Topology for Time Series


Topology studies the global properties of a space, such as the data collected from a system changing over time, and can classify objects by those properties. This makes it very useful for comparing a group of systems that may or may not have the same properties. By learning about how topology can be used to study time series, you’ll be equipped to study data that changes over time at a global system level.

This talk will introduce participants to topological algorithms to compare time series data. We’ll overview time series data, examine South African and Egyptian stock market trends, learn about topology and an algorithm called persistent homology, and implement our analysis in R. Participants will come away with an understanding of the persistent homology algorithm, an understanding of the caveats of analyzing/comparing time series data, and an understanding of how to implement the algorithm in R.

Colleen Farrelly

Colleen M. Farrelly

Author of The Shape of Data

Colleen M. Farrelly is a lead machine learning scientist who has brought products to market in education, biotech, healthcare, quantum technologies, and consumer packaged goods. She is the author of The Shape of Data (No Starch Press), and she is published in over 10 scientific disciplines. She spends her free time on machine learning for social good projects in Rwanda and Cameroon.

We are looking for passionate people willing to cultivate and inspire the next generation of leaders in tech, business, and data science. If you are one of them get in touch with us!

Become a Presenter