Impact of Expert-Following Strategies in Financial Asset Recommendation

2026-07-16

AI Summary

This study addresses the challenge of simultaneously optimizing return on investment (ROI) and alignment with user preferences, as measured by normalized discounted cumulative gain (nDCG), in financial asset recommendation. The authors propose a “follow-the-expert” strategy that identifies historically high-performing investors based on ROI and constructs a recommendation scoring mechanism weighted by their ROI-adjusted purchase frequencies. This approach uniquely achieves concurrent improvements in both ROI and nDCG, overcoming the limitations of conventional single-objective optimization methods. Experimental results on real-world trading data demonstrate that the proposed method significantly outperforms market-average benchmarks across four evaluation thresholds, effectively balancing profitability and personalization.

Abstract

Financial institutions hold rich transaction histories, yet delivering recommendations that simultaneously maximize investment returns and ensure preference alignment remains a significant challenge. Existing approaches, namely return-based and preference-based strategies, each optimize a single objective, resulting in a fundamental trade-off between profitability (ROI) and relevance (nDCG). In this paper, we propose the Expert-Following Strategies: a framework that identifies top-performing investors based on their historical ROI and recommends the assets they purchased, scored by ROI-weighted purchase frequency. Our experiments using real-world transaction histories show that our strategy achieves statistically significant improvement over the market-average baseline in both ROI and nDCG simultaneously across all four thresholds.

Problem

• financial asset recommendation
• return optimization
• preference alignment
• ROI
• nDCG

Innovation

• Expert-Following Strategies
• ROI-weighted recommendation
• multi-objective optimization
• financial asset recommendation
• preference alignment