What question did this study set out to answer?

This research aims to improve the prediction accuracy of binary stock price movements by addressing noise and trend dynamics in financial time series.

May 4, 2026Mathematics1 citationsOpen Access

PULSE-KAN: A Modular Neural Architecture for Stock Movement Prediction

PULSE-KAN: Price-Aware Unified Linear-Attention and Smoothed-Trend Encoder with Kolmogorov–Arnold Network Head for Stock Movement Prediction

View Full Paper

Ask AI

Bookmark

Authors

XZXingwang Zhang JLJiabo Li

Discussion

Member takes

Overview

Randomized trial demonstrates enhanced stock movement prediction using PULSE-KAN architecture, implying improved accuracy and trend awareness.

Key Points

This research aims to improve the prediction accuracy of binary stock price movements by addressing noise and trend dynamics in financial time series.
Proposed PULSE-KAN architecture integrates three components: P-EMA Trend Bridge for trend representation, Pola Pulse Router for temporal aggregation, and KAN Signal Refiner for nonlinear decision boundaries.
Experiments conducted on two public benchmark datasets comparing PULSE-KAN against traditional recurrent and attention-based models.
PULSE-KAN shows superior classification accuracy compared to baseline models with a statistically significant increase in the Matthews Correlation Coefficient.
Each modular component of PULSE-KAN independently contributes to the overall performance enhancement.

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/69f837c23ed186a739981ef3 https://doi.org/10.3390/math14091494

View Full Paper

Ask AI

Bookmark

May 4, 2026Mathematics1 citationsOpen Access

PULSE-KAN: A Modular Neural Architecture for Stock Movement Prediction

PULSE-KAN: Price-Aware Unified Linear-Attention and Smoothed-Trend Encoder with Kolmogorov–Arnold Network Head for Stock Movement Prediction

View Full Paper

Ask AI

Bookmark

Authors

XZXingwang Zhang JLJiabo Li

Discussion

Member takes

Overview

Randomized trial demonstrates enhanced stock movement prediction using PULSE-KAN architecture, implying improved accuracy and trend awareness.

Key Points

This research aims to improve the prediction accuracy of binary stock price movements by addressing noise and trend dynamics in financial time series.
Proposed PULSE-KAN architecture integrates three components: P-EMA Trend Bridge for trend representation, Pola Pulse Router for temporal aggregation, and KAN Signal Refiner for nonlinear decision boundaries.
Experiments conducted on two public benchmark datasets comparing PULSE-KAN against traditional recurrent and attention-based models.
PULSE-KAN shows superior classification accuracy compared to baseline models with a statistically significant increase in the Matthews Correlation Coefficient.
Each modular component of PULSE-KAN independently contributes to the overall performance enhancement.

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/69f837c23ed186a739981ef3 https://doi.org/10.3390/math14091494

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark