Non-Cognitive Assessment System for Applicant Success Prediction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional educational institution admission processes primarily focus on cognitive metrics, neglecting non-cognitive variables that are crucial for predicting an applicant's success in completing educational programs, leading to a lack of functionality in assessing and addressing risk factors impacting non-cognitive attributes.
Innovation Solution
A method and system that utilize a computing device to execute an assessment tool to identify non-cognitive variables, risk factors, and recommend actions for applicants to improve their likelihood of success by integrating applied people analytics and psychological science, providing tailored recommendations to educational institutions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional admission processes focus only on cognitive metrics, then the admission process remains simple and quick, but the prediction of applicant success is inaccurate
Solution Approach 1:
The assessment process is segmented into distinct modules: cognitive assessment components and non-cognitive assessment components. The non-cognitive assessment is further divided into specific variable evaluations (motivation, resilience, social skills, etc.). This segmentation allows the system to handle complex multi-dimensional data while maintaining organized processing structure.
Solution Approach 2:
The patent transitions from one-dimensional cognitive assessment to two-dimensional assessment by adding non-cognitive variables as a new dimension. The analysis engine processes both cognitive and non-cognitive dimensions simultaneously to produce comprehensive success predictions, thereby improving accuracy without overwhelming complexity.
2Reliability
If non-cognitive variables are assessed, then the likelihood of requirement completion is improved, but the assessment process becomes more complex
Solution Approach 1:
The analysis engine serves as an intermediary component that processes both cognitive and non-cognitive assessment data. It mediates between the raw assessment inputs and the final success prediction outputs, transforming complex multi-variable data into actionable insights and recommendations while managing system complexity.
Solution Approach 2:
The system incorporates feedback mechanisms where the analysis engine continuously refines predictions based on the relationship between non-cognitive variables and completion likelihood. The generated recommendations are fed back into the assessment process, allowing iterative improvement of prediction accuracy while managing complexity through structured feedback loops.
3Measurement precision
If multiple assessment variables are collected, then the prediction of success is more accurate, but the time required for assessment increases
Solution Approach 1:
The assessment tool is designed to collect and process non-cognitive variables during the application review phase, before final admission decisions are made. This preliminary action allows the analysis engine to pre-process and weight the variables, reducing the time required for final assessment decisions while maintaining high prediction accuracy.
Solution Approach 2:
The system dynamically adjusts the weightings and processing depth of different assessment variables based on the specific program requirements and applicant profiles. By changing parameter settings adaptively, the system maintains high accuracy for complex cases while using simplified processing for straightforward evaluations, thereby reducing overall assessment time.
Data Source
AI summary
A method for generating recommendations for actions to be executed to improve non-cognitive metrics impacting likelihood of requirement completion includes executing, by a computing device, an assessment tool for assessing at least one non-cognitive variable of an applicant. The method includes identifying, by an analysis engine executed by the computing device, at least one risk factor for non-persistence by the applicant. The method includes identifying, by the analysis engine, a likelihood of success by the applicant in completing at least one requirement of an educational institution. The method includes identifying, by the analysis engine, at least one action to recommend for execution, execution of the at least one action satisfying a threshold level of likelihood of improving the likelihood of success. The method includes providing, by the analysis engine, to the educational institution, the identified at least one action.