Towards Deep and Representation Learning for Talent Search at LinkedIn

TL;DR

This paper explores the application of deep and representation learning models to improve talent search and recommendation systems at LinkedIn, focusing on semantic representations, engagement prediction, and ranking, with promising offline and online results.

Contribution

It introduces neural network-based semantic representations for entities and deep models for engagement and response prediction in talent search, advancing beyond traditional linear and ensemble models.

Findings

Deep models improve candidate relevance.

Semantic entity representations enhance matching accuracy.

Online evaluation shows increased recruiter engagement.

Abstract

Talent search and recommendation systems at LinkedIn strive to match the potential candidates to the hiring needs of a recruiter or a hiring manager expressed in terms of a search query or a job posting. Recent work in this domain has mainly focused on linear models, which do not take complex relationships between features into account, as well as ensemble tree models, which introduce non-linearity but are still insufficient for exploring all the potential feature interactions, and strictly separate feature generation from modeling. In this paper, we present the results of our application of deep and representation learning models on LinkedIn Recruiter. Our key contributions include: (i) Learning semantic representations of sparse entities within the talent search domain, such as recruiter ids, candidate ids, and skill entity ids, for which we utilize neural network models that take advantage of LinkedIn Economic Graph, and (ii) Deep models for learning recruiter engagement and candidate response in talent search applications. We also explore learning to rank approaches applied to deep models, and show the benefits for the talent search use case. Finally, we present offline and online evaluation results for LinkedIn talent search and recommendation systems, and discuss potential challenges along the path to a fully deep model architecture. The challenges and approaches discussed generalize to any multi-faceted search engine.