Can Perturbations Help Reduce Investment Risks? Risk-Aware Stock Recommendation via Split Variational Adversarial Training

Paper: arXiv 2304.11043

Authors: Jiezhu Cheng, Kaizhu Huang, Zibin Zheng

Abstract

In the stock market, a successful investment requires a good balance between profits and risks. Based on the learning to rank paradigm, stock recommendation has been widely studied in quantitative finance to recommend stocks with higher return ratios for investors. Despite the efforts to make profits, many existing recommendation approaches still have some limitations in risk control, which may lead to intolerable paper losses in practical stock investing. To effectively reduce risks, we draw inspiration from adversarial learning and propose a novel Split Variational Adversarial Training (SVAT) method for risk-aware stock recommendation. Essentially, SVAT encourages the stock model to be sensitive to adversarial perturbations of risky stock examples and enhances the model’s risk awareness by learning from perturbations. To generate representative adversarial examples as risk indicators, we devise a variational perturbation generator to model diverse risk factors. Particularly, the variational architecture enables our method to provide a rough risk quantification for investors, showing an additional advantage of interpretability. Experiments on several real-world stock market datasets demonstrate the superiority of our SVAT method. By lowering the volatility of the stock recommendation model, SVAT effectively reduces investment risks and outperforms state-of-the-art baselines by more than 30% in terms of risk-adjusted profits. All the experimental data and source code are available at https://drive.google.com/drive/folders/14AdM7WENEvIp5x5bV3zV_i4Aev21C9g6?usp=sharing.

Complexity vs Empirical Score

• Math Complexity: 6.5/10
• Empirical Rigor: 6.0/10 (capped from 8.0: transaction costs not modelled; see penalty flags)
• Quadrant: Holy Grail — high math complexity, high empirical rigor

Why this score: The paper introduces a novel application of Split Variational Adversarial Training (SVAT) to stock recommendation, effectively bridging deep generative/adversarial models with risk management. It features rigorous real-world backtesting against state-of-the-art baselines and provides open-access code and data for full reproducibility.

Research Flowchart

  flowchart TD
    A[Research Goal: Reduce stock investment risks using adversarial perturbations] --> B[Input Data: Real-world stock market datasets]
    B --> C[Methodology: Split Variational Adversarial Training - SVAT]
    C --> D[Computational Process: Variational Perturbation Generator models diverse risk factors]
    D --> E[Computational Process: Train model to be sensitive to risky adversarial examples]
    E --> F[Outcomes: Risk quantification interpretability & reduced model volatility]
    F --> G[Key Finding: >30% improvement in risk-adjusted profits over SOTA baselines]