---
title: Impact of Evaluation Metrics on ML Models for Stock Market Indices
url: https://www.ml-quant.com/papers/repec/avo-emipdu-v-32-y-2023-i-2-p-533-545/
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: RePEc:avo:emipdu:v:32:y:2023:i:2:p:533-545
source_url: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fhrcak.srce.hr%2Findex.php%2Fclanak%2F448608%3Bh%3Drepec%3Aavo%3Aemipdu%3Av%3A32%3Ay%3A2023%3Ai%3A2%3Ap%3A533-545
featured: 2023-12-20
citations: unknown
topic: Trading, Microstructure & Execution
---


# Impact of Evaluation Metrics on ML Models for Stock Market Indices

The study reveals that the choice of machine learning algorithm significantly affects the financial performance of trading systems, with the random forest algorithm proving most effective.

- Source: https://econpapers.repec.org/scripts/redir.pf?u=https%3A%2F%2Fhrcak.srce.hr%2Findex.php%2Fclanak%2F448608%3Bh%3Drepec%3Aavo%3Aemipdu%3Av%3A32%3Ay%3A2023%3Ai%3A2%3Ap%3A533-545
- Identifier: RePEc:avo:emipdu:v:32:y:2023:i:2:p:533-545
- Released: 2023-12-20
- First featured: Quant Letter No. 30 (2023-12-20): https://www.ml-quant.com/issues/2023-12-20/
- Citations (Semantic Scholar): not tracked
- Published in: not yet
- 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.
- [Deep reinforcement learning for arbitrage in decentralized exchanges](https://www.ml-quant.com/papers/ssrn/4666504/): The study explores trading performances under arbitrage conditions in decentralized exchanges, using a simulation model and deep reinforcement learning to determine optimal arbitrage strategies for eight cryptocurrency pairs.
- [Limit Order Book Dynamics and Order Size Modelling Using Compound Hawkes Process](https://www.ml-quant.com/papers/arxiv/2312.08927/): The research introduces a new method using Compound Hawkes Process to model Limit Order Book dynamics, taking into account order size and maintaining a positive spread.
- [Deep Reinforcement Learning: Policy Gradients for US Equities Trading](https://www.ml-quant.com/papers/ssrn/4645453/): The study shows that Deep Reinforcement Learning can effectively interpret synthetic alpha signals in financial trading, outperforming the market benchmark.
- [The Paradox Of Just-in-Time Liquidity in Decentralized Exchanges: More Providers Can Sometimes Mean Less Liquidity](https://www.ml-quant.com/papers/arxiv/2311.18164/): The research analyzes the paradox of just-in-time (JIT) liquidity provision in decentralized exchanges, which can reduce liquidity, and suggests a two-tiered fee structure to counteract this.