Authors

1. Ms. Ritu Khandelwal

Affiliation

• Assistant Professor, International School of Informatics & Management, Jaipur

Abstract

Extreme wealth and income inequality are a big concern, especially in the United States. The potential to end poverty is a strong justification for lowering the world's rising economic disparity. The idea of universal economic disparity promotes a country's economic stability and guarantees sustainable development. The governments of many nations have been working hard to address this issue and offer an ideal answer. This paper focus on the issue of income inequality is addressed using machine learning. Machine learning is a technique that uses artificial intelligence, and other learning techniques to find the pattern of data and related knowledge from several large datasets. Orange is both a free and open-source application for data analysis and data visualization. We can now forecast future earnings with the quick advancements in storage capacity and computer performance. This study's issue will be the classification of adult datasets utilizing the orange tool. the various classification techniques applied to an adult sensory dataset utilizing the orange tool.
For this, the UCI Adult Dataset has been used. To tie up current learners and add some pre-processing to create new versions, this paper addresses the highlights. In this study, different categorization techniques are contrasted with an analysis of the outcome using a confusion matrix. It comprises a few performance indicators, such as recall, an area under the curve (AUC), an F1 score, and precision. Using main features, classification is applied to determine a person's yearly income that falls higher than $50,000 or less than $50,000. The main purpose of this study is to give comprehensive analysis of relevant methods on dataset. The decision tree model, Naive Bayes, k-Nearest Neighbour(KNN), and support vector machine(SVM) were used for the comparative study of this paper. One of those, the decision tree recorded the maximum accuracy of 98.4%, surpassing the standard accuracy of earlier works. Attained levels of precision and recall are 98.6% and 99.3%, respectively.

Keywords

Machine learning, Decision tree, Naive Bayes, KNN, SVM, Data mining

References

1. Khandelwal, R., & Virwani, H. (2019). Comparative Analysis for Prediction of Success of Bollywood Movie. SSRN Electronic Journal, 104–111. https://doi.org/10.2139/ssrn.3350907
2. Khandelwal, R., Goyal, H., & Shekhawat, R. S. (2020). Comparative Analysis of Machine Learning Techniques Using Predictive Modeling. Recent Advances in Computer Science and Communications, 15(3), 1136–1147. https://doi.org/10.2174/2666255813999200904164539
3. Income Classification using Adult Census Data ( CSE 258 Assignment 2 ) | Semantic Scholar. (n.d.). Retrieved March 26, 2023, from https://www.semanticscholar.org/paper/Income-Classification-using-Adult-Census-Data-(-CSE-Chockalingam-Shah/3dd5e9f335511efbb81 d65f1d6d 4995019f8b5fd
4. Deepajothi, S., & Selvarajan, S. (2012). A Comparative Study of Classification Techniques On Adult Data Set 1. International Journal of Engineering Research & Technology (IJERT), 1(8), 1–8.
5. Chakrabarty, N., & Biswas, S. (2018, October). A statistical approach to adult census income level prediction. In 2018 International Conference on Advances in Computing, Communication Control and Networking (ICACCCN) (pp. 207-212). IEEE.