HybridSwingNet for explainable swing trading using multi-encoder deep learning and confidence-calibrated signal execution
4 affiliations
- 1Department of Computer Engineering, Pimpri Chinchwad College of Engineering
- 2Department of Computer Science, Applied College, Princess Nourah bint Abdulrahman University
- 3School of Computer Sciences, University of Petroleum and Energy Studies (UPES)
- 4Department of Computer Science, King Khalid University
Abstract
The challenge with swing trading is that short to medium term price movements are noisy, fast moving and dominated by transient technical, contextual and sentiment driven signals. Existing forecasting approaches typically treat these information sources independently or fuse them via static fusion, which limits the adaptability, selectivity and interpretability in non-stationary markets. To address this issue, this paper proposes a hybrid multi-encoder deep learning framework that combines multi-source market signals with dynamic fusion and confidence-aware signal execution for explainable swing-trading decisions. The key novelties are horizon-specific feature routing, adaptive multi-encoder fusion and calibrated confidence filtering which enable the model to focus on different representations across forecast horizons in a transparent and execution-aware manner. On a 100-stock Indian equity universe (84 Nifty 100 constituents + 16 large-cap Nifty 500 additions) over 2013–2026, the framework achieves 68.7% H1 smoothed-trend directional accuracy on held-out test stocks (70.2% on a fully blind holdout set; p = 3.18× 10−63 ), rising to 82.9% (test) / 85.3% (blind) at a 0.75 confidence threshold. The Conservative profile yields +11.51% (Sharpe 1.2) across 2025 over 85 trades, with a profit factor of 1.43 (win rate 54.1%) when combined with a dynamic regime filter and full Indian retail delivery transaction costs ( 41 basis points round-trip). A second out of sample period is negative in 2026 and truthfully reported in the limitations. This implies that the main contribution of the framework is to transform noisy forecasts into selective and risk-aware trading actions.
Related
- Calibrated Reliance on Large Language Models for Personalized Surgical Care: A Critical Narrative Review of Confidence, Clinical Reasoning and Decision Support
- HistoMRIFuseNet: retrospective confidence-calibrated decision fusion of independent histopathology and DCE-MRI classifiers
- Development and temporal validation of a calibrated machine learning model for in-hospital blood culture positivity using routine clinical data
- Explainable machine learning and deep learning models for predicting in-hospital mortality in burn patients
- EEG Biomarkers for Rett Syndrome: A Comparative Analysis of Machine Learning and Deep Learning with Explainable AI
BibTeX
@article{sambare2026hybridswingnet,
title = {{HybridSwingNet for explainable swing trading using multi-encoder deep learning and confidence-calibrated signal execution}},
author = {G. B. Sambare and Swati Shinde and Onkar Jadhav and Harsh Itkar and Lalit Deore and Sarthak Joshi and Lubna A. Gabralla and Tanupriya Choudhury and Minakshi Singh},
journal = {Scientific Reports},
year = {2026},
month = jul,
doi = {10.1038/s41598-026-63497-w},
url = {https://doi.org/10.1038/s41598-026-63497-w},
note = {CC BY},
}
RIS
TY - JOUR
TI - HybridSwingNet for explainable swing trading using multi-encoder deep learning and confidence-calibrated signal execution
AU - G. B. Sambare
AU - Swati Shinde
AU - Onkar Jadhav
AU - Harsh Itkar
AU - Lalit Deore
AU - Sarthak Joshi
AU - Lubna A. Gabralla
AU - Tanupriya Choudhury
AU - Minakshi Singh
PY - 2026
DA - 2026/07/01
JO - Scientific Reports
DO - 10.1038/s41598-026-63497-w
UR - https://doi.org/10.1038/s41598-026-63497-w
AB - The challenge with swing trading is that short to medium term price movements are noisy, fast moving and dominated by transient technical, contextual and sentiment driven signals. Existing forecasting approaches typically treat these information sources independently or fuse them via static fusion, which limits the adaptability, selectivity and interpretability in non-stationary markets. To address this issue, this paper proposes a hybrid multi-encoder deep learning framework that combines multi-source market signals with dynamic fusion and confidence-aware signal execution for explainable swing-trading decisions. The key novelties are horizon-specific feature routing, adaptive multi-encoder fusion and calibrated confidence filtering which enable the model to focus on different representations across forecast horizons in a transparent and execution-aware manner. On a 100-stock Indian equity universe (84 Nifty 100 constituents + 16 large-cap Nifty 500 additions) over 2013–2026, the framework achieves 68.7% H1 smoothed-trend directional accuracy on held-out test stocks (70.2% on a fully blind holdout set; p = 3.18× 10^−63 ), rising to 82.9% (test) / 85.3% (blind) at a 0.75 confidence threshold. The Conservative profile yields +11.51% (Sharpe 1.2) across 2025 over 85 trades, with a profit factor of 1.43 (win rate 54.1%) when combined with a dynamic regime filter and full Indian retail delivery transaction costs ( 41 basis points round-trip). A second out of sample period is negative in 2026 and truthfully reported in the limitations. This implies that the main contribution of the framework is to transform noisy forecasts into selective and risk-aware trading actions.
SN - 2045-2322
ER -