Student Performance Analytics Engine

Student Analytics Engine is a data-driven web application that analyzes student performance from Excel/CSV files and automatically generates insights such as class average, toppers, defaulters, and risk categories. The system uses a high-performance C analytics engine for fast computation and a Python (Flask) backend to expose the results to a web-based dashboard with tables and charts. Teachers can upload a class file and instantly view visual reports without needing any technical knowledge.
Through this project, I learned how to design a multi-layer system that integrates low-level computation (C), backend APIs (Python/Flask), and frontend visualization (HTML, JavaScript, Chart.js). I also gained hands-on experience with file processing, REST APIs, deployment, and version control using Git and GitHub.

Implemented a JSON export layer that outputs complete academic analytics, including class statistics, student CGPA, and risk classifications, in a structured machine-readable format. This enables seamless integration with web and mobile applications.

Integrated an academic risk prediction layer that classifies students into safe, medium-risk, and high-risk categories based on their CGPA. The system now identifies at-risk students and highlights those who may require academic intervention, along with class-wide performance metrics.
Extended the analytics engine with a data export layer that generates structured CSV reports containing CGPA and academic risk classifications. This enables the system’s results to be consumed by external dashboards, apps, and further data pipelines.

implemented a weighted CGPA calculation model that converts attendance and exam scores into a standardized academic performance metric. The engine now produces per-student performance scores for further analysis.

Added class-level analytics to the engine, including average CGPA calculation, topper identification, and defaulter detection. The system now produces comparative performance insights across all students, enabling ranking and academic benchmarking.

Implemented the core data layer by defining a Student data model and building a CSV loader in C. The engine now reads real academic records from a structured dataset and loads them into memory, forming the foundation for analytics and performance prediction.

I am working on a C-based Student Performance Analytics Engine that analyzes academic data to estimate CGPA, identify at-risk students, and generate performance insights.