PulseExploreJournal ClubDebatesTrendingResearchersJournals
Instagram
HomeExploreJournal ClubTrending
Synapse
⌘+K
Synapse
May 4, 2026Mathematics1 citationsOpen Access

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

View Full Paper
XZXingwang ZhangJLJiabo Li

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.

Abstract

Accurate prediction of binary stock price movements remains a challenging task due to the coexistence of short-term noise and medium-term trend dynamics in financial time series. Existing recurrent models typically encode raw price sequences within a single representation stream and aggregate temporal information using softmax-based attention, which often entangles noisy fluctuations with underlying trends and limits nonlinear expressiveness in the final classification stage. In this paper, we propose PULSE-KAN (Price-aware Unified Linear-attention and Smoothed-trend Encoder with Kolmogorov–Arnold Network Head), a modular neural architecture designed to enhance binary stock movement prediction. The proposed framework introduces three plug-and-play components designed for LSTM-based pipelines as demonstrated here within the Adv-ALSTM framework. First, the P-EMA Trend Bridge constructs an explicit smoothed trend representation via a parameterized exponential moving average and fuses it with the raw price stream to improve trend awareness. Second, the Pola Pulse Router performs efficient temporal aggregation using linear-complexity polarized attention combined with local convolutional priors, enabling better capture of multi-scale temporal dependencies. Third, the KAN Signal Refiner replaces the conventional linear prediction head with learnable Chebyshev-polynomial activations, providing enhanced nonlinear modeling capacity for decision boundaries. Extensive experiments on two public benchmark datasets demonstrate that PULSE-KAN consistently outperforms strong recurrent and attention-based baselines in terms of both classification accuracy and the Matthews Correlation Coefficient. Further ablation studies verify that each proposed component contributes independently and significantly to the overall performance improvement.

Ask AI
Helpful
Bookmark
Share
View Full Paper

Cite This Study

Zhang et al. (2026) studied this question.

synapsesocial.com/papers/69f837c23ed186a739981ef3https://doi.org/10.3390/math14091494
Ask AI
Helpful
Bookmark
Share
View Full Paper