System and method for rule-based modeling of electronic transactions using artificial intelligence

Abstract

A method for rule-based modeling can include capturing a plurality of historical transaction data for a customer account. The method can also include extracting a plurality of item-level features from the plurality of historical transaction data. The method can also include providing the plurality of item-level features to a predictive machine learning model. The predictive machine learning model can be trained to identify patterns within the plurality of item-level features and generate a projected balance for the customer account based on the identified patterns. The method can also include transmitting the projected balance to a user interface.

Description

[0001] Cross-references to related applications

[0002] This application claims the benefit or priority of Indian Application No. 202411004605, filed January 23, 2024, and U.S. Nonprovisional Application No. 18 / 758,304, filed June 28, 2024, the entire contents of which are incorporated herein by reference. Technical Field

[0003] The various embodiments disclosed herein generally relate to artificial intelligence and machine learning-based techniques for managing electronic transactions and accounts. Background Technology

[0004] Administrators of computing systems may face challenges in analyzing and taking action based on data related to such systems. In some cases, administrators may be exposed to risks due to the inability to analyze data in a timely manner and take action based on that data.

[0005] Unless otherwise stated herein, the materials described in this section are not prior art to the claims of this application and are not recognized as prior art or suggestions of prior art by virtue of their inclusion in this section. Summary of the Invention

[0006] In one aspect, an exemplary embodiment of a method for rule-based modeling might include capturing multiple historical transaction data sets of a customer account. The method might also include extracting multiple item-level features from the multiple historical transaction data sets. The method might further include providing the multiple item-level features to a predictive machine learning model. The predictive machine learning model might be trained to identify patterns within the multiple item-level features and generate an expected balance for the customer account based on the identified patterns. The method might also include transmitting the expected balance to a user interface.

[0007] On the other hand, an exemplary embodiment of a system for rule-based modeling may include a memory storing instructions and a predictive machine learning model. The predictive machine learning model may be trained to identify patterns within a plurality of item-level features and generate an expected balance for a customer account based on the identified patterns. The system may also include a processor operatively connected to the memory and configured to execute the instructions to perform operations. These operations may include capturing a plurality of historical transaction data for the customer account. These operations may also include extracting the plurality of item-level features from the plurality of historical transaction data. These operations may further include providing the plurality of item-level features to the predictive machine learning model. These operations may also include transmitting the expected balance to a user interface by one or more processors.

[0008] Additional objects and advantages of the disclosed aspects will be set forth in part in the description which follows, and in part will be apparent from the description, or may be learned by practice of the disclosed aspects. The objects and advantages of the disclosed aspects will be realized and obtained by means of the elements and combinations particularly pointed out in the appended claims.

[0009] It should be understood that the foregoing general description and the following detailed description are merely exemplary and interpretive, and not limitations on the disclosed aspects as claimed. Attached Figure Description

[0010] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate a variety of exemplary aspects and, together with the description, serve to explain the principles of the disclosed aspects.

[0011] Figure 1 An exemplary environment for using a machine learning model for rule-based modeling, according to one or more embodiments, is described.

[0012] Figure 2 A flowchart depicts an exemplary method for rule-based modeling according to one or more embodiments.

[0013] Figure 3 A flowchart is depicted for an exemplary method for liquidity optimization according to one or more embodiments.

[0014] Figure 4 A flowchart is depicted for an exemplary method for report generation according to one or more embodiments.

[0015] Figure 5 A flowchart for training a machine learning model is depicted according to one or more embodiments.

[0016] Figure 6 An example of a computing device according to one or more embodiments is described.

