A study of machine learning algorithms for predicting financial well-being: Logistic regression vs. MLP

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.