GUNAWAN, PETER ROBERT (2025) COMPARISON OF RANDOM FOREST, SUPPORT VECTOR MACHINE, AND K-NEAREST NEIGHBORS TO PREDICT MENTAL HEALTH CONDITIONS. S1 thesis, UNIVERSITAS KATOLIK SOEGIJAPRANATA.

Preview	Text 21.K1.0020_PETER ROBERT GUNAWAN_COVER.pdf Download (471kB) | Preview
	Text 21.K1.0020_PETER ROBERT GUNAWAN_BAB I.pdf Restricted to Registered users only Download (411kB)
	Text 21.K1.0020_PETER ROBERT GUNAWAN_BAB II.pdf Restricted to Registered users only Download (485kB)
	Text 21.K1.0020_PETER ROBERT GUNAWAN_BAB III.pdf Restricted to Registered users only Download (660kB)
	Text 21.K1.0020_PETER ROBERT GUNAWAN_BAB IV.pdf Restricted to Registered users only Download (2MB)
	Text 21.K1.0020_PETER ROBERT GUNAWAN_BAB V.pdf Restricted to Registered users only Download (407kB)
Preview	Text 21.K1.0020_PETER ROBERT GUNAWAN_DAPUS.pdf Download (468kB) | Preview
	Text 21.K1.0020_PETER ROBERT GUNAWAN_LAMP.pdf Restricted to Registered users only Download (581kB)

Abstract

Mental health problems are common nowadays for a variety of reasons. These problems can be anticipated with the application of artificial intelligence technologies. According to several journals, the most accurate model for predicting mental health issues is Random Forest. Therefore, the other journals suggested that Random Forest, K-Nearest Neighbors, and Support Vector Machine produce comparable accuracy outcomes. The purpose of this study is to compare the models K-Nearest Neighbors, Random Forest, and Support Vector Machine in order to determine which one performs the best in predicting mental health problems. The dataset for this research are Mental Disorder Classification taken from psychologists patient records.

Actions (login required)

View Item