Invest Like The Best
Episode 105 Machine Learning in Investing
Invest Like The Best

Episode 105: Machine Learning in Investing

Invest Like The Best

Episode 105

Machine Learning in Investing

Jeremiah Lowin is the founder of Prefect, a data infrastructure company. We cover machine learning in the world of investing, the importance of error minimization in data models, and detail into how tests are set up and deployed in machine learning.

[00:02:06] – (First Question) – What do people need to think about when considering using machine learning tools

[00:03:19] – Types of problems that AI is perfect for

[00:06:09] – Walking through an actual test and understanding the terminology

[00:11:52] – Data in training: training set, test set, validation set

[00:13:55] – The difference between machine learning and classical academic finance modelling

[00:16:09] – What will the future of investing look like using these technologies

[00:19:53] – The concept of stationarity

[00:21:31] – Why you shouldn’t take for granted label formation in tests

[00:24:12] – Ability for a model to shrug

[00:26:13] – Hyper parameter tuning

[00:28:16] – Categories of types of models

[00:30:49] – Idea of a nearest neighbor or K-Means Algorithm

[00:34:48] – Trees as the ultimate utility player in this landscape

[00:38:00] – Features and data sets as the driver of edge in Machine Learning

[00:40:12] – Key considerations when working through time series

[00:42:05] – Pitfalls he has seen when folks try to build predictive market investing models

[00:44:36] – Getting started

[00:46:29] – Looking back at his career, what are some of the frontier vs settled applications of machine learning he has implemented

[00:49:49] – Does interpretability matter in all of this

[00:52:31] – How gradient decent fits into this whole picture

Machine Learning in Investing

Introduction

Patrick
My guest this week is one of my best and oldest friends, Jeremiah Lowin. Jeremiah has had a fascinating career starting with advanced work in statistics before moving into risk management in the hedge fund world. Through his career, he has studied data, risk, stats, and machine learning, the last of which is the topic of our conversation today. He has now left the world of finance to found a company called Prefect, which is a framework for building data infrastructure. Prefect was inspired by observing frictions between data scientists and data engineers and solves these problems with a functional API for defining and extricating data workflows. These problems, while wonky, are ones I can relate to working in the quantitative investing world, and others that suffer from them out there will be nodding their heads right now.

In full and fair disclosure, both me and my family are investors in Jeremiah's business. You won't have to worry about that potential conflict of interest in today's conversation, though, because our focus is on the deployment of machine learning technologies in the realm of investing. What I love about talking to Jeremiah is that he is both an optimist and a skeptic. He loves working with new statistical learning technologies, but often thinks they are overhyped or entirely unsuited to the tasks they are being used for. We get into some deep detail on how tests are set up in this world, the importance of data, and how the minimization of error is a guiding light in machine learning and perhaps all of human learning, too. Let's dive in.

Access the full transcript
Sign in or register to view episode transcripts.

Contact

Get in touch at help@joincollossus.com