Machine learning methods and some aplications

This study titled "Machine Learning Methods and Some Applications," consists of seven sections. In the first section, the purpose of the thesis and the literature review on machine learning are presented. In the second section, some basic statistical information required to create algorithms in Machine Learning Methods, the concept of input data for the algorithms, data preprocessing that must be carried out in order to use the algorithms, and the concepts of model creation and model evaluation are included. In the third section, the mathematical structure of some algorithms in Supervised and Unsupervised Machine Learning methods are examined. In the fourth section, some machine learning algorithms are applied to two different data sets using Python programming language and models are created. Afterwards, the models are compared by performance using model evaluation. If there are outliers in the data set that cause misleading results, the least squares regression line is incompatible with the data. One of the solutions of this problem is Robust Regression, which seeks to find estimators that are not affected much by outliers, and Robust Regression Analysis is discussed in the fifth section. The sixth section is the main part of the study and the algorithm is developed in this section. In the last part, the models created for the datasets in the fourth part are compared according to their performance. In addition, it has been shown that the lines obtained as a result of the application of the developed algorithm to different data sets are more compatible with the data than the least square lines.