Scalable AI-Based Recommendation Systems for E-Commerce and Streaming Platforms

Abstract

In the age of e-commerce, streaming services, and digital platforms, delivering custom user experiences is critical in today's digital world, with its rapid expansion.In the digital world of e-commerce, streaming services, and digital platforms, customizing user experiences has became a pivotal element of business. Based on hybrid collaborative filtering content based filtering, the paper presents the hybrid collaborative filtering content based filtering hybrid recommendation system which is scalable and applies the artificial intelligence methods. The model uses machine learning algorithms and matrix factorization techniques, such as Singular Value Decomposition (SVD), to enhance the accuracy and efficiency of recommendations. It addresses common problems such as data sparsity by providing optimized similarity calculation and feature extraction techniques, as well as overcoming the cold-start problem. The findings of the experimental work indicate that the hybrid model gives better performance in terms of Root Mean Square Error (RMSE), precision and recall than does the traditional approach. This design also allows for the easy handling of a vast amount of information and allows the easier provision of real-time updates. The outcomes show that this system is conceivable to be utilized on the current systems based on suggestions.