Enhancing Product Bundling with Large Language Models

Recommendation systems have become popular in recent years. Today, in a world where competition is increasing, recommendation systems are used in many different areas. When the number of products and customers is high, it is important to recommend the right products to the right people. For this reason, different methods are widely used in recommendation systems and various techniques have been explored and developed to improve recommendation accuracy. The study evaluates the potential use of large language models. ChatGPT is chosen to create and expand existing product bundles. Apriori and word embedding models such as Word2Vec and FastText have been prepared for recommendations based on existing and bundles. The results show that large language models can improve bundle creation processes in some scenarios and that tools such as ChatGPT have the potential to improve recommender systems.