Leveraging Vision-Language Models for Granular Market Change Prediction
Utilizing Vision-Language models for predicting stock market changes using image and text representations of data.
What it examines
This study explores a novel approach to stock market prediction by using Vision-Language models to process image and text representations of stock data, aiming to improve market forecasting accuracy.
What it concludes
The study concludes that CLIP-based models offer remarkable performance in market forecasting, with potential applications in real-time trading and financial decision-making. Future research could explore other markets and data periods to generalize the findings.
Evidence objects
The study concludes that CLIP-based models offer remarkable performance in market forecasting, with potential applications in real-time trading and financial decision-making. Future research could explore other markets and data periods to generalize the findings.
key_findings bullet 1 · key_findings · validation V0
Raw abstract and provenance
Abstract: Predicting future direction of stock markets using the historical data has been a fundamental component in financial forecasting. This historical data contains the information of a stock in each specific time span, such as the opening, closing, lowest, and highest price. Leveraging this data, the future direction of the market is commonly predicted using various time-series models such as Long-Sho… ▽ More Predicting future direction of stock markets using the historical data has been a fundamental component in financial forecasting. This historical data contains the information of a stock in each specific time span, such as the opening, closing, lowest, and highest price. Leveraging this data, the future direction of the market is commonly predicted using various time-series models such as Long-Short Term Memory networks. This work proposes modeling and predicting market movements with a fundamentally new approach, namely by utilizing image and byte-based number representation of the stock data processed with the recently introduced Vision-Language models. We conduct a large set of experiments on the hourly stock data of the German share index and evaluate various architectures on stock price prediction using historical stock data. We conduct a comprehensive evaluation of the results with various metrics to accurately depict the actual performance of various approaches. Our evaluation results show that our novel approach based on representation of stock data as text (bytes) and image significantly outperforms strong deep learning-based baselines. △ Less
Source row: 1204 · abstract type: unknown