Machine Learning for “Single-Point” User Conversion and Global Marketplace Optimization at Upwork
Machine Learning for “Single-Point” User Conversion and Global Marketplace Optimization at Upwork

Abstract: 

The two fundamental challenges in running an online service marketplace like Upwork are: (1) promoting growth at the user level, and (2) ensuring that growth is also healthy and sustainable at the global market level.

We present an overview of the ML-based methods we use for for local, single-point user conversion and for global marketplace optimization at Upwork. The focus will be on part 1 of the problem: We discuss how we use machine learning to optimize every step of our client/buyer and freelancer/seller conversion funnel. Topics covered include CTR Optimization, Learning-to-Rank, Content-based and Collaborative Filtering, Word and Object Embeddings, Client Modeling (Lifetime Value, Buying Intent, Price Sensitivity) and Freelancer Modeling (Expertise, Interest, Career Paths).

Bio: 

Thanh Tran is VP of Data Science and Search Engineering at Upwork, where he works with a team of 45+ scientists and engineers to innovate the core engine behind the world’s largest platform for freelancing and flexible work. As an entrepreneur and advisor of Bay Area startups, he helped build teams, raised capital for many companies and successfully shipped innovative technology solutions and end-user applications. Thanh previously served as a professor at the Karlsruhe Institute of Technology (Germany), where he led a worldwide top research group in semantic search. He earned various awards and recognition for his academic work (Most Cited Article 5-years award, among top-5 in Semantic Search, and top-50 in Web Search per 2016 Google Scholar Global Index).