Academic Intervention Using Non-Academic Data for Early SAP Risk
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing academic intervention systems lack the ability to make proactive determinations about a student's likelihood of making satisfactory academic progress (SAP) during a current academic period when historical academic results are not yet available, leading to potential failure or expulsion due to delayed interventions.
Innovation Solution
A computer-based system that monitors non-academic data through APIs and applies a trained machine-learning model to predict SAP likelihood, generating timely interventions using academic and non-academic data, even when historical results are unavailable.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of time
If traditional academic intervention systems wait for historical academic results to identify at-risk students, then they can use established academic performance data for accurate predictions, but they fail to provide timely interventions before students fail to make satisfactory academic progress
Solution Approach 1:
The system performs preliminary actions by monitoring non-academic data and generating early warnings before academic results are available. The machine learning model predicts SAP likelihood using non-academic indicators in real-time, enabling interventions to be initiated proactively rather than reactively after academic failure occurs.
Solution Approach 2:
The system introduces non-academic data as an intermediary mediator between student behavior and academic outcomes. By monitoring non-academic indicators (such as engagement data, behavioral patterns, and external factors) through APIs, the system creates an early warning signal that bridges the gap between current student status and future academic performance.
2Adaptability or versatility
If the system uses only historical academic results to predict SAP likelihood, then the prediction methodology is simple and well-established, but it cannot provide proactive predictions when current academic period results are unavailable
Solution Approach 1:
The system achieves multi-functionality by creating a unified prediction model that can operate in multiple scenarios: using non-academic data during the current academic period when results are unavailable, and transitioning to use historical academic results when they become available. This universal approach eliminates the need for separate prediction systems for different time periods.
Solution Approach 2:
The system dynamically adapts its data sources and prediction methodology based on data availability. During the current academic period, it dynamically switches to monitoring non-academic data through APIs; once historical results are available, it dynamically transitions to using academic performance data. This dynamic behavior allows the system to maintain continuous predictive capability throughout the academic cycle.
Data Source
AI summary
Computer-based academic intervention techniques are disclosed. A system monitors an application programming interface (API) of a computer system. While monitoring the API during a current academic period, the system detects a change in non-academic data exposed by the API. Responsive to detecting the change in the non-academic data, the system identifies a subset of the non-academic data that is associated with a particular student, and applies a machine-learning model to the subset of non-academic data to obtain a predicted likelihood of the particular student making satisfactory academic progress (SAP) at an academic institution where the particular student is enrolled. Responsive to determining that the predicted likelihood of the particular student making SAP at the academic institution does not satisfy a threshold criterion, the system presents a warning in a graphical user interface that the particular student is at risk of not making SAP.