# Multimodal Stock Price Prediction: A Case Study of the Russian Securities Market

arXiv: https://arxiv.org/abs/2503.08696 · HTML: https://mlsanity.com/paper/2503.08696/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 9 references that are in the map.
- First posted on arXiv 5 Mar 2025.

## Builds on (most cited first, 5 of 5)

- [Adaptation of Deep Bidirectional Multilingual Transformers for Russian Language](https://mlsanity.com/paper/1905.07213/) (2019)
- [Temporal Data Meets LLM -- Explainable Financial Time Series Forecasting](https://mlsanity.com/paper/2306.11025/) (2023)
- [Instruct-FinGPT: Financial Sentiment Analysis by Instruction Tuning of General-Purpose Large Language Models](https://mlsanity.com/paper/2306.12659/) (2023)
- [Vikhr: The Family of Open-Source Instruction-Tuned Large Language Models for Russian](https://mlsanity.com/paper/2405.13929/) (2024)
- [Text Mining of Stocktwits Data for Predicting Stock Prices](https://mlsanity.com/paper/2103.16388/) (2021)

## Built on by (most cited first, 1 of 1)

- [Finance-Grounded Optimization For Algorithmic Trading](https://mlsanity.com/paper/2509.04541/) (2025)

## Abstract (arXiv)

Classical asset price forecasting methods primarily rely on numerical data, such as price time series, trading volumes, limit order book data, and technical analysis indicators. However, the news flow plays a significant role in price formation, making the development of multimodal approaches that combine textual and numerical data for improved prediction accuracy highly relevant. This paper addresses the problem of forecasting financial asset prices using the multimodal approach that combines candlestick time series and textual news flow data. A unique dataset was collected for the study, which includes time series for 176 Russian stocks traded on the Moscow Exchange and 79,555 financial news articles in Russian. For processing textual data, pre-trained models RuBERT and Vikhr-Qwen2.5-0.5b-Instruct (a large language model) were used, while time series and vectorized text data were processed using an LSTM recurrent neural network. The experiments compared models based on a single modality (time series only) and two modalities, as well as various methods for aggregating text vector representations. Prediction quality was estimated using two key metrics: Accuracy (direction of price movement prediction: up or down) and Mean Absolute Percentage Error (MAPE), which measures the deviation of the predicted price from the true price. The experiments showed that incorporating textual modality reduced the MAPE value by 55%. The resulting multimodal dataset holds value for the further adaptation of language models in the financial sector. Future research directions include optimizing textual modality parameters, such as the time window, sentiment, and chronological order of news messages.