The e-commerce industry thrives on the promise of timely deliveries. However, the unpredictability of shipment arrival times can undermine customer satisfaction and trust. This project seeks to develop a robust predictive model to forecast whether an e-commerce shipment will be delivered on time. By leveraging historical shipment data and advanced machine learning techniques, we aim to provide reliable delivery estimates and optimize logistics operations.
- Define Problem Statements
- Project Proposal (Proposed Solution)
- Initial Project Planning Report
- Data Collection Plan & Raw Data Sources Identification Report
- Data Quality Report
- Data Exploration and Preprocessing Report
- Feature Selection Report
- Model Selection Report
- Initial Model Training Code, Model Validation, and Evaluation Report
- Model Optimization and Tuning Report
- Model Training file
- Model Testing file
- Flask files (local deployment)
- Project Documentation
- Project Demonstration
- Python 3.x
- Jupyter Notebook
- Libraries:
scikit-learn
,pandas
,numpy
,seaborn
,pickle
,matplotlib
,Flask
- Clone the repository:
git clone https://github.com/your_username/ecommerce-shipping-prediction.git cd ecommerce-shipping-prediction
- Install the required libraries:
pip install -r requirements.txt
- Navigate to the Jupyter Notebook file in Sub-Folder 5:
cd '5. Project Executable Files' jupyter notebook Ecommerce_Shipping_Prediction.ipynb
- Run all cells in the notebook to train and evaluate the model.
- Navigate to the Flask application directory in Sub-Folder 5:
cd '5. Project Executable Files/Flask-Ecommerce'
- Run the Flask application:
python app.py
|
|
|
|
|
|
- Fork the repository.
- Create a new branch:
git checkout -b feature_branch
- Make your changes and commit them:
git commit -m "Feature description"
- Push to the branch:
git push origin feature_branch
- Create a new Pull Request
This project is licensed under the MIT License - see the LICENSE file for details.
- Kaggle for the dataset
- Team members for their contributions