Talk Abstract: Fashion Recommendations at ASOS: Challenges, Approaches and Learnings
In this talk, we discuss our journey in the design and development of recommender systems for our platform. We first discuss the technical and business challenges we faced when starting to build our recommendation engine. Next, we explore the main characteristics of the fashion domain and how we approached the importance of incorporating domain knowledge within our recommendation framework.
We then detail various use cases we have been working on, such as product recommendations, related products, out of stock recommendations, category recommendations and visual browsing. In addition, we illustrate how various important other functions and elements contribute to the success of a recommender system and what specific challenges we faced in putting our algorithms into a production environment.
We conclude the talk by outlining our data science roadmap, which includes context-aware recommendations, session-based recommendations and tensor decomposition techniques.
Bio: Soraya Hausl is a Senior Data Scientist at ASOS where she leads the Recommendations Team. She is passionate about building data products that improve customer experience. Prior to ASOS, Soraya obtained a MSc degree in Machine Learning from the University College London (UCL) and has worked in strategy consulting.