Deep Learning Stock Index Forecasting Against Tuned Learners and Naive Baselines Under a Leakage-Free Protocol
Machine Learning and Knowledge Extraction · 06.11.2026 · 8 (11) · 366
DOI: 10.3390/make8110366 ↗Kurz gefasst
Studienprotokoll in der Zeitschrift Machine Learning and Knowledge Extraction, online erschienen am 06.11.2026. Verfasst von Arsanchai Sukkuea und 3 weiteren Autor:innen. Die Arbeit nennt 83 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Deep learning forecasters of stock index direction often report high accuracy, but results are rarely checked under leakage-free protocols, against naive baselines, or across markets. We compared compact deep networks, classical learners, and naive rules for next-day direction over 3910 out-of-sample sessions (2022–2025), with SET100, the S&P 500, and CSI 300 as confirmatory markets and SET50, whose test years an earlier single-market version of this work had used, as exploratory. All models shared one point-in-time contract with expanding windows, purged boundaries, and train-only scaling; tuned and extended arms (GRU, TCN, DLinear, PatchTST-style, and MLP networks) selected settings on validation windows only, and the comparison was repeated with stationary features. No network showed a significant advantage over logistic regression or persistence in any confirmatory market, with original or stationary features, and equivalence within ±2 points was not established, so small advantages can be neither confirmed nor excluded. Cross-entropy networks mostly collapsed to all-up forecasts (AUC 0.43–0.55). A tuned random forest on CSI 300 (55.0% balanced accuracy) outperformed an independence benchmark in the Pesaran–Timmermann test after joint adjustment but showed no significant paired improvement over the competing baselines and lost significance with stationary features; it remains a candidate for prospective testing, not evidence of dependable skill. The study evaluates directional forecasting, not trading profitability. Single protocol errors raised the raw accuracy to 80%, and reporting 100 minus the mean absolute percentage error gave 99%. Code and predictions are openly available.
Zitieren
APA
Sukkuea, A., Rungwallapa, T., Tharu, N. K., & Akkajit, P. (2026). Deep Learning Stock Index Forecasting Against Tuned Learners and Naive Baselines Under a Leakage-Free Protocol. Machine Learning and Knowledge Extraction, 8(11), 366. https://doi.org/10.3390/make8110366
Vancouver
Sukkuea A, Rungwallapa T, Tharu NK, Akkajit P. Deep Learning Stock Index Forecasting Against Tuned Learners and Naive Baselines Under a Leakage-Free Protocol. Machine Learning and Knowledge Extraction. 2026;8(11):366. doi:10.3390/make8110366
BibTeX
@article{Sukkuea2026,
author = {Sukkuea, Arsanchai and Rungwallapa, Tanawat and Tharu, Nanda Kumar and Akkajit, Pensiri},
title = {Deep Learning Stock Index Forecasting Against Tuned Learners and Naive Baselines Under a Leakage-Free Protocol},
journal = {Machine Learning and Knowledge Extraction},
year = {2026},
volume = {8},
number = {11},
pages = {366},
doi = {10.3390/make8110366}
}
EUVIMED