---
title: Stock Price Crash Prediction Based on Multimodal Data Machine Learning Models
url: https://www.ml-quant.com/papers/ssrn/4575784/
site: ML-Quant (https://www.ml-quant.com)
updated: 2026-09-26
license: Summaries CC BY 4.0; links go to the original sources
index: https://www.ml-quant.com/llms.txt
identifier: SSRN 4575784
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4575784
featured: 2023-09-21
citations: 1
topic: ML & AI Methods
---


# Stock Price Crash Prediction Based on Multimodal Data Machine Learning Models

The paper suggests a machine learning framework that predicts stock market crashes by combining market data, graph data, and sentiment analysis, with LightGBM showing superior accuracy.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4575784
- Identifier: SSRN 4575784
- Released: 2023-09-19
- First featured: Quant Letter No. 16 (2023-09-21): https://www.ml-quant.com/issues/2023-09-21/
- Citations (Semantic Scholar): 1
- Published in: not yet
- Topic: ML & AI Methods

## Related

- [Online learning techniques for prediction of temporal tabular datasets with regime changes](https://www.ml-quant.com/papers/arxiv/2301.00790/): A machine learning pipeline is suggested for ranking predictions on temporal panel datasets, showing improved performance with Gradient Boosting Decision Trees models.
- [Wasserstein Gradient Boosting: A Framework for Distribution-Valued Supervised Learning](https://www.ml-quant.com/papers/arxiv/2405.09536/): Wasserstein gradient boosting, a new type of gradient boosting, improves probabilistic prediction by approximating the output-distribution parameter's posterior distribution.
- [Financial Fraud Detection System Based on Improved Random Forest and Gradient Boosting Machine (GBM)](https://www.ml-quant.com/papers/arxiv/2502.15822/): The paper suggests a financial fraud detection system that uses an improved Random Forest and Gradient Boosting Machine model, offering an efficient and reliable solution for detecting financial fraud.
- [High-Accuracy Stock Market Prediction Using Machine Learning Techniques](https://www.ml-quant.com/papers/ssrn/5235296/): The paper investigates advanced machine learning techniques for stock market prediction, concluding that deep learning models combined with sentiment features perform better than traditional methods.
- [Gender Diversity Prediction in Chinese Boardrooms with Machine Learning](https://www.ml-quant.com/papers/repec/eee-riibaf-v-66-y-2023-i-c-s0275531923001794/): A study successfully used machine learning, specifically the XGBoost model, to predict gender diversity on the boards of Chinese publicly-traded companies.
- [XGBoost Framework for Fraud Detection in Mobile Payments](https://www.ml-quant.com/papers/repec/spr-infosf-v-25-y-2023-i-5-d-10-1007-s10796-022-10346-6/): A proposed XGBoost-based framework for detecting fraud in mobile transactions was found to be most effective when combined with multiple unsupervised outlier detection algorithms.