estimated graduation time of the target student for each of the multiple recommended academic programs; The estimated financial investment for the target student to complete each of the multiple recommended academic programs; The average time to complete each of the multiple recommended academic programs; or The number of units required to complete each of the multiple recommended academic programs; and In response to receiving user input to select the specific academic program, display the specific coursework required to start the specific academic program.

9. The medium according to claim 1, Wherein, Displaying in a pop-up window on the first window in the graphical user interface the set of factors used to calculate the first recommendation score includes: Determine a plurality of factors used to calculate the first recommendation score, the plurality of factors including the set of factors and a second set of factors; Determine that the set of factors is more decisive than the second set of factors when calculating the first recommendation score; Display the set of factors in the pop-up window and do not display the second set of factors in the pop-up window.

10. A system for generating academic program recommendations and displaying academic program recommendations in a graphical user interface, Comprising: One or more devices, each device including at least one hardware processor; The system is configured to perform operations including the following: Populate a student information repository with student information from multiple sources, at least one of the multiple sources containing academic data associated with multiple previous students who have respectively enrolled in multiple academic programs; Based on a set of characteristics associated with a target student: Determine a first recommendation score associated with recommending a first academic program among the multiple academic programs to the target student, wherein determining the first recommendation score includes: (a) Identify previous students among the multiple previous students who have enrolled in the first academic program, (b) Assign a weight to the first academic program at least partially based on whether the previous student has completed the first academic program, and (c) Calculate the first recommendation score at least partially based on the weight assigned to the first academic program; Determine a second recommendation score associated with recommending a second academic program among the multiple academic programs to the target student; Identify a first threshold associated with the first academic program; Compare the first recommendation score with the first threshold associated with the first academic program; In response to determining that the first recommendation score meets the first threshold: Group the first academic program into multiple recommended academic programs; Identify a second threshold associated with the second academic program; Compare the second recommendation score with the second threshold associated with the second academic program, wherein the first threshold and the second threshold are different; In response to determining that the second recommendation score does not meet the second threshold: Group the second academic program into multiple non-recommended academic programs; Simultaneously display for the target student in a first window in a graphical user interface: The multiple recommended academic programs, without simultaneously displaying the multiple non-recommended academic programs; In response to receiving user input selecting an interface element associated with the first academic program: Display in a pop-up window on the first window of the graphical user interface a set of factors used to calculate the first recommendation score.

11. A method for generating academic program recommendations and displaying academic program recommendations in a graphical user interface, Comprising: Populate a student information repository with student information from multiple sources, at least one of the multiple sources containing academic data associated with multiple previous students who have respectively enrolled in multiple academic programs; Based on a set of characteristics associated with a target student: Determine a first recommendation score associated with recommending a first academic program among the multiple academic programs to the target student, wherein determining the first recommendation score includes: (a) Identify previous students among the multiple previous students who have enrolled in the first academic program, (b) Assign a weight to the first academic program at least partially based on whether the previous student has completed the first academic program, and (c) Calculate the first recommendation score at least partially based on the weight assigned to the first academic program; Determine a second recommendation score associated with recommending a second academic program among the multiple academic programs to the target student; Identify a first threshold associated with the first academic program; Compare the first recommendation score with the first threshold associated with the first academic program; In response to determining that the first recommendation score meets the first threshold: Group the first academic program into a plurality of recommended academic programs; Identify a second threshold associated with the second academic program; Compare the second recommendation score with the second threshold associated with the second academic program, wherein the first threshold and the second threshold are different; In response to determining that the second recommendation score does not meet the second threshold: Group the second academic program into a plurality of non-recommended academic programs; Simultaneously display for the target student in a first window of a graphical user interface: The plurality of recommended academic programs, without simultaneously displaying the plurality of non-recommended academic programs; In response to receiving user input selecting an interface element associated with the first academic program: Display in a pop-up window on the first window of the graphical user interface a set of factors used to calculate the first recommendation score; Wherein the method is executed by one or more devices, each device including at least one hardware processor.

Images