PlaceWise AI is a Machine Learning-based web application that predicts student placement readiness, identifies skill gaps, and provides personalized recommendations for improvement.
🌐 Live Demo | 📓 EDA Notebook
- 🎯 Placement prediction using trained ML models
- 📊 Readiness score calculation with skill breakdown
⚠️ Weakness detection and gap analysis- 💡 Personalized improvement recommendations
- 🔍 Explainable AI insights (feature importance)
- 📈 Interactive skill visualization dashboard
- 📄 Downloadable placement analysis report
| Model | Accuracy |
|---|---|
| Logistic Regression | 86.02% |
| SVM | 85.98% |
| Random Forest | 85.72% |
| KNN | 83.96% |
| Decision Tree | 78.83% |
Random Forest selected as the final model based on performance and robustness.
| Factor | Description |
|---|---|
| Technical Skills | Programming, DSA, domain knowledge |
| Aptitude Score | Logical reasoning and quantitative ability |
| Communication Skills | Verbal and written communication |
| Academic Performance | CGPA and backlog status |
| Project Experience | Number and quality of projects |
| Soft Skills | Teamwork, leadership, adaptability |
| Category | Tools |
|---|---|
| Language | Python 3.x |
| ML & Data | Scikit-learn, Pandas, NumPy |
| Visualization | Matplotlib, Seaborn |
| Web App | Streamlit |
| Model Persistence | Joblib |
PlaceWise-AI/
├── dataset/
│ ├── raw/ # Original dataset
│ └── processed/ # Cleaned dataset
├── notebooks/
│ └── EDA.ipynb # Exploratory Data Analysis
├── models/
│ ├── rf_model.pkl # Trained Random Forest model
│ ├── logistic_model.pkl # Trained Logistic Regression model
│ └── scaler.pkl # Feature scaler
├── images/ # App screenshots
├── app.py # Streamlit application
├── requirements.txt
└── README.md
Data Collection → Preprocessing → EDA → Feature Engineering → Model Training (5 models) → Evaluation → Streamlit App → Deployment
- Synthetic student placement dataset with 7 key features
- Preprocessing includes handling missing values, feature scaling, and encoding
- Note: Dataset is synthetic, used for model development and demonstration
git clone https://github.com/tejasvinifulari5/PlaceWise-AI.git
cd PlaceWise-AI
pip install -r requirements.txt
streamlit run app.py- Integrate real campus placement data via surveys
- Add SHAP-based per-prediction explainability
- Include resume scoring and ATS compatibility check
- Multi-college comparative analytics
Tejasvini Fulari AI & Data Science Engineering Student | VPKBIET, Baramati GitHub · LinkedIn
This project is licensed under the MIT License.