Food Delivery Time Prediction Model
This project predicts the estimated delivery time for food orders using input factors such as distance, weather, traffic, and courier experience. The model is trained using Linear Regression and deployed using Streamlit for interactive usage.
📌 Key Features
- Predicts delivery times based on user-provided inputs
- Visualizes trends with Seaborn and Matplotlib
- Implements Linear Regression using Scikit-learn
- Deployed as an interactive web app with Streamlit
- Saves and loads trained model using Pickle
🛠️ Technologies Used
- Python
- Pandas, NumPy for data handling
- Matplotlib, Seaborn for visualization
- Scikit-learn for machine learning
- Streamlit for frontend deployment
- Pickle for model serialization
📥 Inputs & 📤 Output
Users provide delivery-related details like distance, weather, traffic, time of day, vehicle type, preparation time, and courier experience. The output is the estimated delivery time in minutes.
📈 Project Workflow
- Performed EDA and data cleaning
- Engineered features and encoded variables
- Trained Linear Regression model using Scikit-learn
- Evaluated model using RMSE and R²
- Deployed model with Streamlit
🔗 GitHub Link: View Project on GitHub
