OneDigital, the data and digital division of one of Australia's leading conglomerates, Wesfarmers, faces the challenge of building machine learning (ML) products utilising vast amounts of data. The growing demand for better scalability and a more efficient end-to-end productionization process prompted the need to uplift our existing platform with modern architecture and improved performance capabilities.
In this talk we will explore the journey of building a new ML platform using Ray, Anyscale, and other complementary products. We will delve into the key requirements for building this comprehensive platform that provides a rich user experience and reduces model deployment time and complexity, and cover the architecture, strategies and techniques used. Finally, we will showcase some retail use cases which use advanced ML models fine-tuned on Ray, to better identify customer segments, behaviors and preferences.
Paridhi is a senior machine learning engineer at Wesfarmers OneDigital. After her early career in software engineering with Cisco and Amazon, Paridhi moved to machine learning engineering where she has worked in a range of industries, including e-commerce, retail, and banking and has worked on ads classification, fraud detection, recommendations, and facial recognition. Paridhi holds a Master's degree in Artificial Intelligence from the University of Edinburgh.
Come connect with the global community of thinkers and disruptors who are building and deploying the next generation of AI and ML applications.