Paper Session 10: Novel and Practical

Date: Wednesday, Aug 30, 2017, 10:45-12:30
Location: Room 1
Chair: Robin Burke

  • LPRecommending Product Sizes to Customers by Vivek Varadarajan Sembium, Rajeev Rastogi, Atul Saroop and Srujana Merugu

    We propose a novel latent factor model for recommending product size fits {Small, Fit, Large} to customers. Latent factors for customers and products in our model correspond to their physical true size, and are learnt from past product purchase and returns data. The outcome for a customer, product pair is predicted based on the difference between customer and product true sizes, and efficient algorithms are proposed for computing customer and product true size values that minimize two loss function variants. In experiments with Amazon shoe datasets, we show that our latent factor models incorporating personas, and leveraging return codes show a 17-21% AUC improvement compared to baselines. In an online A/B test, recommendations produced by our algorithms show an improvement of 33 basis points in percentage of Fit transactions over control.

  • LPPractical Lessons from Developing a Large-Scale Recommender System at Zalando by Antonino Freno

    Developing a real-world recommender system, i.e. for use in large-scale online retail, poses a number of different challenges. Interestingly, only a small part of these challenges are of algorithmic nature, such as how to select the most accurate model for a given use case. Instead, most technical problems usually arise from operational constraints, such as: adaptation to novel use cases; cost and complexity of system maintenance; capability of reusing pre-existing signal and integrating heterogeneous data sources.

    In this paper, we describe the system we developed in order to address those constraints at Zalando, which is one of the most popular online fashion retailers in Europe. In particular, we explain how moving from a collaborative filtering approach to a learning-to-rank model helped us to effectively tackle the challenges mentioned above, while improving at the same time the quality of our recommendations. A fairly detailed description of our software architecture is provided, along with an overview of the algorithmic approach. On the other hand, we present some of the offline and online experiments that we ran in order to validate our models.

  • LPExploiting Socio-Economic Models for Lodging Recommendation in the Sharing Economy by Raul Sanchez-Vazquez, Jordan Silva and Rodrygo L.T. Santos

    Recent years have witnessed the emergence of sharing economy marketplaces, which enable users to share goods and services in a peer-to-peer fashion. A prominent example in the travel industry is Airbnb, which connects guests with hosts, allowing both to exchange cultural experiences in addition to the economic transaction. Nonetheless, Airbnb guest profiles are typically sparse, which limits the applicability of traditional lodging recommendation approaches. Inspired by recent socio-economic analyses of repurchase intent behavior on Airbnb, we propose a context-aware learning-to-rank approach for lodging recommendation, aimed to infer the user’s perception of several dimensions involved in choosing which lodging to book. In particular, we devise features aimed to capture the user’s price sensitivity as well as their perceived value of a particular lodging, the risk involved in choosing it rather than other available options, the authenticity of the cultural experience it could provide, and its overall perception by other users through word of mouth. Through a comprehensive evaluation using publicly available Airbnb data, we demonstrate the effectiveness of our proposed approach compared to a number of alternative recommendation baselines, including a simulation of Airbnb’s own recommender.

  • SPSurveying User Reactions to Recommendations Based on Inferences Made by Face Detection Technology by Jennifer Marlow and Jason Wiese

    It is increasingly possible to use cameras and sensors to detect and analyze human appearance for the purposes of personalizing user experiences. Such systems are already deployed in some public places to personalize advertisements and recommend items. However, since these technologies are not yet widespread, we do not have a good sense of the perceived benefits and drawbacks of public display systems that use face detection as an input for personalized recommendations. We conducted a user study with a system that inferred a user’s gender and age from a facial detection and analysis algorithm and used this to present recommendations in two scenarios (finding stores to visit in a mall and finding a pair of sunglasses to buy).  This work provides an initial step towards understanding user reactions to a new and emerging form of implicit recommendation based on physical appearance.

  • SPAn Insurance Recommendation System Using Bayesian Networks by Maleeha Qazi, Glenn M. Fung, Katie J. Meissner and Eduardo R. Fontes

    In this paper we describe a deployed recommender system to predict insurance products for new and existing customers. Our goal is to give our customers personalized recommendations based on what other similar people with similar portfolios have, in order to make sure they were adequately covered for their needs. Our system uses customer characteristics in addition to customer portfolio data. Since the number of possible recommendable products is relatively small compared to other recommender domains and missing data is relatively frequent, we chose to use Bayesian Networks for modeling our system. Experimental results show advantages of using probabilistic graphical models over the widely used low-rank matrix factorization model for the insurance domain.

Back to Program

Diamond Supporter
 
Platinum Supporters
 
 
 
 
Gold Supporter
 
Silver Supporter
 
Special Supporters