ReSGA: A Large Tail Risk Model for Learning Value-at-Risk and Expected Shortfall

• URL: http://arxiv.org/abs/2606.04576v1
• Date: Wed, 03 Jun 2026 08:11:45 GMT
• Title: ReSGA: A Large Tail Risk Model for Learning Value-at-Risk and Expected Shortfall
• Abstract summary: We propose a retrieval-enhanced self-grouping autoencoder (ReSGA) to exploit the rich cross-sectional dependence and long-term temporal dynamics of assets.<n>ReSGA is applied to monthly US equity returns from 1926 to 2023 with 153 firm characteristics.
• Score: 18.057073658552458
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: Learning Value-at-Risk (VaR) and Expected Shortfall (ES) is important for managing financial risks effectively. Existing approaches with limited parameters are vulnerable to model misspecification in the era of big data. To address this limitation, we propose a large tail risk model, the retrieval-enhanced self-grouping autoencoder (ReSGA), which is designed with millions of parameters to exploit the rich cross-sectional dependence and long-term temporal dynamics of assets using their characteristics. Applied to monthly US equity returns from 1926 to 2023 with 153 firm characteristics, ReSGA outperforms twelve econometric and machine learning competitors in terms of out-of-sample loss and statistical backtesting. In addition, its forecast advantages can translate into significant economic gains from long-short decile portfolios that are constructed by a new size-enhanced left-side momentum strategy. To clarify the role of complexity, we further conduct a systematic scaling analysis and demonstrate that improvements in joint VaR-ES forecasting are primarily driven by data complexity rather than model complexity. Finally, our analyses of group-importance and transfer-learning exhibit the interpretability and cross-market generalizability of ReSGA.

