---
title: ML Predicts Stock Volatility
url: https://www.ml-quant.com/papers/ssrn/4708642/
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 4708642
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4708642
featured: 2024-01-30
citations: unknown
topic: Derivatives & Volatility
---


# ML Predicts Stock Volatility

Machine learning algorithms, especially neural networks, can predict stock return volatility using accounting-based characteristics, with profitability-related traits being the most predictive.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4708642
- Identifier: SSRN 4708642
- Released: 2021-11-24
- First featured: Quant Letter No. 35 (2024-01-30): https://www.ml-quant.com/issues/2024-01-30/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Derivatives & Volatility

## Related

- [No-Arbitrage Deep Calibration for Volatility Smile and Skewness](https://www.ml-quant.com/papers/arxiv/2310.16703/): The introduction of a Derivative-Constrained Neural Network (DCNN) enhances the calibration of implied volatility surface in option prices, aiding in understanding market dynamics and risk management.
- [TSMixer and Realized Volatility Prediction](https://www.ml-quant.com/papers/ssrn/4713756/): Stock Volatility Forecasting with Neural Networks: The TSMixer neural network model has proven to be more effective than traditional models in predicting stock market volatility, indicating a possible shift towards simpler models in the future.
- [A deep implicit-explicit minimizing movement method for option pricing in jump-diffusion models](https://www.ml-quant.com/papers/arxiv/2401.06740/): The paper introduces a deep learning method for pricing European basket options using Artificial Neural Networks and two methods for discretizing the integral operator, focusing on assets with jump-diffusion dynamics.
- [On pricing of discrete Asian and Lookback options under the Heston model](https://www.ml-quant.com/papers/arxiv/2211.03638/): The authors suggest a data-driven method using artificial neural networks for efficient pricing of certain options, reducing computational time and increasing accuracy.
- [Computing Volatility Surfaces using Generative Adversarial Networks with Minimal Arbitrage Violations](https://www.ml-quant.com/papers/arxiv/2304.13128/): The article introduces a generative adversarial network (GAN) method for calculating volatility surfaces, showing that the GAN model is more accurate and faster than artificial neural network (ANN) methods.
- [A time-stepping deep gradient flow method for option pricing in (rough) diffusion models](https://www.ml-quant.com/papers/arxiv/2403.00746/): The study introduces a new deep learning method for pricing European options in diffusion models, transforming the option pricing equation into an energy minimization problem and using deep artificial neural networks.