Recommending Accommodation Filters with Online Learning

Online Accommodations Platforms match guests searching for accommodation with hospitality service providers. A fundamental characteristic of efficient platforms is the ability to satisfy the needs and preferences of the guests. To achieve this goal, a common search tool is the Results Filtering capability which allows users to refine query results with explicit criteria. However, as supply grows and diversifies, more filtering options become available, reaching hundreds of different criteria for one query, and making it hard for customers to find the ones that are relevant to them. In this work we present the implementation of an Accommodation Filters Recommender System addressing this issue. The problem poses several challenges around recommendations feedback, user experience constraints, and non stationarity among others. We provide an end-to-end description of the System, discuss implementation issues and provide techniques to address them including a large scale distributed online learning architecture. The solution was validated through several Online Controlled Experiments performed in Booking.com, a top Online Travel Agency serving millions of daily users, showing statistically significant results on various user behaviour metrics indicating a strong positive effect on User Engagement.

[1]  J. Langford,et al.  The Epoch-Greedy algorithm for contextual multi-armed bandits , 2007, NIPS 2007.

[2]  Qingyun Wu,et al.  Learning Contextual Bandits in a Non-stationary Environment , 2018, SIGIR.

[3]  Wei Chu,et al.  A contextual-bandit approach to personalized news article recommendation , 2010, WWW '10.

[4]  U. Yuksel,et al.  What Can Tourists and Travel Advisors Learn from Choice Overload Research , 2017 .

[5]  Yi Chang,et al.  Streaming Recommender Systems , 2016, WWW.

[6]  Roberto Turrin,et al.  Controlling Consistency in Top-N Recommender Systems , 2010, 2010 IEEE International Conference on Data Mining Workshops.

[7]  Joaquin Quiñonero Candela,et al.  Practical Lessons from Predicting Clicks on Ads at Facebook , 2014, ADKDD'14.

[8]  Jaap Kamps,et al.  The Continuous Cold-start Problem in e-Commerce Recommender Systems , 2015, CBRecSys@RecSys.

[9]  Rishabh K. Iyer,et al.  A Unified Batch Online Learning Framework for Click Prediction , 2018, ArXiv.

[10]  M. Lepper,et al.  The Construction of Preference: When Choice Is Demotivating: Can One Desire Too Much of a Good Thing? , 2006 .

[11]  Kilian Q. Weinberger,et al.  Feature hashing for large scale multitask learning , 2009, ICML '09.

[12]  S. Jang,et al.  Confused by too many choices? Choice overload in tourism , 2013 .

[13]  Lucas Theis,et al.  Addressing delayed feedback for continuous training with neural networks in CTR prediction , 2019, RecSys.

[14]  Olivier Chapelle,et al.  Modeling delayed feedback in display advertising , 2014, KDD.

[15]  Dong Wang,et al.  Click-through Prediction for Advertising in Twitter Timeline , 2015, KDD.

[16]  Licia Capra,et al.  Temporal diversity in recommender systems , 2010, SIGIR.

[17]  David Cortes,et al.  Adapting multi-armed bandits policies to contextual bandits scenarios , 2018, ArXiv.

[18]  Pablo Estevez,et al.  150 Successful Machine Learning Models: 6 Lessons Learned at Booking.com , 2019, KDD.

[19]  Basak Denizci Guillet,et al.  The effects of choice set size and information filtering mechanisms on online hotel booking , 2020 .

[20]  John Langford,et al.  Normalized Online Learning , 2013, UAI.