Gross Domestic Product Prediction Model Using Gradient Boosting Algorithm in Machine Learning

Main Article Content

Viswanathan Chakravarthi, Karthikeyan Palaniappan, Arumugam Santhana Santhanavelu, S.Harini, R.Kamalini

Abstract

The money related worth of every completed goods and services delivered inside a country during a given time is known as the Gross Domestic Product (GDP). This paper enables us to predict the GDP of various countries and find out the factors that affect the GDP. By identifying these factors it helps us to improve the GDP of the country in the future. We have preprocessed the data and EDA is done. Exploratory Data Analysis (EDA) is a method of data analysis that uses a range of methods to gain a deeper understanding of a data set, find outliers and deviations, and identify key variables. We then predict the GDP per capita of the countries with the help of parameters such as population, Area (sq .mi), population density, coastline, net migration, infant mortality, literacy, birth rate, death rate, etc. We have compared the performance of the model using 3 algorithms and the best prediction performance is achieved by Gradient Boosting, followed by Random forest and Linear regression.

Article Details

How to Cite
Viswanathan Chakravarthi, Karthikeyan Palaniappan, Arumugam Santhana Santhanavelu, S.Harini, R.Kamalini. (2021). Gross Domestic Product Prediction Model Using Gradient Boosting Algorithm in Machine Learning . Annals of the Romanian Society for Cell Biology, 25(6), 6262–6271. Retrieved from https://www.annalsofrscb.ro/index.php/journal/article/view/6677
Section
Articles