A study of machine learning algorithms for predicting financial well-being: Logistic regression vs. MLP
Senior Data Engineer, Independent Researcher, India.
Research Article
World Journal of Advanced Engineering Technology and Sciences, 2021, 03(01), 084–096.
Article DOI: 10.30574/wjaets.2021.3.1.0058
Publication history:
Received on 08 July 2021; revised on 22 August 2021; accepted on 25 August 2021
Abstract:
This study investigates the applicability of machine learning techniques on diverse datasets. We explore the effectiveness of two algorithms, Logistic Regression and Multi-Layered Perceptron (MLP), on predicting financial well-being. Specifically, we employ a salary prediction dataset to evaluate the model’s capacity to classify individuals earning above a specific income threshold (e.g., $50,000 per year). Through comparative analysis, this research aims to elucidate the strengths and limitations of each algorithm when applied to these contrasting data types, offering insights into their suitability for various prediction tasks. Furthermore, we present a framework for data analysis, outlining essential steps for data cleaning, exploration, and preparation, which can be applied to enhance the effectiveness of machine learning models across diverse datasets.
Keywords:
Machine Learning; Heterogeneous Data; Comparative Analysis; Prediction Modeling; Data Analysis Techniques; Salary Prediction; Logistic Regression; Multi-Layered Perceptron; Data Preprocessing
Full text article in PDF:
Copyright information:
Copyright © 2021 Author(s) retain the copyright of this article. This article is published under the terms of the Creative Commons Attribution Liscense 4.0