Experience the complete prediction workflow directly in the browser.
No installation required.
ScholarIQ is a machine-learning-based student performance prediction system designed to estimate a student's final academic score using important academic and behavioral indicators.
Instead of waiting for final examination results, ScholarIQ provides an early performance forecast and highlights factors that may influence the student's outcome.
Student Data
↓
Machine Learning Model
↓
Predicted Score
↓
Performance Analysis
↓
Personalized Recommendations
| Feature | Description |
|---|---|
| Student Profile | Enter student information and academic details |
| Academic Analysis | Analyze assignments, internal marks and study hours |
| Attendance Analysis | Calculate and visualize attendance percentage |
| ML Prediction | Predict final academic score |
| Grade Prediction | Convert predicted score into academic grade |
| Performance Breakdown | Visualize the contribution of important factors |
| Recommendations | Generate improvement suggestions |
| Report Generation | Download the student's prediction report |
| Live Preview | Dashboard updates instantly as values change |
| Modern UI | Dark, responsive academic intelligence dashboard |
The first screen allows users to enter the student's profile and academic information.
- Student name
- Gender
- Age
- Assignments submitted
- Internal marks
- Self-study hours
- Previous failures
- Extra classes
- Total classes conducted
- Classes attended
- Automatically calculated attendance percentage
Once the required information is entered, the user can select:
Predict Final Score →
to generate the prediction.
ScholarIQ — Student input and prediction dashboard
After prediction, ScholarIQ presents the results through an interactive analytics dashboard.
Displays:
- Predicted score
- Grade
- Performance category
- Projected final score
The system visualizes individual factors including:
- Assignments
- Internal marks
- Attendance
- Study hours
- Discipline
The application automatically generates actionable recommendations based on the student's profile.
For example:
Submit all assignments on time.
Focus more on internal assessments.
ScholarIQ — Prediction, performance analysis and recommendations
┌─────────────────────────┐
│ Enter Student Profile │
└────────────┬────────────┘
↓
┌─────────────────────────┐
│ Enter Academic Data │
│ │
│ • Assignments │
│ • Internal Marks │
│ • Study Hours │
│ • Previous Failures │
└────────────┬────────────┘
↓
┌─────────────────────────┐
│ Enter Attendance │
│ │
│ Total Classes │
│ Classes Attended │
└────────────┬────────────┘
↓
┌─────────────────────────┐
│ Predict Final Score │
└────────────┬────────────┘
↓
┌─────────────────────────┐
│ ML Prediction │
└────────────┬────────────┘
↓
┌─────┴─────┐
↓ ↓
┌────────────┐ ┌────────────────┐
│ Score & │ │ Performance │
│ Grade │ │ Breakdown │
└─────┬──────┘ └───────┬────────┘
│ │
└────────┬───────┘
↓
┌─────────────────────────┐
│ Personalized │
│ Recommendations │
└────────────┬────────────┘
↓
┌─────────────────────────┐
│ Download Student Report │
└─────────────────────────┘
The project follows a complete machine learning workflow:
Raw Dataset
↓
Data Cleaning
↓
Feature Engineering
↓
Exploratory Data Analysis
↓
Feature Selection
↓
Model Training
↓
Model Evaluation
↓
Model Serialization
↓
Streamlit Deployment
The trained model is stored as:
Model/student_model.pkl
ScholarIQ uses the following student-related attributes:
| Feature | Description |
|---|---|
| Gender | Student gender |
| Age | Student age |
| Assignments | Number of assignments submitted |
| Internal Marks | Internal assessment performance |
| Attendance | Calculated attendance percentage |
| Self Study Hours | Daily study duration |
| Previous Failures | Number of previous academic failures |
| Extra Classes | Whether the student attends extra classes |
The application generates:
A final academic score on a 0–100 scale.
The predicted score is converted into an academic grade.
The application classifies the student's predicted performance.
