Trading Confidence: Comprehensive Uncertainty Estimation in Algorithmic Trading
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.
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
Exploring Agentic Tool-Calling Decisions via Uncertainty-Aligned Reinforcement Learning
This paper proposes TRUST, a method that integrates uncertainty quantification into reinforcement learning reward design to improve LLM agents' tool-calling decisions, enhancing decision quality and maintaining reliable uncertainty estimates.
AI-Trader: Benchmarking Autonomous Agents in Real-Time Financial Markets
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.
Tracing sources of epistemic uncertainty in deep learning predictions: homo- and hetero-scedastic linearized estimators
The paper adapts classical statistical estimators to deep learning for tracing epistemic uncertainty into aleatoric and data-scarcity sources, leveraging approximate Fisher Information Matrices for scalability.
Uncertainty-Aware and Temporally Regulated Expert Advice in Reinforcement Learning for Autonomous Driving
This paper proposes an uncertainty-aware reinforcement learning framework for autonomous driving that uses expert advice guided by adaptive uncertainty thresholds and a commitment-cooldown strategy to improve safety and efficiency. Experiments in the CARLA simulator show a 5-7% success improvement over the IQN baseline.
A Unified Risk View of Uncertainty: Posterior Risk for Disentanglement and Evaluation Beyond Proxies
This paper proposes a unified definition of uncertainty as pointwise posterior risk and introduces a theory-backed benchmark using semi-synthetic datasets to directly compute oracle epistemic and aleatoric uncertainty, enabling fine-grained evaluation beyond proxy tasks.