[0017] It is worth noting that, for the sake of simplicity and clarity, certain aspects of the accompanying drawings depict general configurations of a wide variety of embodiments. Descriptions and details of well-known features and technologies may be omitted to avoid unnecessarily obscuring other features. Elements in the drawings are not necessarily drawn to scale; the dimensions of some features may be exaggerated relative to other elements to improve understanding of the exemplary embodiments. Detailed Implementation

[0018] The various aspects disclosed herein generally relate to artificial intelligence and machine learning-based technologies for managing electronic transactions and accounts, and particularly to the use of artificial intelligence and other machine learning models for decision-making. Therefore, a simple and seamless approach to better understand cash and risk may be feasible. Artificial intelligence models may be used to manage accounts, such as extracting data, generating queries, predicting account balances, predicting and implementing best practices for liquidity, and using natural language processing to generate reports. Artificial intelligence or machine learning models may generate scenarios for liquidity optimization based on a set of rules and automatically select the optimal scenario. Furthermore, sentiment analysis and forecasting may be used to predict ending balances, cash flows, etc.

[0019] By using the disclosed technologies, users (e.g., account owners, administrators, or managers) may optimize returns, minimize costs, and mitigate risks associated with current and future cash positions. Users may effectively manage cash resources, whether for short-term or long-term liquidity. The decision-making processes for achieving these outcomes, as well as the execution of these decisions, may be automated by using the technologies described herein.

[0020] As used herein, "machine learning model" generally encompasses instructions, data, and / or a model configured to receive input and apply one or more of weights, biases, classifications, or analyses to the input to generate an output. The output may include, for example, a classification of the input, an analysis based on the input, a design, process, prediction, or recommendation associated with the input, or any other suitable type of output. Machine learning models are typically trained using training data, such as empirical data, and / or samples of the input data, which are fed into the model to establish, adjust, or modify one or more aspects of the model, such as weights, biases, criteria used to form classifications or clusters, etc. The aspects of a machine learning model may operate on the input linearly, in parallel, via a network (e.g., a neural network), or via any suitable configuration.

[0021] The execution of a machine learning model may involve deploying one or more machine learning techniques, such as linear regression, logistic regression, random forests, gradient boosting machines (GBM), deep learning, and / or deep neural networks. Supervised and / or unsupervised training may be employed. For example, supervised learning may involve providing training data and corresponding labels, such as ground truth values. Unsupervised methods may include clustering, classification, etc. K-means clustering or K-nearest neighbors may also be used, and these may be supervised or unsupervised. A combination of K-nearest neighbors and unsupervised clustering techniques may also be used. Any suitable type of training may be used, such as randomized training, gradient boosting training, randomized seed training, recursive training, epoch-based or batch-based training, etc.

[0022] While the examples herein involve certain types of machine learning and artificial intelligence, it should be understood that the techniques according to this disclosure may be applicable to any suitable type of machine learning and artificial intelligence. It should also be understood that the examples above are merely illustrative. The techniques and solutions disclosed herein may be suitable for any suitable activity.

[0023] While financial applications and various finance-related aspects (e.g., account management and automation) have been described as illustrative examples in various aspects of the invention, these aspects are not limited to such examples. For instance, aspects of the invention can be implemented for other types of fields, such as any scenario related to optimizing data, predicting results, or generating reports.

[0024] Figure 1 An exemplary environment 100 is depicted that may be utilized in conjunction with the technologies presented herein. One or more user devices 112 may communicate across electronic network 110. One or more user devices 112 may be associated with a user, such as a user managing an account, an administrator of one or more components of environment 100, etc. As will be discussed in more detail below, one or more computing systems 102 may communicate across electronic network 110 with one or more other components of environment 100.

[0025] User equipment 112 may be configured to enable a user to access and / or interact with other systems within environment 100. For example, user equipment 112 may each be a computer system, such as a desktop computer, mobile device, tablet, etc. In some embodiments, user equipment 112 may include one or more electronic applications, such as programs, plugins, browser extensions, etc., installed on the memory of user equipment 112. In some embodiments, electronic applications may be associated with one or more other components within environment 100. For example, electronic applications may include one or more of system control software, system monitoring software, software development tools, etc.

[0026] In various embodiments, environment 100 may include data storage device 114 (e.g., a database). Data storage device 114 may include server systems and / or data storage systems, such as computer-readable storage, such as hard disks, flash drives, disks, etc. In some embodiments, data storage device 114 includes an application programming interface and / or interacts with the application programming interface for exchanging data with other systems, such as one or more other components of the environment. Data storage device 114 may include, and / or act as, a repository or source for storing historical transaction data, project-level features, inputs and / or outputs of machine learning or artificial intelligence models, generated reports, etc. (e.g., for the user of user device 112 or any other component of environment 100).