The system identifies areas where the student can improve.
| Score | Grade | Performance |
|---|---|---|
| 90–100 | A+ | Outstanding |
| 80–89 | A | Excellent |
| 70–79 | B | Very Good |
| 60–69 | C | Good |
| 50–59 | D | Average |
| < 50 | F | Needs Improvement |
A student enters:
Student Name : Pardi
Age : 20
Assignments : 5 / 10
Internal Marks : 5 / 10
Attendance : 90%
Study Hours : 3 hrs/day
Previous Failures : 0
Extra Classes : Yes
ScholarIQ generates:
┌─────────────────────────────┐
│ PREDICTION RESULT │
│ │
│ 50 / 100 │
│ │
│ GRADE D · AVERAGE │
└─────────────────────────────┘
followed by:
Performance Breakdown
────────────────────────────
Assignments █████ 50
Internal Marks █████ 50
Attendance █████████ 90
Study Hours ███ 30
Discipline ██████████ 100
and personalized recommendations.
┌───────────────────┐
│ Student Input │
└─────────┬─────────┘
│
▼
┌───────────────────┐
│ Feature Processing│
└─────────┬─────────┘
│
▼
┌───────────────────┐
│ Trained ML Model │
│ student_model.pkl │
└─────────┬─────────┘
│
▼
┌───────────────────┐
│ Score Prediction │
└─────────┬─────────┘
│
┌───────────────────┼───────────────────┐
│ │ │
▼ ▼ ▼
┌─────────────┐ ┌──────────────┐ ┌──────────────┐
│ Score/Grade │ │ Performance │ │ Personalized │
│ │ │ Breakdown │ │Recommendations│
└─────────────┘ └──────────────┘ └──────────────┘
│
▼
┌──────────────┐
│ Student │
│ Report │
└──────────────┘
- 🐍 Python
- Scikit-Learn
- Joblib
- NumPy
- Pandas
- Plotly
- Streamlit
- Custom CSS
- Jupyter Notebook
- VS Code
- Git & GitHub
Student-Performance-Prediction-System/
│
├── Dataset/
│ ├── student_data.csv
│ ├── student_data_cleaned.csv
│ ├── student_data_feature_engineered.csv
│ └── student_performance_final.csv
│
├── Model/
│ └── student_model.pkl
│
├── Notebook/
│ ├── Student_Performance.ipynb
│ └── Student_Performance_executed.ipynb
│
├── Streamlit_App/
│ ├── app.py
│ └── style.css
│
├── docs/
│ └── screenshots/
│ ├── student-input-dashboard.png
│ └── prediction-results-dashboard.png
│
├── requirements.txt
├── .gitignore
└── README.md
git clone https://github.com/YOUR_USERNAME/Student-Performance-Prediction-System.gitcd Student-Performance-Prediction-Systempython -m venv .venv
.venv\Scripts\activatepython3 -m venv .venv
source .venv/bin/activatepip install -r requirements.txtstreamlit run Streamlit_App/app.pyThe easiest option is Streamlit Community Cloud.
GitHub Repository
↓
Streamlit Community Cloud
↓
Select app.py
↓
Deploy
↓
Live URL
Set the application entry point to:
Streamlit_App/app.py
Then add the generated URL to the top of this README:
[ Launch ScholarIQ](https://aistudentperformanceanalytics-rxj9rhuavw6ykenw8aszqh.streamlit.app/)ScholarIQ can be extended for:
- Schools
- Universities
- Teachers
- Academic advisors
- Students
- Educational institutions
The system can act as an early-warning mechanism for identifying students who may require additional academic support.
- Teacher dashboard
- Student login system
- Database integration
- Historical performance tracking
- Student progress analytics
- Explainable AI with SHAP
- AI-generated study plans
- Advanced PDF reports
- Email report delivery
- Academic risk-level prediction
- Production cloud deployment
- Mobile-friendly interface
ScholarIQ is designed around a simple principle:
Don't wait for failure to identify a problem. Predict it early and act on it.
The long-term goal is to transform the application from a simple score prediction system into an AI-powered academic early-warning and intervention platform.
Predict
↓
Understand
↓
Identify Weaknesses
↓
Recommend
↓
Improve
Shaik-pardi-11
Computer Science / Artificial Intelligence & Machine Learning
If this project helped you or you found it interesting, consider giving the repository a on GitHub.
ScholarIQ
Predict smarter • Intervene earlier • Perform better