The rapid development of e-commerce has significantly increased the volume of sales transactions and customer interaction data. This presents an opportunity for businesses to leverage data mining techniques to extract valuable insights that support decision-making processes. One such application is the development of product recommendation systems, which play a crucial role in enhancing customer satisfaction and driving sales. This research focuses on utilizing sales transaction data to build a product recommendation system using the Apriori algorithm, a well-known method for association rule mining. The study begins with the collection and preprocessing of transaction data from an e-commerce platform. Through the application of the Apriori algorithm, frequent itemsets are identified, and association rules are generated based on specified support and confidence thresholds. These rules reveal purchasing patterns and relationships between products that are frequently bought together. The system then uses these patterns to recommend relevant products to users, aiming to improve cross-selling opportunities and personalize the shopping experience. The results demonstrate that the Apriori-based recommendation model is effective in identifying meaningful product combinations and can be implemented as a lightweight, interpretable alternative to more complex machine learning methods. Furthermore, the system helps e-commerce businesses optimize inventory management and marketing strategies by understanding customer buying behavior. This research concludes that the integration of the Apriori algorithm into recommendation systems provides tangible benefits for e-commerce platforms seeking data-driven personalization solutions.
Siregar et al. (Sat,) studied this question.