Blending Econometric and Deep Learning Approaches for Enhanced Volatility Forecasting of the KSE-100 Index
Year: 2025
Type: article
Abstract: The objective of this study is to develop a hybrid forecasting model that combines statistical and machine learning techniques to predict stock market volatility in Pakistan.The dataset used spans from January 2019 to December 2023, and the model's accuracy is evaluated using Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE).Traditional forecasting models often struggle to account for market uncertainty due to external economic factors, such as IMF policies and currency fluctuations.By utilising non-linear techniques, including Autoregressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM), Linear Regression, and Generalised Autoregressive Conditional Heteroscedasticity (GARCH), this study aims to enhance volatility predictions, thereby enabling quicker and more informed investment decisions.
Authors: Ubaida Fatima, Rimsha Zafar, Syeda Arsala Shah, Abdus Samad
Institution: NED University of Engineering and Technology
Language: English
Field: Decision Sciences
Domain: Social Sciences
Open Access status: diamond
OpenAlex ID: W4413888096