Personalized Expertise Search at LinkedIn

TL;DR

This paper presents a personalized expertise search system for LinkedIn that uses collaborative filtering and expertise scoring to improve search relevance and click-through rates for members seeking professional skills.

Contribution

It introduces a novel hybrid approach combining matrix factorization for expertise estimation with a heuristic for training data extraction, enhancing personalized search results.

Findings

Significant CTR improvements: 31% for recruiter, 18% for homepage.

Enhanced expertise estimation for listed and unlisted skills.

Models now serve nearly all live LinkedIn skills search traffic.

Abstract

LinkedIn is the largest professional network with more than 350 million members. As the member base increases, searching for experts becomes more and more challenging. In this paper, we propose an approach to address the problem of personalized expertise search on LinkedIn, particularly for exploratory search queries containing {\it skills}. In the offline phase, we introduce a collaborative filtering approach based on matrix factorization. Our approach estimates expertise scores for both the skills that members list on their profiles as well as the skills they are likely to have but do not explicitly list. In the online phase (at query time) we use expertise scores on these skills as a feature in combination with other features to rank the results. To learn the personalized ranking function, we propose a heuristic to extract training data from search logs while handling position and sample selection biases. We tested our models on two products - LinkedIn homepage and LinkedIn recruiter. A/B tests showed significant improvements in click through rates - 31% for CTR@1 for recruiter (18% for homepage) as well as downstream messages sent from search - 37% for recruiter (20% for homepage). As of writing this paper, these models serve nearly all live traffic for skills search on LinkedIn homepage as well as LinkedIn recruiter.