Related papers

• Enhancing a Risk Model by Adding Transient Statistical Factors [90.40844650665713]
  Estimating asset returns is a key component of financial portfolio construction and evaluation.<n>We propose a systematic method based on maximum likelihood estimation to enhance an existing factor model.<n>We show that the proposed extension captures structure in the returns that is missed by the original model.
  arXiv  Detail & Related papers  (2026-05-13T04:15:24Z)
• Mitigating Reward Hacking in RLHF via Bayesian Non-negative Reward Modeling [49.41422138354821]
  We propose a principled reward modeling framework that integrates non-negative factor analysis into the Bradley-Terry preference model.<n>BNRM represents rewards through a sparse, non-negative latent factor generative process.<n>We show that BNRM substantially mitigates reward over-optimization, improves robustness under distribution shifts, and yields more interpretable reward decompositions than strong baselines.
  arXiv  Detail & Related papers  (2026-02-11T08:14:11Z)
• Towards Scaling Laws for Symbolic Regression [45.609070591068836]
  Symbolic regression aims to discover the underlying mathematical expressions that explain observed data.<n>Deep learning-based SR has recently become competitive with genetic programming approaches.<n>We present the first systematic investigation of scaling in SR, using a scalable end-to-end transformer pipeline.
  arXiv  Detail & Related papers  (2025-10-30T01:36:44Z)
• Dependency Network-Based Portfolio Design with Forecasting and VaR Constraints [8.107171581224312]
  This study proposes a novel portfolio optimization framework that integrates statistical social network analysis with time series forecasting and risk management.<n>Using daily stock data from the S&P 500 ( 2020-2024), we construct dependency networks via Vector Autoregression ( VAR) and Forecast Error Variance Decomposition (FEVD)<n>FEVD breaks down the VAR's forecast error variance to quantify how much each stock's shocks contribute to another's uncertainty information we invert to form influence-based edge weights in our network.<n>A dynamic portfolio is constructed using the top-ranked stocks, with capital allocated based on Value at Risk (
  arXiv  Detail & Related papers  (2025-07-26T18:53:39Z)
• Overparametrized models with posterior drift [0.0]
  This paper investigates the impact of posterior drift on out-of-sample forecasting accuracy in overparametrized machine learning models.<n>For the average investor, we find that focusing on holding periods of 15 years can generate very heterogeneous returns.<n>All in all, our findings tend to recommend cautiousness when resorting to large linear models for stock market predictions.
  arXiv  Detail & Related papers  (2025-06-30T08:31:15Z)
• Multi-Agent Stock Prediction Systems: Machine Learning Models, Simulations, and Real-Time Trading Strategies [0.0]
  This paper presents a comprehensive study on stock price prediction, leveraging advanced machine learning (ML) and deep learning (DL) techniques to improve financial forecasting accuracy.<n>The research evaluates the performance of various recurrent neural network (RNN) architectures, including Long Short-Term Memory (LSTM) networks, Gated Recurrent Units (GRU)<n>Our findings show that attention-based models outperform other architectures, achieving the highest accuracy by capturing both short and long-term dependencies.
  arXiv  Detail & Related papers  (2025-02-21T06:36:16Z)
• On the Diminishing Returns of Complex Robust RAG Training in the Era of Powerful LLMs [85.688901949146]
  We investigate the question: does the benefit of complex robust training methods diminish as language models become more powerful?<n>Our analysis reveals a consistent trend: emphthe marginal robustness benefit of sophisticated training strategies decreases substantially as model capacity increases.<n>Further investigation demonstrates that stronger models naturally exhibit better confidence calibration, cross-dataset generalization capability, and more effective attention patterns, even under simple training regimes.
  arXiv  Detail & Related papers  (2025-02-17T03:34:31Z)
• Optimizing Sequential Recommendation Models with Scaling Laws and Approximate Entropy [104.48511402784763]
  Performance Law for SR models aims to theoretically investigate and model the relationship between model performance and data quality.<n>We propose Approximate Entropy (ApEn) to assess data quality, presenting a more nuanced approach compared to traditional data quantity metrics.
  arXiv  Detail & Related papers  (2024-11-30T10:56:30Z)
• Temporal Relational Reasoning of Large Language Models for Detecting Stock Portfolio Crashes [47.34457229947238]
  We propose an algorithmic framework named Temporal Reasoning (TRR)<n>TRR seeks to emulate the spectrum of human cognitive capabilities used for complex problem-solving.<n>We show that TRR is able to outperform state-of-the-art techniques on detecting stock portfolio crashes.
  arXiv  Detail & Related papers  (2024-10-07T11:15:52Z)
• Semi-Supervised Reward Modeling via Iterative Self-Training [52.48668920483908]
  We propose Semi-Supervised Reward Modeling (SSRM), an approach that enhances RM training using unlabeled data. We demonstrate that SSRM significantly improves reward models without incurring additional labeling costs. Overall, SSRM substantially reduces the dependency on large volumes of human-annotated data, thereby decreasing the overall cost and time involved in training effective reward models.
  arXiv  Detail & Related papers  (2024-09-10T22:57:58Z)
• Application of Deep Learning for Factor Timing in Asset Management [21.212548040046133]
  More flexible models have better performance in explaining the variance in factor premium of the unseen period. For flexible models like neural networks, the optimal weights based on their prediction tend to be unstable. We verify that tilting down the rebalance frequency according to the historical optimal rebalancing scheme can help reduce the transaction costs.
  arXiv  Detail & Related papers  (2024-04-27T21:57:17Z)
• Financial Time-Series Forecasting: Towards Synergizing Performance And Interpretability Within a Hybrid Machine Learning Approach [2.0213537170294793]
  This paper propose a comparative study on hybrid machine learning algorithms and leverage on enhancing model interpretability. For the interpretability, we carry out a systematic overview on the preprocessing techniques of time-series statistics, including decomposition, auto-correlational function, exponential triple forecasting, which aim to excavate latent relations and complex patterns appeared in the financial time-series forecasting.
  arXiv  Detail & Related papers  (2023-12-31T16:38:32Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.