Devni Prima Sari, Dina Agustina, Rara Sandhy Winanda, Media Rosha, Yusmet Rizal, Yuni Wardana
Machine Learning (ML) technology is a machine developed to be able to learn by itself without supervision from its users. In machine learning applications, a series of algorithms or statistical processes are trained to find specific patterns and features in a data set. In this study, we will analyze one type of supervised learning: regression. Regression is an analytical technique to identify the relationship or relationship between two or more variables. In this study, two kinds of regression were reviewed, namely simple linear regression and polynomial regression. Then a visual comparison was made between the simple linear regression model and the polynomial regression model. Furthermore, a comparison of the results between Statistical Models and Machine Learning is carried out. The visualization of the polynomial regression model with degree 2 looks better (better fit between the model and the data) than the simple regression model for the data in this study. Meanwhile, machine learning (supervised) aims to get a model that can make repeatable predictions. In comparison, statistical modeling is more about finding the relationship between variables. © 2024 Author(s).
Department of Mathematics, Universitas Negeri Padang, Padang, Indonesia; Data Analytics, Mathematical Modelling, and Forecasting Research Group, Universitas Negeri Padang, Padang, Indonesia
