Main Article Content
Recommender System is tremendously used in numerous spaces, such as e-commerce and entertainment to enhance businesses by increasing the chance of sales. Earlier researches have focused more on traditional Machine Learning (ML) and Artificial Intelligence (AI)-based approaches. Developing a scalable recommender system has been challenging concerning high availability and fault tolerance. The traditional collaborative filtering approach used with the recommender system also faces challenges due to the absence of explicit product ratings by the customer and the cold start problem. We have proposed a scalable Alternating least square (ALS) and collaborative filtering-based approach for the recommender system. The experimental results of the proposed hybrid approach show improved performance as compared with the traditional approach.