[0027] In some embodiments, components of environment 100 are associated with a common entity, such as a company or financial institution, a service provider, an account provider, etc. For example, in some embodiments, computing system 102 and data storage device 114 may be associated with a common entity. In some embodiments, one or more components of the environment are associated with a different entity than another component. For example, computing system 102 may be associated with a first entity (e.g., a service provider), while data storage device 114 may be associated with a second entity (e.g., a storage entity that provides storage services to the first entity). The systems and devices of environment 100 may communicate in any layout. As will be discussed herein, the systems and / or devices of environment 100 may communicate to perform one or more of the generation, training, or use of machine learning and / or artificial intelligence models, to manage accounts, and other activities.

[0028] As discussed in further detail below, computing system 102 may (i) perform one or more of the following on a machine learning model configured to manage an account: generating, storing, training, or using the model. Computing system 102 may include a machine learning model and / or instructions associated with it, such as instructions for generating, training, or using the machine learning model. Computing system 102 may include instructions for retrieving, adjusting, or / or manipulating the display of user device 112 to output, for example, results adjusted based on the machine learning model. Computing system 102 may include training data, such as historical transaction data and / or item-level features, and may include ground truth, for example, (i) training historical transaction data and (ii) training item-level feature data to generate output.

[0029] like Figure 1 The depicted computing system 102 may include a capture module 104. In various embodiments, the capture module 104 is configured to capture historical transaction data of a customer account. This historical transaction data may be received by the computing system 102 via network 110.

[0030] The computing system 102 may also include an extraction module 106. In various embodiments, the extraction module 106 may be configured to extract item-level features from historical transaction data. Item-level features may be stored in data storage device 114 and retrieved for use by components of the computing system 102.

[0031] like Figure 1 The computing system 102, as depicted, may also include a machine learning module 108. In some embodiments, systems or devices other than the computing system 102 are used to generate and / or train machine learning models. For example, such a system may include instructions for generating machine learning models, training data, and ground truth values, and / or instructions for training machine learning models. The resulting trained machine learning model may then be provided to the computing system 102.

[0032] Typically, a machine learning model comprises a set of variables, such as nodes, neurons, and filters, which are tuned through the application of training data, for example, by being weighted or biased to different values. In supervised learning, for example, where the true values ​​of the provided training data are known, training might be performed by feeding samples of the training data into the model, whose variables are set to initial values, for example, randomly, based on Gaussian noise, or pre-trained models. The output might be compared to the true values ​​to determine the error, which might then be backpropagated through the model to adjust the values ​​of the variables.

[0033] Training may be conducted in any suitable manner, such as in batches, and may include any suitable training methods, such as stochastic or non-stochastic gradient descent, gradient boosting, random forests, etc. In some embodiments, a portion of the training data may be retained during training, and / or used to validate the trained machine learning model, for example, by comparing the output of the trained model with the ground truth of that portion of the training data to evaluate the accuracy of the trained model. The training of the machine learning model may be configured to enable the machine learning model to learn item-level features, and / or associations in historical transaction data, and / or to identify patterns, thereby configuring the trained machine learning model to generate output results.

[0034] In a variety of embodiments, the variables of a machine learning model may be correlated with each other in any suitable layout to generate output. For example, in some embodiments, the machine learning model may include a data processing architecture configured to identify, isolate, and / or extract features from one or more of historical transaction data and project-level features. For example, the machine learning model may include one or more convolutional neural networks ("convolutional neural network CNNs") configured to identify patterns in project-level features, and may include additional architectures, such as connection layers, neural networks, etc., configured to determine relationships between the identified patterns to output predictions, actions to be taken, or reports generated.

