Online parameter selection for web-based ranking problems Agarwal et al., KDD'18 Last week we looked at production systems from Facebook, Airbnb, and Snap Inc., today it’s the turned of LinkedIn. This paper describes the system and model that LinkedIn use to determine the items to be shown in a user’s feed: It replaces previous hand-tuning … Continue reading Online parameter selection for web-based ranking problems

I know you’ll be back: interpretable new user clustering and churn prediction on a mobile social application Yang et al., KDD'18 Churn rates (how fast users abandon your app / service) are really important in modelling a business. If the churn rate is too high, it’s hard to maintain growth. Since acquiring new customers is … Continue reading I know you’ll be back: interpretable new user clustering and churn prediction on a mobile social application

Customized regression model for Airbnb dynamic pricing Ye et al., KDD'18 This paper details the methods that Airbnb use to suggest prices to listing hosts (hosts ultimately remain in control of pricing on the Airbnb platform). The proposed strategy model has been deployed in production for more than 1 year at Airbnb. The launch of … Continue reading Customized regression model for Airbnb dynamic pricing