Linear Stock Rankings Survive Execution in a Thin Market: Forecasting, Selection, and Net Performance on Bursa Malaysia*
Asia-Pacific Journal of Financial Studies · 19.11.2026
DOI: 10.1111/ajfs.70068 ↗Kurz gefasst
Fachartikel in der Zeitschrift Asia-Pacific Journal of Financial Studies, online erschienen am 19.11.2026. Verfasst von Ahmad Shauqi bin Haji Mohamad Zubir und 1 weiteren Autor:innen. Die Arbeit nennt 43 Literaturangaben.
Abstract (Originalsprache)
For the 300 largest Bursa Malaysia stocks over 2022–2025, we ask whether linear and machine learning forecasts predict return levels, rank stocks, and payoff after trading costs. None predicts the level; only linear models rank stocks. In the predesignated test, a long‐only mean‐variance portfolio built on the OLS ranking earns a net Sharpe ratio of 0.58, not significantly above the FBM KLCI's 0.30. Charging the optimizer for its trades lifts the ratio to 1.16; adjusted for all strategies tested, this portfolio significantly beats a value‐weighted benchmark of the same stocks but only marginally beats the index.
Zitieren
APA
Zubir, A. S. B. H. M., & Zamani, W. N. N. B. W. M. (2026). Linear Stock Rankings Survive Execution in a Thin Market: Forecasting, Selection, and Net Performance on Bursa Malaysia*. Asia-Pacific Journal of Financial Studies. https://doi.org/10.1111/ajfs.70068
Vancouver
Zubir ASBHM, Zamani WNNBWM. Linear Stock Rankings Survive Execution in a Thin Market: Forecasting, Selection, and Net Performance on Bursa Malaysia*. Asia-Pacific Journal of Financial Studies. 2026. doi:10.1111/ajfs.70068
BibTeX
@article{Zubir2026,
author = {Zubir, Ahmad Shauqi bin Haji Mohamad and Zamani, Wan Nurul Nisrin binti Wan Mohd},
title = {Linear Stock Rankings Survive Execution in a Thin Market: Forecasting, Selection, and Net Performance on Bursa Malaysia*},
journal = {Asia-Pacific Journal of Financial Studies},
year = {2026},
doi = {10.1111/ajfs.70068}
}
EUVIMED