Unveiling the optimal factor model in Pakistan: a machine learning approach using support vector regression and extreme gradient boosting algorithms

Abstract This study examines the explanatory power of Fama–French models to find the optimal model and pointing out the critical factors applying the grid search cross-validation (GridSearchCV)-based support vector regression (SVR) and extreme gradient boosting (XGBoost) in the Pakistani Stock Marke...

Full description

Saved in:
Bibliographic Details
Main Authors: Rizwan Ullah, Muhammad Naveed Jan, Muhammad Tahir
Format: Article
Language:English
Published: SpringerOpen 2025-06-01
Series:Future Business Journal
Subjects:
Online Access:https://doi.org/10.1186/s43093-025-00560-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850222518632185856
author Rizwan Ullah
Muhammad Naveed Jan
Muhammad Tahir
author_facet Rizwan Ullah
Muhammad Naveed Jan
Muhammad Tahir
author_sort Rizwan Ullah
collection DOAJ
description Abstract This study examines the explanatory power of Fama–French models to find the optimal model and pointing out the critical factors applying the grid search cross-validation (GridSearchCV)-based support vector regression (SVR) and extreme gradient boosting (XGBoost) in the Pakistani Stock Market. Data from 1990 to 2022 was collected from DataStream, and 100 test portfolios were formed, bivariate sorted on input factors to ensure accuracy and robustness. ANOVA and Diebold–Mariano tests were applied to pick the best model, while SHAP (SHapley Additive exPlanations) and TreeSHAP analyses identified the significant input factors by using the explainable artificial intelligence (ExP AI). Results reveal a six-factor model outperforms others, while market and size factors are the most influential factors. Opposing to Fama and French five-factor model, the value factor remains vital in the Pakistani equity market, like India and China, while investment factor is the least influential factor. Through the box-plot graphs, robustness was confirmed. The findings recommend investors should prioritize market and size risks, while policymakers should focus on growth of SME’s (small- and medium-size enterprises) and macroeconomic stability to ensure and enhance market efficiency.
format Article
id doaj-art-e56d504697474406b588efeb6cac3fe8
institution OA Journals
issn 2314-7210
language English
publishDate 2025-06-01
publisher SpringerOpen
record_format Article
series Future Business Journal
spelling doaj-art-e56d504697474406b588efeb6cac3fe82025-08-20T02:06:19ZengSpringerOpenFuture Business Journal2314-72102025-06-0111112010.1186/s43093-025-00560-4Unveiling the optimal factor model in Pakistan: a machine learning approach using support vector regression and extreme gradient boosting algorithmsRizwan Ullah0Muhammad Naveed Jan1Muhammad Tahir2COMSATS University IslamabadCOMSATS University IslamabadCOMSATS University IslamabadAbstract This study examines the explanatory power of Fama–French models to find the optimal model and pointing out the critical factors applying the grid search cross-validation (GridSearchCV)-based support vector regression (SVR) and extreme gradient boosting (XGBoost) in the Pakistani Stock Market. Data from 1990 to 2022 was collected from DataStream, and 100 test portfolios were formed, bivariate sorted on input factors to ensure accuracy and robustness. ANOVA and Diebold–Mariano tests were applied to pick the best model, while SHAP (SHapley Additive exPlanations) and TreeSHAP analyses identified the significant input factors by using the explainable artificial intelligence (ExP AI). Results reveal a six-factor model outperforms others, while market and size factors are the most influential factors. Opposing to Fama and French five-factor model, the value factor remains vital in the Pakistani equity market, like India and China, while investment factor is the least influential factor. Through the box-plot graphs, robustness was confirmed. The findings recommend investors should prioritize market and size risks, while policymakers should focus on growth of SME’s (small- and medium-size enterprises) and macroeconomic stability to ensure and enhance market efficiency.https://doi.org/10.1186/s43093-025-00560-4Asset pricingEmerging marketMachine learningSHAP
spellingShingle Rizwan Ullah
Muhammad Naveed Jan
Muhammad Tahir
Unveiling the optimal factor model in Pakistan: a machine learning approach using support vector regression and extreme gradient boosting algorithms
Future Business Journal
Asset pricing
Emerging market
Machine learning
SHAP
title Unveiling the optimal factor model in Pakistan: a machine learning approach using support vector regression and extreme gradient boosting algorithms
title_full Unveiling the optimal factor model in Pakistan: a machine learning approach using support vector regression and extreme gradient boosting algorithms
title_fullStr Unveiling the optimal factor model in Pakistan: a machine learning approach using support vector regression and extreme gradient boosting algorithms
title_full_unstemmed Unveiling the optimal factor model in Pakistan: a machine learning approach using support vector regression and extreme gradient boosting algorithms
title_short Unveiling the optimal factor model in Pakistan: a machine learning approach using support vector regression and extreme gradient boosting algorithms
title_sort unveiling the optimal factor model in pakistan a machine learning approach using support vector regression and extreme gradient boosting algorithms
topic Asset pricing
Emerging market
Machine learning
SHAP
url https://doi.org/10.1186/s43093-025-00560-4
work_keys_str_mv AT rizwanullah unveilingtheoptimalfactormodelinpakistanamachinelearningapproachusingsupportvectorregressionandextremegradientboostingalgorithms
AT muhammadnaveedjan unveilingtheoptimalfactormodelinpakistanamachinelearningapproachusingsupportvectorregressionandextremegradientboostingalgorithms
AT muhammadtahir unveilingtheoptimalfactormodelinpakistanamachinelearningapproachusingsupportvectorregressionandextremegradientboostingalgorithms