A comprehensive ARIMA-LSTM hybrid model for accurate covid-19 time series forecasting in Malaysia

Title : A comprehensive ARIMA-LSTM hybrid model for accurate covid-19 time series forecasting in Malaysia

Abstract:

Introduction: The COVID-19 pandemic has underscored the need for accurate predictive models to inform public health interventions. Traditional models like Autoregressive Integrated Moving Average (ARIMA) model assume a linear relationship and constant error variance over time with in COVID-19 case trends And Long Short-Term Memory (LSTM) networks exceed in imprison nonlinear dependencies but struggles with high-dimensional data, resulting in inaccurate predictions and poor fit due to high computational demands. This study aims to robust in accuracy of COVID-19 case predictions in Malaysia by developing a hybrid ARIMALSTM model that combines the strengths of both ARIMA and LSTM approaches. 

Methodology: We trained and validated the hybrid model using real-time COVID-19 case data from the Malaysian Ministry of Health, focusing on September 12 to September 18, 2021. The best hyperparameter of the proposed model for ARIMA p = 9, d = 2, q = 2 and LSTM epochs = 472, batch size = 22 verbose = 1 respectively. The model's execution was analogous to standalone ARIMA and LSTM models using key metrics: Mean Squared Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Root Mean Square Error (RMSE), and Relative Root Mean Square Error (RRMSE). 

Results: Our analysis revealed the ARIMA-LSTM hybrid model performed much better across all criteria than either of the solo models. The lowest values of error metrics in ARIMA -LSTM hybrid model compared to others standalone models ARMA and LSTM. The values of ARIMA-LSTM hybrid model are MSE = 0.02, MAE = 0.10, MAPE = 2.80, RMSE = 0.14 and RRMSE = 0.05, respectively. 

Conclusion: The ARIMA-LSTM hybrid model offers a spirited tool for predicting COVID-19 case trends, providing valuable insights for policymakers. This study demonstrated the prospect of mixed modelsin epidemiological forecasting, with broader implications for managing public health crises

Biography:

Al Mahmud is a passionate researcher and biostatistics student with a strong foundation in statistics. He earned his BSc in Statistics from Shahjalal University of Science and Technology, Bangladesh, in 2022, and is pursuing an MSc in Biostatistics at Universiti Sains Malaysia. His research focuses on enhancing COVID-19 forecasting using a hybrid ARIMA-LSTM machine learning approach. Al Mahmud has published in journals like PLOS ONE and presented at mental health conferences. His dedication to Biostatistics and Public Health research has earned him recognition, including funding through an FRGS grant from Malaysia's Ministry of Higher Education.