How shiv1810/student-performance-prediction-app works
Main Components
• iOS App Client: The overall mobile application includes several modules:
• User Authentication and Profile (SignIn_FacultyView.swift, SignIn_StudentView.swift)
• Faculty Dashboard (Faculty Dashboard directory) for CRUD operations and analysis.
• Student Dashboard (Student Dashboard directory) for viewing marks, timetables, and performance.
• Various views for charts and stats (e.g., subdirectories in BookstoreStategist, Charts).
• Supporting screens (AttendanceView.swift, ProfileView.swift, etc.)
• Firebase/Firestore Backend: Represent the cloud backend components handling authentication, real-time database, and storage of user and app data.
• CoreML Prediction Engine: Represent the integrated CoreML model (files such as SPPA.mlmodel and my_model.mlmodel) and its conversion/integration from a Python-trained scikit-learn model.
• Graph/Visualization Library: Mark the component that renders charts (many view files in “Charts” and “BookstoreStategist/basics tutorial” directories).
Interactions and Data Flow
• Data flow from the iOS UI (especially in dashboard views) to the CoreML model where predictions are computed.
• Rendering of dynamic visualization with the graph library by showing the flow from processed data (either entered by the user or retrieved from the backend) to the view layer.
Architectural Patterns
• The app also demonstrates modularization by separating different dashboards and tutorials into distinct modules (Faculty, Student, Books/Charts).
Relevant Technologies and Frameworks
• Xcode/Swift and SwiftUI for the front-end.
• Firebase and Firestore for the backend services.
• CoreML for machine learning inference.
• The Graph library (such as Charts or Core Plot) for visualizations.
• Any additional libraries used across the project (e.g., Swift Package Manager managed dependencies inside SPPA.xcodeproj).
• iOS App Layer:
• User Interface: Screens for sign-in, dashboards (student and faculty), chart displays.
• Business Logic: Models and view models handling core data (book sales, marks, effort metrics).
• Services Interaction: API calls to Firebase, data binding to the visualization components.
• Backend Services:
• Firebase Authentication and Firestore: Handling user data, real-time updates, and CRUD operations.
• Analytics and Prediction:
• CoreML Integration: Block depicting the CoreML model (converted from Python scikit-learn training) processing input parameters to generate performance predictions.
• Visualization:
• Graph Library: Represent the layer that transforms data into charts (bar charts, line charts, pie charts, etc.).