Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Robust meta gradient learning for high-dimensional data with noisy-label ignorance.

PloS one·2023
See all related articles

Related Experiment Video

Updated: Jul 10, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

559

A Framework for Enhancing Stock Investment Performance by Predicting Important Trading Points with Return-Adaptive

Yu Lin1,2, Ben Liu1,2

  • 1Joint Lab of Data Science and Business Intelligence, Southwestern University of Finance and Economics, Chengdu 610074, China.

Entropy (Basel, Switzerland)
|November 24, 2023
PubMed
Summary

This study introduces a new framework for predicting important trading points (ITPs) in stock markets using advanced AI models. The approach enhances stock investment returns by improving prediction accuracy and risk management.

Keywords:
Batch Attention Multi-Scale Convolution Recurrent Neural Network (Batch-MCRNN)Return-Adaptive Piecewise Linear Representation (RA-PLR)important trading points (ITPs)stock markettrading strategy

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

409
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K

Related Experiment Videos

Last Updated: Jul 10, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

559
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

409
Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
06:37

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention

Published on: December 15, 2023

3.8K

Area of Science:

  • Quantitative Finance
  • Machine Learning
  • Algorithmic Trading

Background:

  • Stock market data is inherently noisy and random, making precise price prediction difficult.
  • Existing prediction models often suffer from lagging, hindering the capture of market turning points and reducing investment returns.
  • The need for accurate stock analysis and forecasting to improve returns and mitigate risks is critical for market participants.

Purpose of the Study:

  • To propose a novel framework for predicting Important Trading Points (ITPs) to enhance stock investment returns.
  • To address the limitations of traditional stock price prediction and lagging phenomena in trading strategies.
  • To develop a robust trading strategy integrated with ITP predictions for improved performance.

Main Methods:

  • Utilized Return-Adaptive Piecewise Linear Representation (RA-PLR) for historical ITP detection.
  • Employed a Batch Attention Multi-Scale Convolution Recurrent Neural Network (Batch-MCRNN) for future ITP prediction, integrating spatial, temporal, and sample data dimensions.
  • Developed a trading strategy combining the Relative Strength Index (RSI) and Double Check (DC) method for ITP prediction matching.

Main Results:

  • The proposed RA-PLR and Batch-MCRNN framework significantly outperformed state-of-the-art benchmark models in prediction accuracy.
  • The method demonstrated superior performance across various indicators, including risk and return metrics, on real-world stock market datasets.
  • The integrated trading strategy effectively leveraged ITP predictions, leading to improved investment outcomes compared to existing approaches.

Conclusions:

  • The developed framework offers a significant advancement in stock market analysis and forecasting by accurately predicting ITPs.
  • The combination of RA-PLR and Batch-MCRNN provides a powerful tool for navigating noisy market data and capturing turning points.
  • This research holds substantial reference value for stock market participants seeking to optimize investment strategies and enhance returns.