VISTA: Vision-Language Inference for Training-Free Stock Time-Series Analysis

TL;DR

VISTA introduces a training-free, multi-modal approach using vision-language models to improve stock price forecasting by combining textual and visual data, outperforming traditional methods.

Contribution

It presents VISTA, a novel zero-shot framework leveraging vision-language models for stock prediction without task-specific training, integrating visual and textual data modalities.

Findings

VISTA outperforms ARIMA and text-only prompting baselines by up to 89.83%.

Multi-modal inference captures complementary patterns missed by unimodal approaches.

VISTA demonstrates the potential of vision-language models in financial forecasting.

Abstract

Stock price prediction remains a complex and high-stakes task in financial analysis, traditionally addressed using statistical models or, more recently, language models. In this work, we introduce VISTA (Vision-Language Inference for Stock Time-series Analysis), a novel, training-free framework that leverages Vision-Language Models (VLMs) for multi-modal stock forecasting. VISTA prompts a VLM with both textual representations of historical stock prices and their corresponding line charts to predict future price values. By combining numerical and visual modalities in a zero-shot setting and using carefully designed chain-of-thought prompts, VISTA captures complementary patterns that unimodal approaches often miss. We benchmark VISTA against standard baselines, including ARIMA and text-only LLM-based prompting methods. Experimental results show that VISTA outperforms these baselines by up to 89.83%, demonstrating the effectiveness of multi-modal inference for stock time-series analysis and highlighting the potential of VLMs in financial forecasting tasks without requiring task-specific training.