[0035] In some embodiments, the machine learning model of computing system 102 may include a recurrent neural network (“RNN”). Typically, an RNN is a type of feedforward neural network that may be well-suited for processing input sequences. In some embodiments, the machine learning model may include a Long Short-Term Memory (“LSTM”) model and / or a sequence-to-sequence (“Sequence-to-Sequence Seq2Seq”) model. The LSTM model may be configured to generate output from samples that take into account at least some previous samples and / or outputs. The Seq2Seq model may be configured, for example, to receive a sequence of item-level features and output a prediction, action to be taken, expected balance, report, etc.

[0036] like Figure 1The depicted environment 100 may also include an electronic network 110. In various embodiments, the electronic network 110 may be a wide area network ("WAN"), a local area network ("LAN"), a personal area network ("PAN"), etc. In some embodiments, the electronic network 110 includes the Internet, and information and data provided between various systems occur online. "Online" may mean connecting to or accessing source data or information from a location geographically distant from other devices or networks coupled to the Internet. Alternatively, "online" may mean connecting to or accessing an electronic network (wired or wireless) via a mobile communication network or device. The Internet is a global computer network system, a network of networks in which one party at a computer or other device connected to the network can obtain information from any other computer and communicate with another party at other computers or devices. The most widely used part of the Internet is the World Wide Web (often abbreviated as "WWW" or simply "Web"). A “website page” typically encompasses location, data storage device, etc., which is hosted and / or operated by a computer system to be accessible online, and may include data configured to cause programs such as web browsers to perform operations such as sending, receiving or processing data, generating visual displays, and / or interactive interfaces.

[0037] Despite Figure 1 While depicted as separate components, it should be understood that components or portions of components in environment 100 may be integrated with or incorporated into one or more other components in some embodiments. In another example, computing system 102 may be integrated into a data storage system. The data storage system may be configured to communicate with and / or receive / transmit data across electronic network 110 and other components of environment 100. In some embodiments, the operation or aspects of one or more of the components discussed above may be distributed across one or more other components. Any suitable layout and / or integration of a wide variety of systems and devices may be used in environment 100.

[0038] Other aspects of the machine learning model, and / or how to leverage it to process historical account data, and / or other aspects of project-level features, are discussed in more detail in the methodologies below. In these methodologies, a wide variety of actions may be described as being performed by… Figure 1The components of the environment 100 discussed above may execute or implement instructions or actions, such as computing system 102, user equipment 112, or components thereof. However, it should be understood that in various embodiments, various components of the environment 100 discussed above may execute instructions or perform actions, including those discussed below. Actions performed by a device may be considered as being performed by a processor, actuator, etc., associated with that device. Furthermore, it should be understood that in various embodiments, various steps may be added, omitted, and / or reordered in any suitable manner.

[0039] Figure 2 An exemplary method 200 for rule-based modeling is illustrated. Exemplary method 200 begins with step 205, where multiple historical transaction data points for a customer account are captured. In this example, multiple historical transaction data points might include fund transfers, purchases, account credits, payments, etc. Historical transaction data may represent any feasible time period, such as days, weeks, or years. The time period for which historical transaction data is captured may be the duration of the account, but the computing system (e.g., such as...) Figure 1 The computing system 102 described herein may capture a portion of historical transaction data during the account's lifetime for processing. For example, if the account has been open for 2 years, the computing system may capture historical transaction data from the most recent 3 months as a subset of the total historical transaction data captured for processing. At step 210, multiple item-level features are extracted from the multiple historical transaction data. In an example, the multiple item-level features may include numerical and / or textual data associated with the historical transaction data. Such numerical and / or textual data may represent monetary amounts, identifiers associated with the account associated with each transaction, etc. In a variety of embodiments, item-level features are data that may be processed as such from historical transaction data that provides the history of a customer's account.

[0040] At step 215, multiple item-level features are provided to a predictive machine learning model. The predictive machine learning model may be trained to identify patterns within the multiple item-level features and generate an expected balance for the customer account based on the identified patterns. In one instance, the predictive machine learning model may identify patterns such as a decrease in the account balance following a series of historical actions on the account. In this way, it may predict that if similar actions are taken on the account, the account balance may decrease in a similar manner. In other instances, the predictive machine learning model may identify patterns associated with relevant events. In a specific instance, the account balance may have historically increased with each interest rate change. Therefore, the predictive machine learning model may be trained to identify those patterns among the factors affecting the customer account, allowing the predictive machine learning model to output an expected balance for the customer account given a current or simulated set of situations. Exemplary method 200 ends at step 220, where the expected balance may be transmitted to a user interface (e.g., as shown in the image). Figure 1 The user interface of user device 112 depicted in the figure.

