EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Uncertainty-First Forecasting of the South African Equity Market Using Deep Learning and Temporal Conformal Prediction

Phumudzo Lloyd Seabe, Claude Rodrigue Bambe Moutsinga, Maggie Aphane

Big Data and Cognitive Computing · 20.03.2026 · 10 (3) · 93

DOI: 10.3390/bdcc10030093 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Big Data and Cognitive Computing, online erschienen am 20.03.2026. Verfasst von Phumudzo Lloyd Seabe und 2 weiteren Autor:innen. Die Arbeit nennt 78 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Accurate forecasting of equity returns remains fundamentally constrained by weak short-horizon predictability, pronounced noise, and structural non-stationarity. While deep learning models have been widely applied to financial time series, most studies prioritize point prediction and provide limited guidance on reliable uncertainty quantification, particularly in emerging markets. This study developed an uncertainty-aware forecasting framework for the South African equity market by integrating variational mode decomposition (VMD), gated recurrent units (GRUs), and temporal conformal prediction (TCP) to construct distribution-free prediction intervals with finite-sample coverage guarantees. Using daily returns from the FTSE/JSE All Share Index, we first confirmed that baseline recurrent models applied directly to raw returns exhibited negligible out-of-sample explanatory power, consistent with weak-form market efficiency. Incorporating VMD enhanced representation learning and improved point forecast accuracy by isolating latent frequency components. However, model-based predictive variance alone proved insufficient for reliable calibration. Embedding the models within a rolling conformal prediction framework restored near-nominal coverage across multiple confidence levels while allowing interval widths to adapt dynamically to changing volatility regimes. Robustness analyses, including walk-forward validation, stress-regime evaluation, and block permutation negative control experiments, indicated that the observed performance was not driven by temporal leakage or alignment artifacts. The results further highlight a trade-off between interval sharpness and tail-risk protection, particularly during extreme market events. Overall, the findings support a shift from return-level prediction toward calibrated uncertainty estimation as a more stable and economically meaningful objective in non-stationary financial environments.

Zitieren

APA

Seabe, P. L., Moutsinga, C. R. B., & Aphane, M. (2026). Uncertainty-First Forecasting of the South African Equity Market Using Deep Learning and Temporal Conformal Prediction. Big Data and Cognitive Computing, 10(3), 93. https://doi.org/10.3390/bdcc10030093

Vancouver

Seabe PL, Moutsinga CRB, Aphane M. Uncertainty-First Forecasting of the South African Equity Market Using Deep Learning and Temporal Conformal Prediction. Big Data and Cognitive Computing. 2026;10(3):93. doi:10.3390/bdcc10030093

BibTeX
@article{Seabe2026,
  author = {Seabe, Phumudzo Lloyd and Moutsinga, Claude Rodrigue Bambe and Aphane, Maggie},
  title = {Uncertainty-First Forecasting of the South African Equity Market Using Deep Learning and Temporal Conformal Prediction},
  journal = {Big Data and Cognitive Computing},
  year = {2026},
  volume = {10},
  number = {3},
  pages = {93},
  doi = {10.3390/bdcc10030093}
}
Kostenlos starten →