International Research Journal of Engineering and Technology (IRJET) e-ISSN: 2395-0056 Volume: 06 Issue: 11 | Nov 2019 www.irjet.net p-ISSN: 2395-0072 © 2019, IRJET | Impact Factor value: 7.34 | ISO 9001:2008 Certified Journal | Page 2419 Future Prediction of World Countries Emotions Status to Understand Economic Status using Happiness Index and SVM Kernel B. Prashanthi 1 , Dr. R. Ponnusamy 2 1 PG Scholar in CSE Department, CVR College of Engineering, Telangana, Hyderabad, India. 2 Professor in CSE Department, CVR College of Engineering, Telangana, Hyderabad, India ---------------------------------------------------------------------***---------------------------------------------------------------------- Abstract - For many years there has been a focus on individual welfare and societal advancement. In addition to the economic system, diverse experiences and the habitats of people are crucial factors that contribute to the well-being and progress of the nation. The predictor of quality of life called the Better Life Index (BLI) visualizes and compares key elements—environment, jobs, health, civic engagement, governance, education, access to services, housing, community, and income—that contribute to well-being in different countries. This paper presents a supervised machine-learning analytical model that predicts the life satisfaction score of any specific country based on these given parameters. This work is a stacked generalization based on a novel approach that combines different machine- learning approaches to generate a meta-machine-learning model that further aids in maximizing prediction accuracy. The work utilized an Organization for Economic Cooperation and Development (OECD) regional statistics dataset with four years of data, from 2015 to 2019. Using the data of 187 countries from the UN Development Project, this work is able to identify which factor needed to be improved by a certain country to increase the happiness of their citizens. The novel model achieved a high root mean squared error (RMSE) value of 0.3 with 10-fold cross-validation on the balanced class data. Compared to base models, the ensemble model based on the stacked generalization framework was a significantly better predictor of the life satisfaction of a nation. It is clear from the results that the ensemble model presents more precise and consistent predictions in comparison to the base learners. Keywords- data mining; classification; feature selection; principal component analysis; support vector machine. 1. INTRODUCTION World happiness has been actively studied throughout the last ten years. The work in [8] argues that the government of a country is usually driven by the happiness of their citizens. Some factors that are controlled or authorized by the government positively correlate with the happiness level. That work shows that the key role to determine the citizen happiness is the improvement of public policy. Understanding happiness factors will help governments to make a better policy and legislation. However, the factors that influence happiness could be different due to different human perspectives. We cannot just simply say that The United State is happier than Indonesia country because The United State has higher GDP. Peggy in [1] stated that happiness is correlated with national economic and cultural living conditions. The work in [2] determined Happiness using three factors which are life expectancy, experienced well-being and Ecological Footprint. Other work in [9] shows a new measurement to improve the happiness of a country. Unlike the previous work, this work studies that happiness is not only related to physical but also mental needs. Therefore, they also consider mental health, which includes stress, depression, and emotional problems. As a result of the increase of human social complexity, the factors proposed by [2] and [9] may not be reliable anymore. Additional factors such as health and human development index should be examined carefully. However, analyzing the factor to determine happiness of a particular country is not a trivial problem. A single factor can have a bigger impact than another. NEF organization in [2] proposes an equation to calculate the happiness index. However, this equation does not consider the economical aspects. Therefore, this work proposes an approach by extending the factors and adopting machine learning techniques to learn about those factors. Due to numerous size of the features, it is unwise to rely on the prediction of a world happiness done by manual analysis. That process will result in high cost of analysis. Therefore, this work also proposes the use of machine learning to predict the world happiness. Machine learning is a widely known technique to learn about patterns in data. There are several machine learning techniques which can be used to perform a prediction task [3]. One of the remarkable techniques is the support vector machine. This work uses support vector machine because its outstanding ability to perform a classification task. 2. RELATED WORK This section briefly explains the related work in this project. Firstly, the national happiness analysis is described. It will discuss the importance of happiness analysis. Secondly, the used machine learning is introduced. Lastly, the proposed factor analysis is discussed. A. World Happiness Analysis The work in [4] mentioned that happiness could be a good indicator for how well a society is doing. This becomes important because Betham [5] said that the best society is the one where the citizens are happiest. Several researches have been conducted on positive aspects and the matters of