Time series prediction of under-five mortality rates for Nigeria: comparative analysis of artificial neural networks, Holt-Winters exponential smoothing and autoregressive integrated moving average models

Abstract

Background Accurate forecasting model for under-five mortality rate (U5MR) is essential for policy actions and planning. While studies have used traditional time series modeling techniques (e.g., autoregressive integrated moving average (ARIMA) and Holt-Winters smoothing exponential methods), their appropriateness to predict noisy and non-linear data (such as childhood mortality) has been debated. The objective of this study was to model long-term U5MR with group method of data handling (GMDH)-type artificial neural network (ANN), and compare the forecasts with the commonly used conventional statistical methods—ARIMA regression and Holt-Winters exponential smoothing models. Methods The historical dataset of annual U5MR in Nigeria from 1964 to 2017 was obtained from the official website of World Bank. The optimal models for each forecasting methods were used for forecasting mortality rates to 2030 (ending of Sustainable Development Goal era). The predictive performances of the three methods were evaluated, based on root mean squared errors (RMSE), root mean absolute error (RMAE) and modified Nash-Sutcliffe efficiency (NSE) coefficient. Statistically significant differences in loss function between forecasts of GMDH-type ANN model compared to each of the ARIMA and Holt-Winters models were assessed with Diebold-Mariano (DM) test and Deming regression. Results The modified NSE coefficient was slightly lower for Holt-Winters methods (96.7%), compared to GMDH-type ANN (99.8%) and ARIMA (99.6%). The RMSE of GMDH-type ANN (0.09) was lower than ARIMA (0.23) and Holt-Winters (2.87). Similarly, RMAE was lowest for GMDH-type ANN (0.25), compared with ARIMA (0.41) and Holt-Winters (1.20). From the DM test, the mean absolute error (MAE) was significantly lower for GMDH-type ANN, compared with ARIMA (difference = 0.11, p-value = 0.0003), and Holt-Winters model (difference = 0.62, p-value< 0.001). Based on the intercepts from Deming regression, the predictions from GMDH-type ANN were more accurate (β0 = 0.004 ± standard error: 0.06; 95% confidence interval: − 0.113 to 0.122). Conclusions GMDH-type neural network performed better in predicting and forecasting of under-five mortality rates for Nigeria, compared to the ARIMA and Holt-Winters models. Therefore, GMDH-type ANN might be more suitable for data with non-linear or unknown distribution, such as childhood mortality. GMDH-type ANN increases forecasting accuracy of childhood mortalities in order to inform policy actions in Nigeria.

Changing patterns of gender inequities in childhood mortalities during the Sustainable Development Goals era in Nigeria: findings from an artificial neural network analysis

“…Judging by the coefficient of the intercept from Deming regression, modified Nash-Sutcliffe efficiency coefficient model, root mean squared error (RMSE), root mean absolute error (MAE) and Diebold-Mariano test, GMDH-type ANN outperformed the conventional statistical techniques (ARIMA and Holt-Winters models) and LSTM RNN. 21 The comprehensive details of the different statistical methods can be found in our previous article. 21 …”

“… 21 The comprehensive details of the different statistical methods can be found in our previous article. 21 …”

“…20 Prior to long-term forecasting, the aggregated historical U5MR was first implemented with autoregressive integrated moving average (ARIMA) regression, Holt-Winters exponential smoothing model, long short-term memory recurrent neural network (LSTM RNN) and GMDHtype ANN. 21 This initial intermethod assessment was to determine the best forecasting technique for childhood mortality data for Nigeria. Judging by the coefficient of the intercept from Deming regression, modified Nash-Sutcliffe efficiency coefficient model, root mean squared error (RMSE), root mean absolute error (MAE) and Diebold-Mariano test, GMDH-type ANN outperformed the conventional statistical techniques (ARIMA and Holt-Winters models) and LSTM RNN.…”

Comparison between Mexican and International Medical Graduates’ scores in the ENARM Competing for Clinical Specialities in Mexico during 2012-2019: Data Visualization, Trends and Forecasting Analyses

“…We forecasted our quantitative time-series data using a triple exponential smoothing method, which is also called Holt-Winters exponential smoothing [19,20]. It was applied using ©Tableau software.…”

Machine Learning-Based Algorithms to Knowledge Extraction from Time Series Data: A Review

“…The number of iterations carried out before finishing learning is an arbitrary parameter, but in choosing it, you must keep in mind the problems arising from overfitting [95]. Once the network training process is complete, the model obtained can be used to make predictions.…”