Integrated Recommendation System in ChatGPT to Analyze Post-purchase Behavior of E-commerce Store Users

Abstract

Recommender systems have had a great development in recent years, helping exponentially in the e-commerce sector. This has many applications to improve user behavioral factors with different filtering techniques; however, most of these systems lack a presentation and interaction model that really influences users. In this context, e-commerce sites are looking for different strategies to allocate the recommendations seen by the online user in an accurate and timely manner; still, reviewing different articles it is not very clear whether the way in which the recommended items are presented has a positive impact on user behavior. On the other hand, conversational artificial intelligence systems technology had a large size, highlighting ChatGPT as an innovative tool. Finally, this research aims to validate whether the implementation of an integrated SR in ChatGPT influences the post-purchase behavior of users in an e-commerce store. The results show that by leveraging the potential of conversational AI to deliver more effective and personalized recommendations, there is a 34.15% increase with respect to user recommendation, while in the purchase of recommended products there is an exponential increase of 54.05%; Likewise, it is evident that users who make repurchases after 14 days from their initial purchase have an increase of 46.67%; finally, that the repurchase of products from the e-commerce store has a slight significant increase of 9.52%