A Study of Query Term Deletion using Large-scale E-commerce Search Logs

In ECIR 2014 (To Appear)
A Study of Query Term Deletion using Large-scale E-commerce Search Logs
Bishan Yang, Nish Parikh, Gyanit Singh, Neel Sundaresan
eBay Authors

Query term deletion is one of the commonly used strategies for query rewriting. In this paper, we study the problem of query term deletion using large-scale e-commerce search logs. Especially we focus on queries that do not lead to user clicks and aim to predict a reduced and better query that can lead to clicks by term deletion. Accurate prediction of term deletion can potentially help users recover from poor search results and improve shopping experience.

To achieve this,we use various term-dependent and query-dependent measures as features and build a classifier to predict which term is the most likely to be deleted from a given query. Different from previous work on query term deletion, we compute the features not only based on the query history and the available document collection, but also conditioned on the query category, which captures the high-level context of the query.

We validate our approach using a large collection of query sessions logs from a leading e-commerce site, and show that it provides promising performance in term deletion prediction, and significantly outperforms baselines that rely on query history and corpus-based statistics without incorporating the query context information.

Another publication from the same author: Nish Parikh

In proceedings of the Workshop on Log-based Personalization (the 4th WSCD workshop) at WSDM 2014

A Large Scale Query Logs Analysis for Assessing Personalization Opportunities in E-commerce Sites

Neel Sundaresan, Zitao Liu

Personalization offers the promise of improving online search and shopping experience. In this work, we perform a large scale analysis on the sample of eBay query logs, which involves 9.24 billion session data spanning 12 months (08/2012-07/2013) and address the following topics

(1) What user information is useful for personalization;

(2) Importance of per-query personalization

(3) Importance of recency in query prediction.

In this paper, we study these problems and provide some preliminary conclusions


Another publication from the same category: Machine Learning and Data Science

Washinton DC, 27-30 Oct. 2014

Astro: A Predictive Model for Anomaly Detection and Feedback-based Scheduling on Hadoop

Chaitali Gupta, Mayank Bansal, Tzu-Cheng Chuang, Ranjan Sinha, Sami Ben-romdhane

The sheer growth in data volume and Hadoop cluster size make it a significant challenge to diagnose and locate problems in a production-level cluster environment efficiently and within a short period of time. Often times, the distributed monitoring systems are not capable of detecting a problem well in advance when a large-scale Hadoop cluster starts to deteriorate i n performance or becomes unavailable. Thus, inc o m i n g workloads, scheduled between the time when cluster starts to deteriorate and the time when the problem is identified, suffer from longer execution times. As a result, both reliability and throughput of the cluster reduce significantly. In this paper, we address this problem by proposing a system called Astro, which consists of a predictive model and an extension to the Hadoop scheduler. The predictive model in Astro takes into account a rich set of cluster behavioral information that are collected by monitoring processes and model them using machine learning algorithms to predict future behavior of the cluster. The Astro predictive model detects anomalies in the cluster and also identifies a ranked set of metrics that have contributed the most towards the problem. The Astro scheduler uses the prediction outcome and the list of metrics to decide whether it needs to move and reduce workloads from the problematic cluster nodes or to prevent additional workload allocations to them, in order to improve both throughput and reliability of the cluster. The results demonstrate that the Astro scheduler improves usage of cluster compute resources significantly by 64.23% compared to traditional Hadoop. Furthermore, the runtime of the benchmark application reduced by 26.68% during the time of anomaly, thus improving the cluster throughput.