An Interpretable CF-RL-TOPSIS Fusion Model for Skills-Aware Talent Recommendation

2026-05-22

AI Summary

This study addresses the challenge of effectively integrating behavioral transition patterns, trajectory adaptability, and interpretable occupational hierarchy criteria in skill-aware talent recommendation. To this end, we propose the CF-RL-TOPSIS model, which dynamically integrates transition-aware collaborative filtering, occupation-family-based deep Q-network bandits, and entropy-weighted TOPSIS multi-criteria decision-making through an interpretable late-fusion mechanism. The model incorporates a fusion-coefficient auditing scheme to ensure decision traceability and adaptively adjusts branch weights based on talent mobility patterns. Evaluated on the JobHop dataset, our approach achieves an NDCG@5 of 0.3040, significantly outperforming baseline methods, and demonstrates competitive performance on the Karrierewege dataset. Furthermore, it automatically suppresses redundant branches in continuity-dominated scenarios, validating its adaptability and interpretability.

Abstract

Effective skills-aware talent recommendation must balance behavioral transition patterns, trajectory-sensitive adaptation, and inspectable occupation-level criteria. Evidence from public benchmarks on how these signals interact, however, remains limited. This study proposes CF-RL-TOPSIS, an interpretable late-fusion model that integrates a transition-aware collaborative branch, a compact reinforcement-style occupation-family bandit, and an entropy-weighted TOPSIS branch constructed from six semantic proxies; the validation-selected fusion coefficients remain auditable. The model is evaluated on two frozen public ICT talent-history benchmarks, JobHop and Karrierewege, using repeated chronological top-5 ranking and paired Wilcoxon tests. On JobHop the full hybrid attains NDCG@5 = 0.3040 +/- 0.0073 and significantly surpasses repeat-last, item Markov, transition-aware collaborative filtering, the CF+TOPSIS hybrid, GRU4Rec, and SASRec (p <= 0.0039 across planned comparisons). On Karrierewege the hybrid remains competitive but does not significantly exceed the strongest Markov baseline, revealing a persistence-dominated setting in which the bandit branch appropriately shrinks to near-zero weight. Proxy-sensitivity, family-level deep Q-network, and runtime checks support this interpretation, and a worked user-level case shows how branch scores, criterion weights, and rank shifts can be inspected for an individual recommendation. The contribution is not a benchmark-agnostic superiority claim, but a reproducible account of the conditions under which transparent late fusion adds value beyond simple continuation heuristics. In semantically rich, non-saturating talent-history regimes the three branches reinforce one another; in persistence-dominated regimes the same architecture remains competitive through its collaborative backbone, with the adaptive branch correctly inactive.

Problem

• skills-aware talent recommendation
• behavioral transition patterns
• trajectory-sensitive adaptation
• interpretable recommendation
• occupation-level criteria

Innovation

• interpretable fusion
• skills-aware recommendation
• reinforcement learning bandit
• TOPSIS multi-criteria decision
• transition-aware collaborative filtering