Adapting Job Recommendations to User Preference Drift with Behavioral-Semantic Fusion Learning

TL;DR

This work tackles preference drift in job recommendations by introducing BISTRO, a session-based framework that fuses behavioral and semantic signals. It combines coarse-grained semantic clustering, fine-grained job preference extraction via a two-type hypergraph with adaptive wavelet denoising, and personalized top-$k$ recommendations through an RNN. Empirical results show strong offline performance across three real-world datasets and robust online performance in a live deployment, highlighting practical viability for dynamic recruitment settings. The approach offers scalable, noise-robust personalization that remains effective amid resume revisions and evolving job preferences.

Abstract

Job recommender systems are crucial for aligning job opportunities with job-seekers in online job-seeking. However, users tend to adjust their job preferences to secure employment opportunities continually, which limits the performance of job recommendations. The inherent frequency of preference drift poses a challenge to promptly and precisely capture user preferences. To address this issue, we propose a novel session-based framework, BISTRO, to timely model user preference through fusion learning of semantic and behavioral information. Specifically, BISTRO is composed of three stages: 1) coarse-grained semantic clustering, 2) fine-grained job preference extraction, and 3) personalized top-$k$ job recommendation. Initially, BISTRO segments the user interaction sequence into sessions and leverages session-based semantic clustering to achieve broad identification of person-job matching. Subsequently, we design a hypergraph wavelet learning method to capture the nuanced job preference drift. To mitigate the effect of noise in interactions caused by frequent preference drift, we innovatively propose an adaptive wavelet filtering technique to remove noisy interaction. Finally, a recurrent neural network is utilized to analyze session-based interaction for inferring personalized preferences. Extensive experiments on three real-world offline recruitment datasets demonstrate the significant performances of our framework. Significantly, BISTRO also excels in online experiments, affirming its effectiveness in live recruitment settings. This dual success underscores the robustness and adaptability of BISTRO. The source code is available at https://github.com/Applied-Machine-Learning-Lab/BISTRO.

Figures (8)

• Figure 1: A toy example in the online recruitment platform.
• Figure 2: The framework overview of BISTRO. The framework is divided into three parts: coarse-grained semantic clustering, fine-grained job preference extraction, and personalized top-$k$ job recommendation.
• Figure 3: Two types of hyperedges.
• Figure 4: Results of model performance in relation to the proportion of noise in data.
• Figure 5: Results of denoising performance.

Theorems & Definitions (3)

• Definition 1
• Definition 2
• Definition 3