---
title: Bi-objective Cost-sensitive Machine Learning: Predicting Stock Return Direction Using Option Prices
url: https://www.ml-quant.com/papers/ssrn/4546402/
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 4546402
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4546402
featured: 2023-08-24
citations: 0
topic: Derivatives & Volatility
---


# Bi-objective Cost-sensitive Machine Learning: Predicting Stock Return Direction Using Option Prices

The research investigates the use of cost-sensitive loss functions in machine learning models to predict equity market index movement, using option prices as a measure of error costs.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4546402
- Identifier: SSRN 4546402
- Released: 2023-08-21
- First featured: Quant Letter No. 13 (2023-08-24): https://www.ml-quant.com/issues/2023-08-24/
- Citations (Semantic Scholar): 0
- Published in: not yet
- Topic: Derivatives & Volatility

## Related

- ['I'm Stranded': Transition Risk Information in CDS and Options](https://www.ml-quant.com/papers/ssrn/4551442/): The research uses CDS and put option prices to gauge the likelihood and impact of climate change policy-related transition risk events, creating a reliable CDS-based index.
- [On Sparse Grid Interpolation for American Option Pricing with Multiple Underlying Assets](https://www.ml-quant.com/papers/arxiv/2309.08287/): The first article introduces a new method for pricing American options with multiple assets, combining dynamic programming and sparse grid-based polynomial interpolation.
- [Approximation Rates for Deep Calibration of (Rough) Stochastic Volatility Models](https://www.ml-quant.com/papers/arxiv/2309.14784/): The paper offers quantitative error limits for deep neural networks approximating option prices on a risky asset, demonstrating that DNNs can learn option prices with minimal error without the curse of dimensionality.
- [Machine learning for option pricing: an empirical investigation of network architectures](https://www.ml-quant.com/papers/arxiv/2307.07657/): A study finds that the generalized highway network and a DGM variant improve the accuracy and training time of machine learning algorithms for option pricing.
- [A fast Monte Carlo scheme for additive processes and option pricing](https://www.ml-quant.com/papers/arxiv/2112.08291/): The article introduces a quick Monte Carlo method for additive processes, improving accuracy in pricing options that depend on a specific path.
- [Deep Learning of Transition Probability Densities for Stochastic Asset Models with Applications in Option Pricing](https://www.ml-quant.com/papers/arxiv/2105.10467/): New ultra-fast and highly accurate neural Transition Probability Density Function generators have been developed for use in computational finance.