---
title: Machine Learning Execution Time in Asset Pricing
url: https://www.ml-quant.com/papers/ssrn/4623947/
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 4623947
source_url: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4623947
featured: 2023-11-08
citations: unknown
topic: Trading, Microstructure & Execution
---


# Machine Learning Execution Time in Asset Pricing

The research analyzes the execution time of machine learning models in empirical asset pricing, finding that XGBoost is the fastest and most accurate, and that reducing features and time observations can significantly cut execution time.

- Source: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4623947
- Identifier: SSRN 4623947
- Released: 2023-10-31
- First featured: Quant Letter No. 25 (2023-11-08): https://www.ml-quant.com/issues/2023-11-08/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- Topic: Trading, Microstructure & Execution

## Related

- [Machine Learning Execution Time in Asset Pricing](https://www.ml-quant.com/papers/ssrn/4587923/): The XGBoost machine learning model is found to be highly accurate and efficient in empirical asset pricing, with improved performance through feature reduction and shorter time observations.
- [Improving Project Cost Estimates](https://www.ml-quant.com/papers/repec/taf-tprsxx-v-62-y-2024-i-12-p-4372-4388/): A machine learning model using XGBoost has been developed to enhance the accuracy of project cost forecasting, providing consistent and accurate estimates throughout project execution.
- [FAST: Efficient Action Tokenization for Vision-Language-Action Models](https://www.ml-quant.com/papers/arxiv/2501.09747/): A new tokenization scheme, Frequency-space Action Sequence Tokenization (FAST), has been proposed for robot actions, facilitating the training of vision-language action policies for complex and high-frequency tasks.
- [Deep Reinforcement Learning for Active High Frequency Trading](https://www.ml-quant.com/papers/arxiv/2101.07107/): A new Deep Reinforcement Learning framework has been developed for high frequency stock trading, showing potential for profitable long-term strategies.
- [Trading with Concave Price Impact and Impact Decay - Theory and Evidence](https://www.ml-quant.com/papers/ssrn/4625040/): The research examines statistical arbitrage issues, taking into account the nonlinear and temporary price impact of metaorders, and shows that simple trading rules can be established even with nonparametric alpha and liquidity signals.
- [Relative Arbitrage Opportunities in an Extended Mean Field System](https://www.ml-quant.com/papers/arxiv/2311.02690/): The article presents a theoretical model to analyze arbitrage opportunities in a market with unlimited investors, confirming the existence of a unique mean field equilibrium.