Design and Deployment of a Cloud-based Scalable Recommendation System for E- commerce Platforms

ABSTRACT E-commerce platforms generate massive volumes of user interaction data, making personalized recommendation systems essential for enhancing user experience and increasing sales. This research focuses on the design and deployment of a cloud-based scalable recommendation system capable of delivering accurate and real-time product suggestions. The proposed system integrates collaborative filtering and content-based filtering techniques to analyse user behaviour, preferences, and product attributes. Cloud infrastructure is utilized to ensure high availability, scalability, and efficient handling of large datasets and concurrent users. Distributed data storage and parallel processing enable faster model training and recommendation generation. Performance evaluation is conducted using metrics such as accuracy, precision, and response time to validate system effectiveness. The results demonstrate that the cloud-based approach significantly improves scalability and recommendation efficiency compared to traditional standalone systems. This work highlights the importance of cloud computing in building robust, cost-effective, and scalable recommendation solutions for modern e- commerce platforms. Keywords: Cloud Computing, Recommendation System, E-commerce Platforms, Scalability, Collaborative Filtering, Content-Based Filtering, Big Data, Personalization, User Behaviour Analysis