Welcome to the Market Basket Analysis project! This project focuses on analyzing customer purchase patterns to uncover associations between different items. The primary goal is to provide insights that can be valuable for marketing and product placement strategies.
The main task of this project is to conduct market basket analysis using Python. The analysis involves exploring frequent itemsets, association rules, and visualizing the results. The Apriori algorithm is employed to discover patterns within transactions, and key metrics such as support, confidence, and lift are used to evaluate the strength of associations.
Description The project involves the following steps:
Data Cleaning and Exploration: The dataset is preprocessed, and relevant columns are selected for analysis. Exploratory data analysis is conducted to understand the structure of the data.
Correlation Heatmap: A correlation heatmap is created to visualize the relationships between different items and customer-related attributes. This helps identify potential patterns and correlations in the data.
Apriori Algorithm: The Apriori algorithm is applied to identify frequent itemsets in the dataset. Association rules are then generated based on these item sets.
Association Rules Analysis: The generated association rules are analyzed, and key metrics such as confidence and lift are examined. The top association rules are sorted and displayed to provide actionable insights.
Visualization: The results are visualized using various plots, including bar charts for frequent itemsets and a network plot for association rules.
To run this project, follow these installation steps:
Install the required Python packages: pip install pandas matplotlib seaborn mlxtend networkx Run the provided Python script or Jupyter Notebook to execute the market basket analysis.
After installation, you can use the project by following these steps:
Execute the Python script or Jupyter Notebook file. Review the printed results and visualizations to gain insights into customer purchasing patterns. Adjust parameters, such as minimum support and confidence thresholds, based on your specific requirements.
The Core Team Project Lead: Oluwakemi Helen Deniran Data Scientist: Oluwakemi Helen Deniran Developer: N/A
Thank you for using the Market Basket Analysis project! If you have any questions or feedback, please don't hesitate to reach out to the core team.