COVID-19 Cases Prediction in Saudi Arabia Using Tree-based Ensemble Models

Abstract

COVID-19 pandemic has affected more than 144 million people and spread to over 200 countries. The prediction of COVID-19 behaviour and trend is crucial to prevent its spreading. Kingdom of Saudi Arabia (KSA) is Asia's fifth largest country, and it hosts the two holiest cities of the Islamic world. KSA hosts millions of pilgrims every year, and it is of great importance to predict the COV-ID-19 spread to organize these religious activities and bring life to normality in KSA. This study proposes four tree-based ensemble methods to predict the COV-ID-19 daily new cases in KSA. Tree-based ensemble methods are suggested to reduce the variance and/or bias of inconsistent models. The four models utilized in the study are Gradient Tree Boosting (GB), Random Forest (RF), Extreme Gradient Boosting (XGBoost) and Voting Regressor (VR). The study is conducted using "Our Data in World" (OWID) COVID-19 dataset from the first confirmed case in KSA, i.e., 2nd March 2020 to 14th April 2021. The results suggest that the tree-based ensemble models provide a good prediction of daily COVID-19 new cases and can follow the trend of COVID-19. Among the models, XGBoost and VR performed better than the other three models with the best evaluation metric scores (MAE:4.41, RMSE:7.11, MAPE:0.95%). The significant prediction power of the tree-based ensemble methods, especially XGBoost can provide the platform for policymakers to put strategic plans for the closure periods of the educational institutions and organize Hajj and Umrah.

An interpretable hybrid predictive model of COVID-19 cases using autoregressive model and LSTM

“…Extreme Gradient Boosting (XGBoost) 44 , 46 , 48 has shown exceptional performance in various tasks. XGBoost is an ensemble learning method based on gradient boosting trees.…”

“… Study Dataset Models Results Atik 42 Turkey Support Vector Machine (SVM), Linear Regression, Bagged Tree, Fine Tree SVM has the highest R value (99%) and the lowest RMSE and MAE values. Galasso et al 43 USA counties Random Forest MAE below 300 weekly cases/100,000, using easily accessible training features Ali et al 44 Saudi Arabia Gradient Tree Boosting, Random Forest, XGBoost, Voting Regressor The XGBoost and Voting Regressor model outperform the other models Chumachenko et al 45 Germany, Japan, South Korea, and Ukraine Random Forest, K-Nearest Neighbors, Gradient Boosting The Gradient Boosting model has the best performance by related error and MAE Fang et al 46 USA ARIMA, XGBoost The XGBoost model outperforms the ARIMA model on COVID-19 case prediction in the USA Muhammad et al 47 Mexico Logistic Regression, Decision Tree, SVM, Naive Bayes, and Artificial Neutral Network Decision tree model has the highest accuracy (94.99%). SVM model has the highest sensitivity (93.34%).…”

Design of Middle School Chemistry Experiment Simulation System Based on Apriori Algorithm

“…To develop the VR fire hazard troubleshooting system, we first need to understand all the hidden dangers of fire in the dormitory [15], store the information of these hidden danger points, use 3dsmax to model and texture map the dormitory scene, establish an exquisite model corresponding to all the hidden danger points, import it into the unity engine [16], and develop the interactive function module of hidden danger point troubleshooting in the unity engine, Use intersecting ball detection technology and adding explosion point technology to add fire and explosion effects for each hidden danger point [17], design eye-catching UI, provide clear experience for the experimenter, and finally release the generated system to HTC vive [18]. The overall process is shown in Fig.…”

Prediction of the number of COVID-19 confirmed cases using the hybrid FUCOM-Pareto analysis- random forest method

“…Almazroi ve Usmani (2022); Suudi Arabistan'daki günlük onaylanmış COVID-19 vakalarını tahmin etmek için gradyan artırma, rastgele orman, ekstrem gradyan arttırma ve voting regresyon yöntemi içeren ağaç tabanlı topluluk yöntemi önermektedir. Çalışmanın önemli özelliğinden biri de onaylanmış vaka sayısının yanı sıra aşılama, seyahat yasakları ve okulların/ iş yerlerinin kapatılması dahil olmak üzere dokuz bileşeni içeren 'Stringency indeks' değişkenlerini girdi olarak kullanmasıdır [11].…”