To search, Click below search items.

 

All Published Papers Search Service

Title

Comparative Analysis of Different Machine Learning Models for Estimating the Population Growth Rate in Data-Limited Area.

Author

Mohammad Mahmood Otoom , Mahdi Jemmali, Yousef Qawqzeh, Khalid Nazim S. A. and Fayez Al Fayez

Citation

Vol. 19  No. 12  pp. 96-101

Abstract

Human population growth plays a key role in any regional planning. However, in many data constraint environment, it is not possible to collect the required demographic data to predict the human population growth rate. In such a context, a tool that could help in predicting human population growth without the need to rely on historical data will be very helpful. This study compares different machine learning (ML) techniques namely k-nearest neighbors (kNN), decision trees, random forest and artificial neural network in their ability to predict the population growth rate (‘pgr’) of an area. The different demographic variables used to predict population growth rate are human population, population density, life expectancy at birth, female life expectancy at birth, infant mortality rate, under five mortality rate and total fertility rate. The study found that all the ML based models were able to predict the population growth rate with more than 90% accuracy. The top two models are kNN and Random forest with prediction accuracy of 96.47% and 95.42%. The study has demonstrated the relevance of ML models in predicting ‘pgr’ in data constraint environment.

Keywords

Machine Learning, Population Growth rate, k-nearest neighbors, decision tree, random forest, artificial neural network.

URL

http://paper.ijcsns.org/07_book/201912/20191214.pdf