Reasoning on Time-Series for Financial Technical Analysis

2025-11-06

AI Summary

This work addresses the domain gap between financial time series and natural language inference. We propose Verbal Technical Analysis (VTA), a framework that converts stock price sequences into structured textual descriptions and jointly models them using large language models (LLMs) and time-series backbone networks. To enhance interpretability and accuracy, VTA introduces an inverse mean squared error (inverse-MSE) reward mechanism to optimize reasoning paths, enabling the generation of explainable natural language reasoning chains alongside high-precision trend forecasts. VTA is the first approach to unify human-readable reasoning with predictive performance in technical analysis. Empirical evaluations across U.S., Chinese, and European markets demonstrate statistically significant improvements over state-of-the-art baselines. Moreover, the generated reasoning chains have received strong validation from domain experts in finance.

Technology Category

• Natural Language Processing: (Large) Language Models
• Machine Learning: Large Multimodal Models (LMMs)
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Web Mining and Content Analysis: Large pretrained models with web data
• Search and Retrieval-Augmented AI: Search Tool Learning with LLM: Teaching LLMs to invoke search and make use of retrieved information
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

While Large Language Models have been used to produce interpretable stock forecasts, they mainly focus on analyzing textual reports but not historical price data, also known as Technical Analysis. This task is challenging as it switches between domains: the stock price inputs and outputs lie in the time-series domain, while the reasoning step should be in natural language. In this work, we introduce Verbal Technical Analysis (VTA), a novel framework that combine verbal and latent reasoning to produce stock time-series forecasts that are both accurate and interpretable. To reason over time-series, we convert stock price data into textual annotations and optimize the reasoning trace using an inverse Mean Squared Error (MSE) reward objective. To produce time-series outputs from textual reasoning, we condition the outputs of a time-series backbone model on the reasoning-based attributes. Experiments on stock datasets across U.S., Chinese, and European markets show that VTA achieves state-of-the-art forecasting accuracy, while the reasoning traces also perform well on evaluation by industry experts.

Problem

• Combining time-series analysis with natural language reasoning
• Converting stock price data into interpretable textual annotations
• Generating accurate forecasts using verbal-latent reasoning framework

Innovation

• Converts stock price data into textual annotations
• Optimizes reasoning trace using inverse MSE reward
• Conditions time-series outputs on reasoning attributes