Mr. Balaji Thadagam Kandavel

Engineered for Engagement: Retail Product Recommendations at Scale

Abstract:

With more and more industries demanding personalization, the automobile industry isn't left out. I outline the architecture and implementation of an intelligent product recommendation system that would amplify user engagement within a car-selling ecosystem.

Extracting in real time the streams of data pipelined through a distributed messaging platform like Apache Kafka, particularly for activities and profile data of users associated with car acquisitions, it ranges from detailed user information like user preference, purchase history, and detailed vehicle specification such as make, model, trim level, and elaborate options including installed accessories, roof type, wheel designs, and fuel type. Such a dataset, continuously being ingested and updated from floor to ceiling, forms the backbone of powerful recommendation algorithms running on scalable cloud platforms like AWS SageMaker.

Thus, the system churns out highly personalized product suggestions that best fit user needs and tastes by training and deploying several machine learning models. It will then be an easy-to-use application; it will intuitively handle the recommendation process for making a very well-informed decision for the best user experience. Will cover some technical considerations and details of implementation around this system using real-time data and cloud-based machine learning for offering personalized automotive recommendations.

Profile:

Full Stack Software Engineer and Cloud Solutions expert with over 17 years of experience in software development, cloud transformation and serverless computing. Have extensive expertise in designing and implementing cloud-native architectures, particularly within the AWS ecosystem, leveraging services such as AWS Lambda, API Gateway, DynamoDB, and CloudFormation. AWS Certified Developer and known for driving innovation through serverless computing, enhancing agility, scalability, and cost-efficiency for organizations. Expert in integrating AI/ML into cloud strategies, enabling predictive analytics, real-time decision-making and personalized customer experiences. 

Published articles and papers on AI-driven analytics and serverless machine learning frameworks. Has a track record of advancing innovation through scholarly contributions  in IEEE and IETE. Evaluated pioneering projects at events like the Edison Awards and Georgia Tech Capstone Design Expo. Have experience in Peer reviewing international conference papers ranging from cyberSecurity, AI/ML and Electronics.