Studying the Stock Market via Unsupervised Machine Learning: How Well Do Sectors Align with Clusters?

Abstract

This paper utilizes k-means clustering to cluster stocks in the Istanbul Stock Exchange based on certain financial indicators, principal component analysis to graph the data points and clusters with as much variance as possible in two dimensions. In the end, a confusion matrix is created to calculate the accuracy of the cluster prediction given sectors.

Leave a Comment

Your email address will not be published. Required fields are marked *

This site uses Akismet to reduce spam. Learn how your comment data is processed.

Scroll to Top