Recommendation System using Gen AI

Mrs. D. Sirisha 1
Assistant Professor, Department ofAI&DSAnnamacharya Institute of
Technology and Sciences, Tirupati –517520, A.P.sirishaaids@gmail.com
N Sukumar 4
Department of AI&DSAnnamacharya Institute of
Technology and Sciences, Tirupati –517520, A.P.nsukumar2212@gmail.com
M Syam Prasad 2
Department of AI&DSAnnamacharya Institute of
Technology and Sciences, Tirupati –517520, A.P.molakasyamprasad2004@gmail.com
S Rahul 5
Department of AI&DSAnnamacharya Institute ofTechnology and Sciences, Tirupati –
517520, A.P.surakanirahul@gmail.com

T Sree Lakshmi 3
Department of AI&DSAnnamacharya Institute ofTechnology and Sciences, Tirupati –
517520, A.P.tharugusreelakshmi@gmail.com

ABSTRACT — Recent advancements in the field of Generative Artificial Intelligence “(Gen AI) and Large Language Models (LLMs) have made it possible to improve the performance of modern recommendation systems. The conventional approaches employed for designing recommendation systems, such as collaborative filtering and content-based filtering, have some limitations, such as the cold-start problem, data sparsity,and lack of diversity in recommendations. These  limitations have led to the poor performance of recommendation systems, especially in situations where there is a lack of interaction data and new users and items are being added to the recommendation system. Toovercome these limitations, a new recommendation system has been proposed in this project based on Generative AI, which utilizes the advantages of theGoogle Gemini 2.5 Flash Large Language Model to design intelligent recommendations and improve the performance of the recommendation system.process