---
title: Combining Machine Learning Classifiers for Stock Trading with Effective Feature Extraction
url: https://www.ml-quant.com/papers/doi/10-1504-ijcse-2023-129152/
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: doi:10.1504/ijcse.2023.129152
source_url: http://dx.doi.org/10.1504/ijcse.2023.129152
featured: 2023-08-17
citations: 4
topic: Trading, Microstructure & Execution
---


# Combining Machine Learning Classifiers for Stock Trading with Effective Feature Extraction

A machine learning model using ensemble learning was developed to make profitable trades in the US stock market, dynamically selecting the top 25 features from 148 before each training session, yielding a 54.35% profit from 2011 to 2019.

- Source: http://dx.doi.org/10.1504/ijcse.2023.129152
- Identifier: doi:10.1504/ijcse.2023.129152
- Released: 2021-07-28
- First featured: Quant Letter No. 12 (2023-08-17): https://www.ml-quant.com/issues/2023-08-17/
- Citations (Semantic Scholar): 4
- Published in: International Journal of Computational Science and Engineering (IJCSE)
- Topic: Trading, Microstructure & Execution

## Related

- [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.
- [Microstructure-Empowered Stock Factor Extraction and Utilization](https://www.ml-quant.com/papers/arxiv/2308.08135/): A new model has been suggested to better predict stock trends and improve order execution by analyzing high-frequency order flow data in stock investment.
- [UAMM: Price-oracle based Automated Market Maker](https://www.ml-quant.com/papers/arxiv/2308.06375/): UBET Market Maker: A new method, UBET AMM (UAMM), is proposed for decentralized exchanges, which calculates prices based on external market prices and liquidity pool loss, effectively removing arbitrage opportunities when external market prices are efficient.
- [Model-Free Analysis of Dynamic Trading Strategies](https://www.ml-quant.com/papers/arxiv/2011.02870/): A new method for analyzing risk and return in dynamic trading strategies is introduced, using a mathematical framework and a non-parametric scenario simulation method that matches empirical data.
- [On Regularized Optimal Execution Problems and Their Singular Limits](https://www.ml-quant.com/papers/arxiv/2101.02731/): The research proposes a unique solution for optimal trading rate under uncertain volatility and liquidity, using a multidimensional Markovian stochastic factor.