All files are related to past projects on statistical learning.

The files beginning with "Titanic__" are related to supervised learning, in which we used available data from Kaggle about the passengers on the Titanic to predict whether they survived the wreck. We strictly used R code to analyze the performance of each model. The code can be found in the PDF file titled "Titanic_Rcode." The written report is titled "Titanic - Machine Learning for Disaster." In this paper, we detail the models we used and the performance analysis of each model. The accuracy/predictability of the final model is 78.2%.

The files beginning with "Cluster__" are related to unsupervised learning, in which we used clustering models to group individuals from a study conducted by the Global School-Based Student Health Survey. The purpose of this project was to identify patterns in individuals who have experienced bullying in school. The R code can be found in the PDF file titled "Cluster_Rcode," and the detailed analysis and final clusters are presented in the PDF file titled "Cluster Analysis - Bullying in School."

Note: Both reports are not formatted in a professional academic manner, they are stored in this repository to showcase my experience with statistical analysis and machine learning.