Smart Product Recommendations in Web E-Commerce: Leveraging Apriori Algorithm for Market Basket Analysis

Abstract

The world of online commerce is becoming increasingly competitive, and to succeed in this field, it is not enough to showcase products to potential buyers. It is crucial to offer various products and keep product recommendations up-to-date, especially for customers who buy multiple items. To address this challenge, an intelligent system is needed that can automatically generate trending product recommendations based on sales data. In this research, the Market Basket Analysis (MBA) method analyzes consumer transaction data and identifies products often purchased together. The apriori algorithm is applied to generate association rules, and the Lift Ratio parameter is used to evaluate the strength of these rules. This research is implemented on an e-commerce website, and the generated association rules will be applied to provide automatic product recommendations based on recent sales trends. The results show that the automatic product recommendation system developed for the e-commerce website significantly helps users enhance their online shopping experience. Using the Lift Ratio parameter in validating association rules provides strong evidence of the relevance and accuracy of the generated product recommendations, which can increase customer satisfaction and sales potential.

Keywords

• apriori, data mining, e-commerce, market basket analysis (mba), website