Presentation Title

Exploring survival on the RMS Titanic with Machine Learning

Faculty Mentor

Dr. Flores

Start Date

18-11-2017 2:15 PM

End Date

18-11-2017 3:15 PM

Location

BSC-Ursa Minor 6

Session

Poster 3

Type of Presentation

Poster

Subject Area

physical_mathematical_sciences

Abstract

Recently, there has been a surge in available data describing phenomenon from genomics to astronomy and high-energy physics. Additionally, access to data has resulted in the development of new information-based industries according to Frontiers in Massive Data Analysis, National Research Council of the National Academies. Accordingly, statistical rigor is imperative to justifying any gains in knowledge obtained from a given data set.

In our project, we will investigate and develop supervised machine learning algorithms that predict the classification of survival of passengers aboard the Titanic. We analyze certain attributes such as class, gender, age, family, and fare that are given in the data set. The main challenge is determining the most significant attributes that clearly distinguish the survivors and the nonsurvivors. Along with attempting to manually create our own attributes using feature engineering, we will use Principle Component Analysis together with a k-nearest neighbors scheme to accurately classify passenger survival on the Titanic.

Keywords: Principal Component Analysis, k-nearest neighbors, RMS Titanic, Machine Learning

This document is currently not available here.

Share

COinS
 
Nov 18th, 2:15 PM Nov 18th, 3:15 PM

Exploring survival on the RMS Titanic with Machine Learning

BSC-Ursa Minor 6

Recently, there has been a surge in available data describing phenomenon from genomics to astronomy and high-energy physics. Additionally, access to data has resulted in the development of new information-based industries according to Frontiers in Massive Data Analysis, National Research Council of the National Academies. Accordingly, statistical rigor is imperative to justifying any gains in knowledge obtained from a given data set.

In our project, we will investigate and develop supervised machine learning algorithms that predict the classification of survival of passengers aboard the Titanic. We analyze certain attributes such as class, gender, age, family, and fare that are given in the data set. The main challenge is determining the most significant attributes that clearly distinguish the survivors and the nonsurvivors. Along with attempting to manually create our own attributes using feature engineering, we will use Principle Component Analysis together with a k-nearest neighbors scheme to accurately classify passenger survival on the Titanic.

Keywords: Principal Component Analysis, k-nearest neighbors, RMS Titanic, Machine Learning