About

Data mining is a very common concept nowadays. Nonetheless, there is still a misunderstanding what exactly is data mining. Perhaps, this is due to the fact that data mining is a wide concept that covers several fields of knowledge, from mathematics and statistics to computer science.

My Master’s Degree course of data mining was very naive with focus on classification methods, although the syllabus was more broad. The main references I have used to study were:

• The Elements of Statistical Learning: Data Mining, Inference, and Prediction

• An Introduction to Statistical Learning

• Machine Learning A Probabilistic Perspective

Course assignments

The lessons were taught by professor Ronaldo Dias. The assessment method adopted were practical data analysis of real world data sets with focus on comparison between the classification methods. More precisely, I have done the following reports and presentation:

• Binary Classifications: A study to classify patients with heart disease

• Decision Trees: Bagging, Random Forest and Boosting

• An Empirical Comparison between Support Vector Machines and Logistic Regression

All analysis were conducted in R software and the codes are available in my Github repository.