Ensemble Methods for Personalized E-Commerce Search Challenge at CIKM Cup 2016
This work addresses personalized search for e-commerce users, but it is incremental as it applies ensemble methods to a competition setting.
The paper tackled the challenge of personalized e-commerce search at CIKM Cup 2016 by developing an ensemble model that blends multiple models, including a novel deep match model, to predict search relevance and re-rank items, and their solution won the competition on all evaluation metrics.
Personalized search has been a hot research topic for many years and has been widely used in e-commerce. This paper describes our solution to tackle the challenge of personalized e-commerce search at CIKM Cup 2016. The goal of this competition is to predict search relevance and re-rank the result items in SERP according to the personalized search, browsing and purchasing preferences. Based on a detailed analysis of the provided data, we extract three different types of features, i.e., statistic features, query-item features and session features. Different models are used on these features, including logistic regression, gradient boosted decision trees, rank svm and a novel deep match model. With the blending of multiple models, a stacking ensemble model is built to integrate the output of individual models and produce a more accurate prediction result. Based on these efforts, our solution won the champion of the competition on all the evaluation metrics.