[0041] Figure 3 An exemplary method 300 for liquidity optimization is illustrated. Exemplary method 300 begins with step 305, where multiple historical transaction data points for a customer account are captured. In this example, the multiple historical transaction data points might include fund transfers, purchases, account credits, payments, etc., as described above. Figure 2 As described, historical transaction data may represent a record of actions taken about a customer account and may be captured relative to the relevance of the data used for processing (e.g., from a certain time period). At step 310, multiple item-level features are extracted from the multiple historical transaction data. In an example, the multiple item-level features may include numerical and / or textual data associated with the historical transaction data. In an example, extracting item-level features from historical transaction data may facilitate computational systems (e.g., such as...) Figure 1 The computing system 102 described herein or the machine learning model, such as the machine learning model described herein, is used for processing.

[0042] At step 315, multiple item-level features are provided to a generative machine learning model. This model may be trained to recognize patterns within these item-level features and generate a set of liquidity rules for the customer account based on the identified patterns. In various embodiments, these liquidity rules may take the form of computer instructions or operations to perform actions on the customer account. In other instances, the set of liquidity rules may be the output of a machine learning model and then formatted into natural language by a computing system, such as using an artificial intelligence model, which may be understood by the user as a set of steps or actions to be taken.

[0043] Therefore, in this instance, this set of liquidity rules might be applied to a client account. As described above, this set of liquidity rules might be automatically applied to the client account via a computational system. In such instances, optimized trading actions might be executed on the client account based on this set of liquidity rules. In a variety of embodiments, optimized trading actions might be fed to predictive machine learning models (e.g., as described above regarding...). Figure 2 The described model). The predictive machine learning model may be further trained to identify patterns within optimized trading actions and generate predicted balances for client accounts based on the identified patterns. In such instances, the predictive machine learning model may predict the account balance of a client account based on simulated execution of optimized trading actions on the client account. Exemplary method 300 ends at step 320, where the set of liquidity rules may be transmitted to the user interface (e.g., as described). Figure 1 (The user interface of user equipment 112 depicted in the figure). In this example, the predicted balance may also be transmitted to the user interface.

[0044] Figure 4 An exemplary method 400 for report generation is illustrated. Exemplary method 400 begins at step 405, where multiple historical transaction data points for a customer account are captured, such as those captured using any methods described herein. In an example, the multiple historical transaction data points may include fund transfers, purchases, account credits, payments, etc. At step 410, multiple item-level features are extracted from the multiple historical transaction data points. In an example, the multiple item-level features may include numerical and / or textual data associated with the historical transaction data. At step 415, the multiple item-level features and a set of user preferences are provided to a natural language machine learning model. In an example, the set of user preferences may include parameters for the final generated customer account report. In a specific instance, such parameters may include selecting a time period as the report's subject, selecting a specific transaction type to be reflected in the report, etc.

[0045] A natural language machine learning model may be trained to recognize patterns within multiple item-level features and generate one or more customer account reports based on the identified patterns and the set of user preferences. In an instance, the natural language machine learning model may be an artificial intelligence model. In a variety of embodiments, the natural language machine learning model may leverage a natural language processor or an artificial intelligence model to generate customer account reports using language that the user will understand, essentially describing the identified patterns in natural language. In an instance, the customer account report may describe to the user what happened to the customer account and why and how certain circumstances or factors affected the customer account. Exemplary method 400 ends at step 420, where one or more customer account reports may be transmitted to a user interface (e.g., such as...). Figure 1The user interface of user device 112 depicted in the figure.

