Context: In an online marketing scenario, there are a lot of choices to select from for any user. So, the need for a recommender system is increasing, as this can help the customers shop on these e-commerce websites. This recommender system uses different algorithms to analyze customers’ behavior and interests, which can be used with the historical data of purchases of products to personalize the product suggestions for individual customers.

Objective: The objective of this article is to develop an efficient recommendation system that caters to the needs of the customers and provides them with a unique and personalized experience on the e-commerce platform. This project aims to suggest relevant products to the customers based on their past interactions and interests and the behaviors of similar customers. This project seeks to improve the customers’ satisfaction and loyalty towards the e-commerce platform through this unique and personalized experience.

Materials/Methods: In this article, we have used collaborative filtering algorithms and content-based filtering techniques to recommend the product, as well as proposed a hybrid algorithm which is a combination of Apriori and FP-Growth. Apart from these, we also used the machine learning algorithm to improve the recommendation accuracy.

Conclusion: After the implementation of the Apriori and FP-Growth algorithms in the recommender system, it was found that the FP-Growth algorithm has better support for the frequent item sets from the data. A hybrid of the two algorithms can give better support. This enables the model to offer accurate suggestions according to historical data. This approach can cater to the diverse needs of the customers and offer them a personalized experience on an e-commerce website.