FlowCast AI is an enterprise-grade intelligent traffic prediction and analytics platform that combines Machine Learning, Deep Learning, Explainable AI, and interactive dashboards to forecast traffic conditions and support data-driven traffic management.
The platform performs complete end-to-end traffic analytics, including:
- Traffic Data Analysis
- Feature Engineering
- Machine Learning Prediction
- Deep Learning Forecasting
- Explainable AI (SHAP & LIME)
- Interactive Dashboard
- Upload Custom Dataset
- Real-Time Traffic Insights
- Enterprise KPI Dashboard
- Interactive Plotly Visualizations
- Traffic Trends
- Congestion Analysis
- Weather Analytics
- Road-wise Traffic Analysis
- Vehicle Distribution
- Correlation Heatmap
- Download Reports
Supports multiple prediction models:
- Random Forest
- XGBoost
- Best ML Model
- LSTM Deep Learning
- Ensemble Prediction
Prediction includes:
- Traffic Volume Forecast
- Congestion Detection
- Confidence Score
- Delay Estimation
- AI Recommendation
- Traffic Gauge
- Model Comparison
- Prediction History
Model Interpretability using
- SHAP Feature Importance
- SHAP Waterfall Plot
- SHAP Summary Plot
- SHAP Dependence Plot
- LIME Explanation
- Global Feature Importance
- Local Prediction Explanation
- AI Decision Summary
Users can upload their own traffic dataset for prediction.
Supported format:
- CSV
Validation includes:
- Missing Values
- Duplicate Records
- Dataset Preview
- Statistics
- Download Clean Data
- dashboard/screenshots/2_home_page
- dashboard/screenshots/3_analytics_page
- dashboard/screenshots/4_prediction_page
- dashboard/screenshots/5_ai_insights
- dashboard/screenshots/6_upload_data
FlowCast-AI
β
βββ dashboard/
β βββ app.py
β βββ assets/
β βββ pages/
β β βββ 01_Home.py
β β βββ 02_Analytics.py
β β βββ 03_Prediction.py
β β βββ 04_AI_Insights.py
β β βββ 05_Upload_Data.py
β βββ screenshots/
β
βββ data/
β βββ raw/
β βββ processed/
β
βββ docs/
β
βββ models/
β βββ artifacts/
β βββ deep_learning/
β βββ best_model.pkl
β βββ xgboost_model.pkl
β
βββ notebooks/
β
βββ reports/
β
βββ requirements.txt
β
βββ README.md
Raw Traffic Data
β
βΌ
Data Cleaning
β
βΌ
Preprocessing
β
βΌ
EDA
β
βΌ
Feature Engineering
β
βΌ
Random Forest
β
βΌ
XGBoost
β
βΌ
LSTM Deep Learning
β
βΌ
Model Evaluation
β
βΌ
Explainable AI
β
βΌ
Interactive Dashboard
| Model | Purpose |
|---|---|
| Random Forest | Baseline Prediction |
| XGBoost | High Accuracy Prediction |
| LSTM | Sequential Traffic Forecasting |
| Ensemble | Final Prediction |
- Python
- Pandas
- NumPy
- Scikit-Learn
- XGBoost
- TensorFlow
- Keras
- SHAP
- LIME
- Plotly
- Matplotlib
- Streamlit
Traffic Dataset
β
Cleaning
β
EDA
β
Feature Engineering
β
Model Training
β
Model Evaluation
β
Explainable AI
β
Traffic Prediction Dashboard
Clone the repository
git clone https://github.com/aparna190417/FlowCast-AI.gitMove into project
cd FlowCast-AIInstall requirements
pip install -r requirements.txtRun Streamlit
streamlit run dashboard/app.py- Live Traffic API Integration
- Google Maps Visualization
- Real-Time Prediction
- IoT Sensor Support
- Cloud Deployment
- Automated Model Retraining
- REST API Support
Aparna Patel
Data Analyst | Machine Learning | Deep Learning | Explainable AI
https://github.com/aparna190417
Please consider giving it a β on GitHub.
Β© 2026 Aparna Patel