Predictive Analysis of COVID-19 Patients in Thailand using Multiple Countries Data

Abstract

COVID-19 is a situation that has spread worldwide since 2019. This study predicts the number of patients with COVID-19 in Thailand. Using data between January 22, 2020, and December 31, 2021, we collect confirmed cases from John Hopkins open data. Using the machine learning model to predict the number of patient cases in the country helps the government manage its policies and resources. In this study, the K-Means clustering algorithm performs to group the countries that have similar patterns of confirmed cases to Thailand. Clustering results show that Japan, Malaysia, the Philippines, Bangladesh, Cuba, Iraq, Mexico, and Vietnam are all in the same cluster as Thailand. Using Long Short-Term Memory (LSTM) to predict the confirmed case of Thailand by feeding the model pairs of countries in the same cluster as Thailand, the performance of LSTM shows that using pairs of countries between Bangladesh, Japan, and Mexico with Thailand has the lowest error on MAPE, respectively, when compared to using only Thailand data.

Predictive Analysis of COVID-19 Epidemic in Thailand: Evaluating Control Lockdown Measures using LSTM Networks

“…However, differences in datasets, assumptions, and model complexity levels across study areas should be noted, potentially impacting the fairness of this comparison. Moreover, Vorathamthongdee, & Chongstitvatana (2023) suggest that incorporating data from countries paired with Thailand into the LSTM model improves the accuracy of predictions. In the study by Winalai et al (2022), the delayed lag for predictors is set to 7, in accordance with the COVID-19 incubation period.…”