Retail Recommender System

Overview

The Retail Recommender System is a Shiny-based web application that provides recommendations for cross-sell opportunities using association rule mining. Built with R, it analyzes customer transaction data, extracts purchasing patterns, and generates rules for cross-sell recommendations. The app is designed to provide business insights, particularly in retail environments, by leveraging market basket analysis.

Features

• Transaction Data Analysis: Loads transactional data from CSV files and processes it using the arules package for association rule mining.
• Cross-Sell Rule Discovery: Applies the Apriori algorithm to identify frequent itemsets and generates rules to highlight cross-sell opportunities.
• Interactive Visualization: Provides interactive plots and graphs to explore the generated rules.
• Customizable Thresholds: Allows users to adjust support and confidence thresholds via a simple UI to fine-tune rule generation.
• Explore Panel: View and analyze the generated rules based on support, confidence, and lift.

Technologies Used

• R Programming Language
  • shiny: For creating the web application.
  • arules: For implementing association rule mining.
  • plotly: For creating interactive plots.
  • igraph: For visualizing rule relationships using graphs.
  • arulesViz: For visualizing association rules.

Installation

To run this project locally, follow these steps:

1. Clone the Repository

   git clone https://github.com/sabareh/retail-recommender-system.git
   cd retail-recommender-system

2. Install Dependencies Make sure you have R installed on your machine. Install the required packages:

   install.packages(c("shiny", "plotly", "arules", "igraph", "arulesViz", "DT"))

3. Run the Application

   runApp('Recommender-App')

4. Access the App Once the application starts, access it by navigating to http://127.0.0.1:6849 in your web browser, where XXXX is the port number displayed in the console.

Project Structure

Retail-Recommender-System/
│
├── data/
│   └── data.csv             # Sample transaction data
├── Recommender-App/
│   ├── app.R                # Main Shiny app file
│   └── ...
├── README.md                # Project documentation
└── LICENSE                  # License information

Sample Data

Ensure the data.csv file follows the below structure:

order_id	product_id
1	A
1	B
2	A
2	C
3	B
3	D

You can modify the data to fit your retail environment, using unique identifiers for products and orders.

How It Works

1. Transaction Loading: The app reads in transaction data from a CSV file.
2. Apriori Algorithm: The Apriori algorithm finds frequent itemsets and generates rules with specified support and confidence thresholds.
3. Visualization: The app displays rules in tabular form and as interactive graphs, allowing for deeper exploration.

Screenshots

1. Cross-Sell Rules Table

2. Rule Graph

Contributing

Contributions are welcome! To contribute:

1. Fork the repository.
2. Create a new feature branch (git checkout -b feature/your-feature).
3. Commit your changes (git commit -m 'Add feature').
4. Push to the branch (git push origin feature/your-feature).
5. Open a pull request.

License

This project is licensed under the MIT License. See the LICENSE file for more details.

Contact

For any inquiries or issues, feel free to reach out:

• Victor Oketch Sabare
• LinkedIn
• Email: [email protected]

---

This README provides a detailed overview of your project, including instructions for installation, usage, and contribution, as well as a sample structure and visualizations to make the repository more accessible for users and contributors.