[0046] Figure 5 A flowchart for training a machine learning model is depicted. For example... Figure 5 As shown in flowchart 500, training data 512 may include one or more of stage inputs 514 and known results 518 associated with the machine learning model to be trained. Stage inputs 514 may come from any applicable source, including the components or sets shown in the accompanying figures provided herein. Known results 518 may be included for machine learning models generated based on supervised or semi-supervised training. Unsupervised machine learning models may not use known results 518 for training. Known results 518 may include known or expected outputs for future inputs that are similar to or belong to the same category as stage inputs 514 that do not have corresponding known outputs.

[0047] Training data 512 and training algorithm 520 may be provided to training component 530, which may apply training data 512 to training algorithm 520 to generate a trained machine learning model 550. According to one implementation, training component 530 may be provided with a comparison result 516 that compares the previous output of the corresponding machine learning model to retrain the machine learning model using the previous result. The comparison result 516 may be used by training component 530 to update the corresponding machine learning model. Training algorithm 520 may utilize machine learning networks and / or models, including but not limited to deep learning networks such as Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Fully Convolutional Networks (FCNs), and Recurrent Neural Networks (RCNs); probabilistic models such as Bayesian networks and graphical models; and / or discriminative models such as decision forests and maximum margin methods. The output of flowchart 500 may be the trained machine learning model 550.

[0048] The machine learning models disclosed herein may be trained by adjusting one or more weights, layers, and / or biases during the training phase. During the training phase, historical or simulated data may be provided as input to the model. The model may adjust one or more of its weights, layers, and / or biases based on such historical or simulated information. Based on training, the adjusted weights, layers, and / or biases may be configured in a production version of the machine learning model (e.g., a trained model). Once trained, the machine learning model may output machine learning model outputs based on the topics disclosed herein. According to one implementation, one or more machine learning models disclosed herein may be continuously updated based on feedback associated with the use or implementation of the machine learning model outputs.

[0049] It should be understood that the aspects in this disclosure are merely exemplary, and other aspects may include a wide variety of combinations of features from other aspects, as well as additional or fewer features.

[0050] Generally, any process or operation discussed in this disclosure that is understood to be computer-executable, such as the process shown in the flowcharts disclosed herein, may be executed by one or more processors of a computer system, such as any system or device in the exemplary environment disclosed herein as described above. A process or process step executed by one or more processors is also referred to as an operation. One or more processors may be configured to execute such a process by accessing instructions (e.g., software or computer-readable code) that, when executed by one or more processors, cause the one or more processors to perform the process. The instructions may be stored in the memory of the computer system. The processor may be a central processing unit (CPU), a graphics processing unit (GPU), or any suitable type of processing unit.

[0051] A computer system, such as a system or apparatus that implements the processes or operations described in the examples above, may include one or more computing devices, such as one or more of the systems or apparatuses disclosed herein. One or more processors of the computer system may be included in a single computing device or distributed across multiple computing devices. The memory of the computer system may include the respective memory of each of the multiple computing devices.

[0052] Figure 6 This is a simplified functional block diagram of a computer 600 according to an exemplary aspect of this disclosure, which may be configured as an apparatus for performing the methods disclosed herein. For example, computer 600 may be configured as a system according to an exemplary aspect of this disclosure. In various aspects, any system herein may be computer 600, which includes, for example, a data communication interface 620 for packet data communication. Computer 600 may also include a central processing unit (“CPU”) 602 in the form of one or more processors for executing program instructions. Computer 600 may include an internal communication bus 608 and a storage unit 606 (such as ROM, HDD, SDD, etc.) that may store data on a computer-readable medium 622, although computer 600 may receive programming and data via network communication.

[0053] Computer 600 may also have memory 604 (e.g., RAM) that stores instructions 624 for performing the techniques presented herein, for example, as referenced. Figures 2 to 4The described method, although instruction 624 may be temporarily or permanently stored in other modules of computer 600 (e.g., processor 602, and / or computer-readable medium 622). Computer 600 may also include input and output ports 612, and / or a display 610, for connection to input and output devices such as a keyboard, mouse, touchscreen, monitor, display, etc. A wide variety of system functions may be implemented in a distributed manner on multiple similar platforms to distribute the processing load. Alternatively, the system may be implemented through appropriate programming of a single computer hardware platform.

