A late-fusion model of CF, RL bandit, and TOPSIS achieves NDCG@5=0.3040 on JobHop (outperforming baselines) but remains competitive without significant gains on Karrierewege, with the bandit branch deactivating in persistence-dominated data.
Canay:Preprint submitted to Knowledge-Based SystemsPage 22 of 23 CF-RL-TOPSIS Fusion for Talent Recommendation Poncio, F.P.,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.IR 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
An Interpretable CF-RL-TOPSIS Fusion Model for Skills-Aware Talent Recommendation
A late-fusion model of CF, RL bandit, and TOPSIS achieves NDCG@5=0.3040 on JobHop (outperforming baselines) but remains competitive without significant gains on Karrierewege, with the bandit branch deactivating in persistence-dominated data.