Market Basket Analysis for Retail Sales Optimization

Supermarkets and grocery stores aim to improve customer experience and maximize sales. Recommending frequently bought items and optimizing the layout of products can enhance customer satisfaction and sales revenue. The proposed system “Market basket analysis for retail sales optimization” introduces a data-driven solution that leverages association rule mining algorithms, namely Eclat, FP-growth, and Apriori to recommend frequently purchased grocery items and optimize their placement within the store layout. The paper starts by utilizing a rich dataset of daily purchased grocery items, including historical transaction data. By employing the algorithms, the system uncovers hidden patterns, associations, and correlations among the purchased items. These algorithms efficiently mine frequent itemsets, allowing the system to recommend items that are often bought together. In addition to personalized recommendations, the project optimizes the store layout. Items that are frequently purchased together are strategically positioned in proximity to enhance customer convenience and encourage additional purchases. Simultaneously, it helps store owners to maximize sales by strategically placing items based on their association with one another. This paper bridges the gap between data analytics and retail optimization, offering a solution that benefits both customers and store operators.