Trading Confidence: Comprehensive Uncertainty Estimation in Algorithmic Trading

arXiv cs.LG Papers

Summary

Proposes an uncertainty-aware reinforcement learning framework for algorithmic trading that integrates distributional, epistemic, and aleatoric uncertainty using SHAP-weighted reconstruction, MC Dropout, and LSTM consensus. Outperforms traditional models on five major US stock indices.

arXiv:2607.02864v1 Announce Type: new Abstract: Reinforcement Learning (RL) has emerged as a powerful approach in financial trading, enabling agents to learn optimal strategies through direct market interaction. However, financial markets are highly uncertain, with price fluctuations driven by stochastic volatility, model limitations, and regime shifts. Traditional RL models struggle in dynamic environments, often failing to adapt to sudden market disruptions, leading to suboptimal trading decisions. To address this challenge, we propose an uncertainty-aware RL framework that integrates distributional, epistemic, and aleatoric uncertainty estimations. Our approach enhances uncertainty estimation using SHAP-weighted reconstruction uncertainty, MC Dropout, and an LSTM-based technical indicator consensus mechanism. Experimental results on five major U.S. stock indices demonstrate that RL agents equipped with uncertainty estimation significantly outperform traditional models in return and risk management. This study advances uncertainty estimation in RL-based financial trading, with future research extending its application to other asset classes and alternative RL architectures for greater adaptability.
Original Article
View Cached Full Text

Cached at: 07/07/26, 04:39 AM

# Trading Confidence: Comprehensive Uncertainty Estimation in Algorithmic Trading
Source: [https://arxiv.org/abs/2607.02864](https://arxiv.org/abs/2607.02864)
[View PDF](https://arxiv.org/pdf/2607.02864)

> Abstract:Reinforcement Learning \(RL\) has emerged as a powerful approach in financial trading, enabling agents to learn optimal strategies through direct market interaction\. However, financial markets are highly uncertain, with price fluctuations driven by stochastic volatility, model limitations, and regime shifts\. Traditional RL models struggle in dynamic environments, often failing to adapt to sudden market disruptions, leading to suboptimal trading decisions\. To address this challenge, we propose an uncertainty\-aware RL framework that integrates distributional, epistemic, and aleatoric uncertainty estimations\. Our approach enhances uncertainty estimation using SHAP\-weighted reconstruction uncertainty, MC Dropout, and an LSTM\-based technical indicator consensus mechanism\. Experimental results on five major U\.S\. stock indices demonstrate that RL agents equipped with uncertainty estimation significantly outperform traditional models in return and risk management\. This study advances uncertainty estimation in RL\-based financial trading, with future research extending its application to other asset classes and alternative RL architectures for greater adaptability\.

## Submission history

From: Lin Li \[[view email](https://arxiv.org/show-email/959c50c0/2607.02864)\] **\[v1\]**Fri, 3 Jul 2026 02:02:15 UTC \(1,638 KB\)

Similar Articles

AI-Trader: Benchmarking Autonomous Agents in Real-Time Financial Markets

Papers with Code Trending

This paper introduces AI-Trader, the first fully automated live benchmark for evaluating LLMs in financial decision-making across US stocks, A-shares, and cryptocurrencies. It highlights that general intelligence does not guarantee trading success and emphasizes the importance of risk control in autonomous agents.