Methods and systems for selecting an optimized scoring function for use in ranking item listings presented in search results

作者: Rami El-Charif , Olivier G. Dumon , Guanglei Song , Sanjay Pundlkrao Ghatare , Muhammad Faisal Rehman

DOI:

关键词:

摘要: Methods and systems for simulating a search, the purpose of evaluating one or more scoring functions used in ordering item listings presentation search results page are described. Consistent with some embodiments, simulation platform includes real-time module that receives result sets queries conclusion transaction. The set is then processed by test functions, such resulting position listing has resulted transaction can be compared actual at which was displayed results. For each function, an average rank shift metric determined, displayed, thereby providing to base decisions about use production system.

参考文章(17)
John Solaro, Jim Gooder, Alex Semko, Sumved Sharma, Combining and re-ranking search results from multiple sources ,(2009)
Steven Conrad, Tool positioning system ,(2010)
Vanessa Murdock, Vassilis Plachouras, Massimiliano Ciaramita, Optimizing ranking functions using click data ,(2008)
Reed Sturtevant, William Gross, Thomas McGovern, Search engine using user intent ,(2005)
Mark Martel, Gokul Rajaram, Advertisement campaign simulator ,(2007)
Iftah Gamzu, Joseph Yossi Azar, Xiaoxin Yin, Ranking results of multiple intent queries ,(2009)
Ming Zhou, Cheng Niu, Cross-lingual search re-ranking ,(2008)
Thomas Christopher Korte, Celia Neuhoff Saino, Sumit Agarwal, Methods and systems for endorsing local search results ,(2005)