A comparison of discriminant analysis, support vector machine, random forest, and neural network supervised learning classification methods with the use of completely synthetic data.

Nützel, Maike (2021) A comparison of discriminant analysis, support vector machine, random forest, and neural network supervised learning classification methods with the use of completely synthetic data. Bachelor's Thesis, Applied Mathematics.

Preview	Text bAppM_2021_NutzelM.pdf Download (718kB) | Preview
	Text Toestemming.pdf Restricted to Registered users only Download (117kB)

Abstract

This Bachelor’s project generates challenging data and compares statistical classification models linear and quadratic discriminant analysis with the supervised learning methods support vector machine, random forest and neural networks. These methods are compared in classification accuracy, precision, recall, and F1 score. In the case of a small number of observations, QDA or RF is the classifier with the highest chance of success. Furthermore, in the case of linearly separable data, LDA will have a simular peformance as QDA, RF, SVM, and NN.

Item Type:	Thesis (Bachelor's Thesis)
Supervisor name:	Krijnen, W.P.
Degree programme:	Applied Mathematics
Thesis type:	Bachelor's Thesis
Language:	English
Date Deposited:	12 Aug 2021 07:38
Last Modified:	12 Aug 2021 07:38
URI:	https://fse.studenttheses.ub.rug.nl/id/eprint/25535

Actions (login required)

View Item