In this roundtable with Ronay Ak from Nvidia, Serdar Kadioglu at Fidelity Investments, and Jacopo Tagliabue, we will be discussing how to build better recommender systems.
Evaluating recommender systems (RecSys) is a complex and dynamic process. It’s challenging because of the multi-modal nature of the data, the sheer size of the data needed, and the difficulty of predicting human behavior that is ever-evolving. Our guest speakers will be sharing the lessons learned from building and collaborating with others in building RecSys.
In this session, you will learn about:
- What makes recommender systems uniquely challenging to build
- How to bake in reproducibility before building recommender systems
- Sustainable best practices for building and evaluating recommender systems