Title: Data analytics on census data to predict the income and economic hierarchy

Authors: K.G. Srinivasa; R. Sharath; S. Krishna Chaitanya; K.N. Nirupam; B.J. Sowmya

Addresses: Department of Information Technology, Ch. Brahm Prakash Government Engineering College, Jaffarpur, New Delhi, 110073, India ' Department of Computer Science and Engineering, M.S. Ramaiah Institute of Technology, Bangalore, 560054, India ' Department of Computer Science and Engineering, M.S. Ramaiah Institute of Technology, Bangalore, 560054, India ' Department of Computer Science and Engineering, M.S. Ramaiah Institute of Technology, Bangalore, 560054, India ' Department of Computer Science and Engineering, M.S. Ramaiah Institute of Technology, Bangalore, 560054, India

Abstract: The US Census Bureau conducts the American Community Survey generating a massive dataset with millions of data points. The rich dataset contains detailed information of approximately 3.5 million households about who they are and how they live including ancestry, education, work, transportation, internet use and residency. This enormous data encourages the need to know more about the population and to derive insight. The ever demanding requirement in exposing the subtlety in case of economic issues is the motivation behind to construe meaningful conclusions in income domain. Hence the focus is to concentrate on bringing out unique insights into the financial status of the people living in the country. These conclusions delineated might aid in delivering wiser decisions in regard to economic growth of the country. Using relevant attributes, demographic graphs are plotted, aiding the conclusions drawn. Also classifications into various economic classes are done using well known classifiers.

Keywords: index terms-demographic graphs; Benford's law; income; K-means clustering; Naive Bayes classifier.

DOI: 10.1504/IJDATS.2018.094133

International Journal of Data Analysis Techniques and Strategies, 2018 Vol.10 No.3, pp.223 - 240

Available online: 17 Aug 2018 *

Full-text access for editors Access for subscribers Purchase this article Comment on this article