Measurement and applications of position bias in a marketplace search engine

TL;DR

This paper investigates position bias in marketplace search engines, using randomization experiments to measure its impact on relevance and model performance, and discusses implications for bias correction and model design.

Contribution

It introduces a novel empirical approach with randomization to quantify position bias and its effects on relevance signals and model features in a marketplace search context.

Findings

Randomization improved relevance models and user experience.

Position bias affects both labels and model features.

The study provides practical methods for bias measurement and mitigation.

Abstract

Search engines intentionally influence user behavior by picking and ranking the list of results. Users engage with the highest results both because of their prominent placement and because they are typically the most relevant documents. Search engine ranking algorithms need to identify relevance while incorporating the influence of the search engine itself. This paper describes our efforts at Thumbtack to understand the impact of ranking, including the empirical results of a randomization program. In the context of a consumer marketplace we discuss practical details of model choice, experiment design, bias calculation, and machine learning model adaptation. We include a novel discussion of how ranking bias may not only affect labels, but also model features. The randomization program led to improved models, motivated internal scenario analysis, and enabled user-facing scenario tooling.