7. Student Performance Trajectory: Visualizes assessment trends, attendance records, and LMS assignment delays to explain student risk.
3. Student Risk Profile: Displays individual risk scores, SHAP-based explanations, and personalized intervention plans.
6. CSV Data Ingestion: Upload classroom datasets for validation, processing, and analytics recomputation.
5. Risk Filter View: Filters students by risk level to help educators quickly identify those needing support.
4. Student Risk Registry: Searchable student records with risk classifications, attendance, assessment trends, and engagement scores.
1. Dashboard Overview: Real-time classroom analytics with student risk indicators, attendance, and academic performance.
2. At-Risk Student Queue: Prioritizes students requiring early intervention with risk levels and recommended actions.

AI Driven Classroom Analytics and Student Success System

Inspiration

Each student has his or her own way of learning, and a lot of students need help with specific subjects. However, it may not be obvious for teachers or professors that a certain student has extreme difficulties succeeding in a particular class, before the results of examinations are presented. We wanted to establish a concept that would help educators identify those students and attempt to improve their learning experience.

Description

AI Driven Classroom Analytics and Student Success System is a concept that converts raw data concerning student performances into a set of easily accessible dashboards and analytical data. The system works on class/course attendance information, grades, engagement, and other metrics to identify patterns, trends, and outliers, highlight them for educators, and thereby support them in their efforts to improve the learning experience of their students.

Implementation

Our team has worked on the system’s architecture, the algorithms required for the analysis of the data, its dashboard, and the machine learning elements integral to its progress. As a system, AI Driven Classroom Analytics and Student Success System processes the set of uploaded CSV files containing student data, performs calculations on them, and outputs the results in the form of dashboard boards and cohorts.

Lessons Learned

One of the biggest challenges our team faced while working on the project was the necessity to update dashboards and make sure that they corresponded to changes in CSV files. Furthermore, the initial version of Machine Learning Intelligence interface and the cohort heatmap had issues with the display of certain data. This challenge was particularly instructive since it required the team to consider various problems that could emerge when the system is integrated with user data and address them (e.g., by implementing individual tests for each algorithm).

Significance

By working on this project, we have enhanced our understanding of data processing, analytics dashboards, artificial intelligence, and the ways in which such systems address the needs of users. In particular, the work on the AI Driven Classroom Analytics and Student Success System allowed us to understand how crucial it is to offer products that are data-driven, user-oriented, and analytically strong.

Future Work

We hope to continue working on the project in the future and focus on its critical importance for the improvement of education. We believe that there is a great amount of potential in the creation of an educational product with powerful artificial intelligence that would be capable of identifying students’ learning patterns and suggesting necessary adjustments to address their needs.