Article Preview
Top1. Introduction
Gross Domestic Product is the important, vital measure for assessing the wealth and growth of the country (Ramesh, 2019; Javaid et. al., 2021). It has become an important part of the economic data of a country and the amount of effort rendered into measuring it is tremendous. Work done in calculating the exact Gross Domestic Product (GDP) number is enormous. Though it can’t be completely automated, tools like this help in validating the predicted number. This work seeks to overcome the difficulties in measuring the Gross Domestic Product of a well-developed economy using macro-economic data like Unemployment rate, Bond rate, Inflation etc. Previous work on this field of research did not use any macro-economic data for predicting the GDP (Shukla et. al., 2018), they rather used simple data like CO2 emission were used to predict the GDP and the accuracy of those predicted values will not be great since they are very loosely related to GDP change, but our datasets include factors that has a direct impact on the country’s economic growth.
One of the fundamental aspect in the growth and development of any country is industrialization, which includes heavy machinery, equipment and other socioeconomic factors. However, these development comes with the by-product of carbon emission, in which CO2 is the major constituent (Sandeep et. al., 2019). As aptly concluded in, irrespective of the developed or developing nation, the economic growth of a country is in direct relationship with the CO2 emission of that country. This emission data could easily be utilized to estimate the gross domestic product of that country. Here, we can understand that the data distribution of developed nation and developing nation is different and thus machine learning techniques are widely used (Sandeep et. al., 2019). Further, simple linear regression have been used to understand the relationship between the two variables of economic growth and the primary forest cover (Pooja et. al., 2018).
Further, the spending on Research and Development is important to have a qualitative and innovative research. The present study tries to assess research productivity in the field of Science and Technology of the two emerging powers viz., India and China. The research productivity shall be related with Gross Domestic Product and proportion of same inverted in Research and Development (Tazeem et. al., 2018). In this purview many robust estimation techniques of co-integration have been used in the prediction (Govindaraju et. al., 2013). Even though a number of new mathematical functions have been proposed for modelling of the GDP growth rate prediction based on the CO2 emissions, in this investigation the main aim is to overcome high nonlinearity by applying the soft computing method. Soft computing can be used as alternative to analytical approach as soft computing offers advantages such as no required knowledge of internal system parameters, compact solution for multi-variable problems (Marjanović et. al., 2016).