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

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Khezresmaeilzadeh, Tina, Razmara, Parsa, Azizi, Seyedarmin, Sadeghi, Mohammad Erfan, Potraghloo, Erfan Baghaei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908870934265856
author Khezresmaeilzadeh, Tina
Razmara, Parsa
Azizi, Seyedarmin
Sadeghi, Mohammad Erfan
Potraghloo, Erfan Baghaei
author_facet Khezresmaeilzadeh, Tina
Razmara, Parsa
Azizi, Seyedarmin
Sadeghi, Mohammad Erfan
Potraghloo, Erfan Baghaei
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2505_18570
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle VISTA: Vision-Language Inference for Training-Free Stock Time-Series Analysis
Khezresmaeilzadeh, Tina
Razmara, Parsa
Azizi, Seyedarmin
Sadeghi, Mohammad Erfan
Potraghloo, Erfan Baghaei
Machine Learning
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.
title VISTA: Vision-Language Inference for Training-Free Stock Time-Series Analysis
topic Machine Learning
url https://arxiv.org/abs/2505.18570