What question did this study set out to answer?

The aim is to compare various forecasting models for predicting daily returns of the Pakistan Stock Exchange's KSE-100 Index.

April 18, 2026Open Access

Intelligent forecasting in emerging markets: A comparison of AI, linear, and hybrid forecasting models at Pakistan Stock Exchange

Puntos clave

The aim is to compare various forecasting models for predicting daily returns of the Pakistan Stock Exchange's KSE-100 Index.
Analyzed data from July 2019 to June 2024 for the KSE-100 Index.
Evaluated traditional econometric models like ARIMA and OLS alongside AI models, including LSTM and CNN.
Used hybrid frameworks, integrating methods like Wavelet-LSTM and ARIMA-LSTM for improved accuracy.
Divided data into 80% training and 20% testing sets for out-of-sample validation.
Assessed performance using RMSE, MAE, MAPE, and directional accuracy.
Hybrid models outperformed standalone AI and traditional models in forecasting accuracy.
Wavelet-LSTM achieved the lowest forecast errors and an out-of-sample directional accuracy of 89.26%.
Findings suggest the importance of noise reduction and nonlinear feature extraction in financial modeling.
Caution is advised in relying on MAPE under conditions of near-zero returns.

Resumen

Abstract This study presents a systematic comparison of linear, artificial intelligence (AI), and hybrid forecasting models for predicting daily returns of Pakistan’s KSE-100 Index, an emerging market characterized by volatility and data scarcity. Daily data spanning July 2019 to June 2024 is employed to evaluate traditional econometric approaches including autoregressive integrated moving average (ARIMA) and ordinary least squares (OLS) models, alongside deep learning architectures, including long short-term memory (LSTM) networks and convolutional neural networks (CNNs), as well as hybrid frameworks integrating signal decomposition and machine learning (Wavelet-LSTM and ARIMA-LSTM). The sample is segregated into 80% training and 20% testing sets to ensure rigorous out-of-sample validation. Forecast performance is assessed using root mean squared error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE), Theil’s U statistic, and directional accuracy. Empirical evidence indicates that hybrid architectures consistently outperform both standalone AI and traditional models in out-of-sample forecasting. The Wavelet-LSTM specification achieves the lowest forecast errors and an out-of-sample directional accuracy of 89.26% which reflect substantial improvements relative to benchmark models. These findings highlight the importance of noise reduction and nonlinear feature extraction in modeling financial time series within emerging markets. However, statistical forecasting superiority does not inherently imply economic profitability in the absence of transaction cost and risk-adjusted performance analysis. Results further suggest caution in relying on MAPE in environments characterized by near-zero returns.

Preguntar a la IA

Me gusta

Guardar

Ver artículo completo