What type of study is this?

This is a Quantitative Study study.

October 1, 2025Journal of Economics Finance and Accounting StudiesOpen Access

Deep Learning Architectures for High-Frequency Stock Price Prediction: An Empirical Evaluation

View Full Paper

Ask AI

Bookmark

Authors

RZRasheed ZakariaThe University of Texas MD Anderson Cancer Center SAS M Shamsil ArefinInstitute of Child and Mother Health SSSarder Abdulla Al ShiamSt. Francis College

Discussion

Member takes

Implication

Empirical evaluation shows deep learning models outperform traditional methods in high-frequency trading, highlighting key architectures for investment strategies.

Key Points

Transformers consistently outperform traditional models in predicting stock prices, especially in high-frequency scenarios.
Evaluation metrics reveal that attention-based architectures provide better predictive power and efficiency than recurrent models.
Traditional econometric models struggle to capture the complexity of high-frequency financial data compared to deep learning methods.
The study emphasizes the importance of model choice in algorithmic trading and risk management practices.

Cite This Study

Zakaria et al. (2025) studied this question.

synapsesocial.com/papers/68dd89defe798ba2fc497b82 https://doi.org/10.32996/jefas.2025.7.6.3

View Full Paper

Ask AI

Bookmark

Implication

Empirical evaluation shows deep learning models outperform traditional methods in high-frequency trading, highlighting key architectures for investment strategies.

Deep Learning Architectures for High-Frequency Stock Price Prediction: An Empirical Evaluation

Discussion

Member takes

Implication

Key Points

Cite This Study

Deep Learning Architectures for High-Frequency Stock Price Prediction: An Empirical Evaluation

Discussion

Member takes

Implication

Key Points

Cite This Study

Also Consider

Also Consider