Zero-Shot Probabilistic Stock Returns Forecasting with Pretrained RVFL Networks

T. Moudiki
Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications, PMLR 329:1119-1124, 2026.

Abstract

We ask whether a zero-shot pretrained quasi-randomized functional link network (Moudiki et al., 2018) (QRVFL) for univariate time series can match a student-t eGARCH model at multi-step probabilistic stock return forecasting, without explicitly specifying volatility dynamics. Using formal equivalence tests across 15 equity time series of length equal to 500 days, three forecast horizons (h $\in$ {5, 10, 21} trading days ahead), and a rolling window cross validation (with 400 training days), we show that the RVFL is statistically equivalent to eGARCH on point accuracy and distributional calibration (within given margins), while producing slightly tighter 95% prediction intervals and running 10$\times$ faster than the eGARCH implementation (with simulations enabled for both models) from R package rugarch.

Cite this Paper

BibTeX
@InProceedings{pmlr-v329-moudiki26a, title = {Zero-Shot Probabilistic Stock Returns Forecasting with Pretrained RVFL Networks}, author = {Moudiki, T.}, booktitle = {Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications}, pages = {1119--1124}, year = {2026}, editor = {Ahlberg, Ernst and Johansson, Ulf and Boström, Henrik and Carlevaro, Alberto and Hallberg Szabadváry, Johan and Carlsson, Lars}, volume = {329}, series = {Proceedings of Machine Learning Research}, month = {02--04 Sep}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/v329/main/assets/moudiki26a/moudiki26a.pdf}, url = {https://proceedings.mlr.press/v329/moudiki26a.html}, abstract = {We ask whether a zero-shot pretrained quasi-randomized functional link network (Moudiki et al., 2018) (QRVFL) for univariate time series can match a student-t eGARCH model at multi-step probabilistic stock return forecasting, without explicitly specifying volatility dynamics. Using formal equivalence tests across 15 equity time series of length equal to 500 days, three forecast horizons (h $\in$ {5, 10, 21} trading days ahead), and a rolling window cross validation (with 400 training days), we show that the RVFL is statistically equivalent to eGARCH on point accuracy and distributional calibration (within given margins), while producing slightly tighter 95% prediction intervals and running 10$\times$ faster than the eGARCH implementation (with simulations enabled for both models) from R package rugarch.} }
Endnote
%0 Conference Paper %T Zero-Shot Probabilistic Stock Returns Forecasting with Pretrained RVFL Networks %A T. Moudiki %B Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications %C Proceedings of Machine Learning Research %D 2026 %E Ernst Ahlberg %E Ulf Johansson %E Henrik Boström %E Alberto Carlevaro %E Johan Hallberg Szabadváry %E Lars Carlsson %F pmlr-v329-moudiki26a %I PMLR %P 1119--1124 %U https://proceedings.mlr.press/v329/moudiki26a.html %V 329 %X We ask whether a zero-shot pretrained quasi-randomized functional link network (Moudiki et al., 2018) (QRVFL) for univariate time series can match a student-t eGARCH model at multi-step probabilistic stock return forecasting, without explicitly specifying volatility dynamics. Using formal equivalence tests across 15 equity time series of length equal to 500 days, three forecast horizons (h $\in$ {5, 10, 21} trading days ahead), and a rolling window cross validation (with 400 training days), we show that the RVFL is statistically equivalent to eGARCH on point accuracy and distributional calibration (within given margins), while producing slightly tighter 95% prediction intervals and running 10$\times$ faster than the eGARCH implementation (with simulations enabled for both models) from R package rugarch.
APA
Moudiki, T.. (2026). Zero-Shot Probabilistic Stock Returns Forecasting with Pretrained RVFL Networks. Proceedings of the Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications, in Proceedings of Machine Learning Research 329:1119-1124 Available from https://proceedings.mlr.press/v329/moudiki26a.html.

Related Material