Optimizing Personalized User Experience - In-Session Recommendations Across E-commerce Verticals

Explore a 31-minute conference talk from the Toronto Machine Learning Series where Loblaw Digital's Machine Learning Engineers, Tina Shen and Charles Zhu, examine the intricacies of personalized recommendation systems in e-commerce. Dive into an analysis of user behaviors across different platforms and learn about innovative solutions that enhance user engagement. Discover various use cases of in-session recommendations implemented across multiple retail platforms including Loblaws, Real Canadian Superstore, Shoppers Drug Mart, and Joe Fresh. Examine an in-house recommendation model that processes multiple item/user data points to deliver personalized suggestions across diverse shopping scenarios. Learn how the model addresses complex user behaviors including multiple shopping intentions, multi-granularity of intentions, and interleaving behavior within shopping sessions. Gain insights into the system design, performance results, and ongoing online evaluations of this practical solution for enhancing digital shopping experiences.