STEP: Career-Path Recommendation via Temporal and Educational Trajectory Modeling

2026-07-13

AI Summary

This study addresses the challenge of modeling professional trajectories from unstructured, multilingual resumes to enable accurate next-job recommendations. To this end, the authors propose STEP, a novel system that integrates a time-decayed GRU to capture temporal dynamics of career progression, a FiLM modulation mechanism conditioned on educational background, and attention-based pooling. Furthermore, they introduce ROUTE, a two-stage contrastive learning framework designed to refine career representations. The approach synergistically combines multilingual contrastive learning with denoising autoencoding strategies, achieving significant performance gains over state-of-the-art methods across four real-world career trajectory datasets. The work also contributes an enhanced version of the JobHop dataset and releases the implementation code publicly.

Abstract

Career paths encode decades of skill acquisition, role transitions, and educational investment, and understanding them at scale underpins workforce planning, labor market policy, and job recommendation. Resumes are a rich source of information about career paths: they contain detailed descriptions of work experience, education, and skills. Yet their unstructured, heterogeneous, and multilingual nature has long prevented large-scale systematic analysis. With the advent of large language models (LLMs), it is now possible to source rich career trajectory data containing temporal and educational signals from unstructured resumes, enabling new opportunities for career-path recommendation. Exploiting this opportunity, we present STEP (Sequential Trajectory of Employment Prediction), a novel career-path recommendation system that leverages temporal and educational signals to predict the next job in a career trajectory. STEP integrates a time-decay Gated Recurrent Unit (GRU) cell to model temporal dynamics, Feature-wise Linear Modulation (FiLM) conditioned on educational attainment, and attention-based sequence pooling to select relevant features for next job prediction. To improve internal occupation representation for STEP, we introduce ROUTE, a two-stage contrastive procedure that first adapts a multilingual encoder to the career domain via unsupervised denoising autoencoding, then performs supervised contrastive fine-tuning with guided negative selection. We evaluate STEP on four datasets of career trajectories, including an improved version of our publicly available JobHop dataset, and show that it outperforms state-of-the-art baselines in next job prediction. The dataset and code are publicly released to support reproducible career-trajectory research.

Problem

• career-path recommendation
• unstructured resumes
• temporal trajectory
• educational trajectory
• next job prediction

Innovation

• career-path recommendation
• temporal modeling
• educational trajectory
• contrastive learning
• large language models