[0054] The programmatic aspect of this technology may be considered a "product" or "artifact," typically in the form of executable code and / or associated data, carried or embodied on a machine-readable medium. "Storage" media include any or all tangible memory or associated modules of computers, processors, etc., such as various types of semiconductor memory, magnetic tape drives, disk drives, etc., which may provide non-transitory storage for software programming at any time. All or part of the software may sometimes be communicated via the Internet or various other telecommunications networks. For example, such communication may enable the loading of software from one computer or processor to another, such as from a management server or host computer of a mobile communication network to a server's computer platform, and / or from a server to a mobile device. Therefore, another class of media that may carry software elements includes light waves, radio waves, and electromagnetic waves, such as those used through physical interfaces between local devices, via wired and optical terrestrial networks, and via various air links. Physical elements carrying such waves, such as wired or wireless links, optical links, etc., may also be considered as media carrying software. As used herein, unless limited to non-transitory tangible "storage" media, terms such as "computer or machine readable medium" refer to any medium that participates in providing instructions to a processor for execution.

[0055] Although the disclosed methods, devices, and systems are described by way of example with reference to transmitted data, it should be understood that the disclosed aspects may be applicable to any environment, such as desktop or laptop computers, car entertainment systems, home entertainment systems, etc. Furthermore, the disclosed aspects may be applicable to any type of Internet protocol.

[0056] It should be recognized that in the foregoing description of exemplary aspects of the invention, various features of the invention are sometimes combined in a single aspect, drawing, or description thereof for the purpose of simplifying the disclosure and aiding in understanding one or more of the various aspects of the invention. However, this approach of the disclosure should not be construed as reflecting an intention that the claimed invention requires more features than expressly recited in each claim. Rather, as reflected in the appended claims, the innovating aspect lies in fewer than all features of a single foregoingly disclosed aspect. Therefore, the claims following the detailed description are thus expressly incorporated into this detailed description, wherein each claim exists on its own as a separate aspect of the invention.

[0057] Furthermore, while some aspects described herein include but do not include all features included in other aspects, combinations of features from different aspects are intended to be within the scope of the invention and form different aspects, as understood by those skilled in the art. For example, in the appended claims, any claimed aspect may be used in any combination.

[0058] Therefore, while certain aspects have been described, those skilled in the art will recognize that other and further modifications may be made without departing from the spirit of the invention, and it is intended that all such changes and modifications fall within the scope of the invention. For example, functions may be added to or removed from the block diagram, and operations may be interchanged between functional blocks. Within the scope of the invention, operations may be added to or removed from the described methods.

[0059] The subject matter disclosed above should be considered illustrative rather than restrictive, and the appended claims are intended to cover all such modifications, improvements, and other implementations that fall within the true spirit and scope of this disclosure. Therefore, to the fullest extent permitted by law, the scope of this disclosure will be determined by the broadest possible interpretation of the appended claims and their equivalents, and should not be bound or limited by the foregoing detailed description. While a wide variety of specific embodiments of this disclosure have been described, it will be apparent to those skilled in the art that many more specific embodiments are possible within the scope of this disclosure. Therefore, this disclosure is not limited except as provided in the appended claims and their equivalents.

Claims

1. A computer-implemented method for rule-based modeling, the method comprising: Multiple historical transaction data points of a customer account are captured by one or more processors; The one or more processors extract multiple project-level features from the multiple historical transaction data; The one or more processors provide the plurality of item-level features to a predictive machine learning model, which is trained to identify patterns within the plurality of item-level features and generate an expected balance for the customer account based on the identified patterns. as well as The expected balance is transmitted to the user interface by the one or more processors.

2. The computer implementation method according to claim 1, further comprising: The one or more processors provide the plurality of project-level features to a generative machine learning model, which is trained to identify patterns within the plurality of project-level features and generate a set of liquidity rules for the customer account based on the identified patterns. as well as The set of liquidity rules is transmitted to the user interface by the one or more processors.

3. The computer implementation method according to claim 2, further comprising: The one or more processors apply the set of liquidity rules to the customer account; as well as Optimized trading actions are performed by the one or more processors on the client account based on the set of liquidity rules.

