Towards Unified Multimodal Financial Forecasting: Integrating Sentiment Embeddings and Market Indicators via Cross-Modal Attention

Sarthak Khanna, Armin Berger, David Berghaus, Tobias Deusser, Lorenz Sparrenberg +1 more
8/18/2025
cs.AI

No confident code implementation found for this paper.

Abstract

We propose STONK (Stock Optimization using News Knowledge), a multimodal framework integrating numerical market indicators with sentiment-enriched news embeddings to improve daily stock-movement prediction. By combining numerical & textual embeddings via feature concatenation and cross-modal attention, our unified pipeline addresses limitations of isolated analyses. Backtesting shows STONK outperforms numeric-only baselines. A comprehensive evaluation of fusion strategies and model configurations offers evidence-based guidance for scalable multimodal financial forecasting. Source code is available on GitHub

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

Multimodal Language Models with Modality-Specific Experts for Financial Forecasting from Interleaved Sequences of Text and Time Series

82% match1 repo52025

MEANT: Multimodal Encoder for Antecedent Information

81% match2024

UniCast: A Unified Framework for Instance-Conditioned Multimodal Time-Series Forecasting

81% match2025

MC-DBN: A Deep Belief Network-Based Model for Modality Completion

80% match1 repo82024

HARLF: Hierarchical Reinforcement Learning and Lightweight LLM-Driven Sentiment Integration for Financial Portfolio Optimization

80% match2025

Cross-Lingual News Event Correlation for Stock Market Trend Prediction

80% match2024

Cite this paper

@article{khanna2025towards,
  title  = {Towards Unified Multimodal Financial Forecasting: Integrating Sentiment Embeddings and Market Indicators via Cross-Modal Attention},
  author = {Sarthak Khanna and Armin Berger and David Berghaus and Tobias Deusser and Lorenz Sparrenberg and Rafet Sifa},
  year   = {2025},
  eprint = {2508.13327},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2508.13327v1}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2508.13327.svg)](https://codeofpaper.com/paper/2508.13327)

Discussion