The Powerful Model Adpredictor for Search Engine Switching Detection Challenge

TL;DR

This paper presents a solution for detecting user search engine switching actions using the Adpredictor model combined with feature engineering, achieving high accuracy and ranking fifth in a competitive challenge.

Contribution

The paper introduces the application of the Adpredictor model with effective feature engineering for search switching detection, outperforming many competitors.

Findings

Achieved an AUC score of 0.84255 on the private leaderboard.

Successfully applied CTR prediction model to switching detection.

Ranked 5th among all competitors.

Abstract

The purpose of the Switching Detection Challenge in the 2013 WSCD workshop was to predict users' search engine swithcing actions given records about search sessions and logs.Our solution adopted the powerful prediction model Adpredictor and utilized the method of feature engineering. We successfully applied the click through rate (CTR) prediction model Adpredicitor into our solution framework, and then the discovery of effective features and the multiple classification of different switching type make our model outperforms many competitors. We achieved an AUC score of 0.84255 on the private leaderboard and ranked the 5th among all the competitors in the competition.