COVID-19 Case Prediction Model Comparison

Important Notice: Due to the discontinuation of daily COVID-19 case reporting to the WHO, our daily predictions have been discontinued. The information below represents our last available data and predictions.

This page displays a 7-day comparison of COVID-19 case predictions using four different models: LSTM/GRU (Long Short-Term Memory/Gated Recurrent Unit), ARIMA (AutoRegressive Integrated Moving Average), Random Forest, and XGBoost. The graphs below show our predictions against the actual reported cases and compare the performance of all models.

Model Performance

The performance of each model is measured using the Mean Absolute Percentage Error (MAPE). Lower values indicate better performance.

LSTM/GRU

MAPE

ARIMA

MAPE

Random Forest

MAPE

XGBoost

MAPE

Last Updated: Loading...

7-Day Model Comparison

This chart displays the actual cases and predicted number of COVID-19 cases for the last 7 days, comparing all four models: LSTM/GRU, ARIMA, Random Forest, and XGBoost.

Actual Cases

LSTM/GRU Model

ARIMA Model

Random Forest Model

XGBoost Model

Methodology

We used four different models for time series forecasting:

LSTM/GRU (Long Short-Term Memory/Gated Recurrent Unit) neural network model
ARIMA (AutoRegressive Integrated Moving Average) model
Random Forest Regressor
XGBoost Regressor

All models were trained on COVID-19 case data from the WHO dataset. Our prediction pipeline followed these steps:

Daily data collection from the WHO COVID-19 dataset
Data preprocessing and cleaning
Feature creation with a sequence length of 90 days
Model training with the latest data
7-day hindcast generation for all models
Comparison of predictions with actual reported cases
Calculation of Mean Absolute Percentage Error (MAPE) for each model

For more details on our methodology, please visit our GitHub repository.