4. The computer implementation method according to claim 3, further comprising: The optimized trading action is provided to the predictive machine learning model by the one or more processors. The predictive machine learning model is trained to identify patterns within the optimized trading action and generate a predicted balance for the customer account based on the identified patterns. as well as The predicted balance is transmitted to the user interface by the one or more processors.

5. The computer implementation method according to claim 1, further comprising: The one or more processors provide the plurality of item-level features and a set of user preferences to a natural language machine learning model, which is trained to identify patterns within the plurality of item-level features and to generate one or more customer account reports based on the identified patterns and the set of user preferences. as well as The one or more processors transmit the one or more customer account reports to the user interface.

6. The computer implementation method according to claim 5, wherein the natural language machine learning model is an artificial intelligence model.

7. The computer implementation method according to claim 1, wherein the plurality of historical transaction data includes at least one of fund transfer, purchase, account credit, or payment.

8. The computer implementation method according to claim 1, wherein the plurality of project-level features include numerical data and / or text data associated with the plurality of historical transaction data.

9. A system for rule-based modeling, the system comprising: The memory stores instructions and a predictive machine learning model, which is trained to identify patterns within multiple item-level features and generate an expected balance for a customer account based on the identified patterns. and A processor, operatively connected to the memory and configured to execute the instructions to perform operations including: The processor captures multiple historical transaction data points of the customer account; The processor extracts the multiple project-level features from the multiple historical transaction data; The processor provides the plurality of project-level features to the predictive machine learning model; as well as The processor transmits the estimated balance to the user interface.

10. The system according to claim 9, further comprising: The processor provides the plurality of project-level features to a generative machine learning model, which is trained to identify patterns within the plurality of project-level features and generate a set of liquidity rules for the customer account based on the identified patterns. as well as The processor transmits the set of flow rules to the user interface.

11. The system of claim 10, further comprising: The processor applies the set of liquidity rules to the customer account; as well as The processor, and on the customer account, executes optimized trading actions based on the set of liquidity rules.

12. The system of claim 11, further comprising: The processor provides the optimized transaction actions to the predictive machine learning model, which is trained to identify patterns within the optimized transaction actions and generate a predicted balance for the customer account based on the identified patterns. as well as The processor transmits the predicted balance to the user interface.

13. The system according to claim 9, further comprising: The processor provides the plurality of item-level features and a set of user preferences to a natural language machine learning model, which is trained to recognize patterns within the plurality of item-level features and to generate one or more customer account reports based on the recognized patterns and the set of user preferences. as well as The processor transmits the one or more customer account reports to the user interface.

14. The system of claim 13, wherein the natural language machine learning model is an artificial intelligence model.

15. The system of claim 9, wherein the plurality of historical transaction data includes at least one of fund transfers, purchases, account credits, or payments.

16. The system of claim 9, wherein the plurality of project-level features include numerical data and / or text data associated with the plurality of historical transaction data.

17. A non-transitory computer-readable medium storing instructions that, when executed by one or more processors, perform operations including: Multiple historical transaction data points of a customer account are captured by one or more processors; The one or more processors extract multiple project-level features from the multiple historical transaction data; The one or more processors provide the plurality of item-level features to a predictive machine learning model, which is trained to identify patterns within the plurality of item-level features and generate an expected balance for the customer account based on the identified patterns. as well as The expected balance is transmitted to the user interface by the one or more processors.

18. The non-transitory computer-readable medium of claim 17, further comprising: The one or more processors provide the plurality of project-level features to a generative machine learning model, which is trained to identify patterns within the plurality of project-level features and generate a set of liquidity rules for the customer account based on the identified patterns. as well as The set of liquidity rules is transmitted to the user interface by the one or more processors.

19. The non-transitory computer-readable medium of claim 17, wherein the plurality of historical transaction data includes at least one of fund transfers, purchases, account credits, or payments.

20. The non-transitory computer-readable medium of claim 17, wherein the plurality of project-level features include numerical data and / or textual data associated with the plurality of historical transaction data.

Images