Back to Community
Quantopian + Chat with Traders

Hello all,

I'm co-hosting a new podcast series with Chat with Traders. Chat with Traders is a podcast in which career traders come on and chat about their work and philosophy with the host, Aaron Fifield. We thought it would be a lot of fun to bring a series covering quantitative investing to the podcast, so we sat down with Aaron and produced a series of 6 episodes covering various parts of a quantitative workflow. The final episode will be a Q&A episode. Send your questions in here.

In the podcast we make references to lectures, tutorials, and examples from Quantopian and elsewhere. I'll post the links to the references here.

Episode 1 - You Don't Know How Wrong You Are
Guests: Delaney Granizo-Mackenzie

The worst case in finance is when you think you’re right, but you’re actually wrong. This can be especially dangerous when you’ve used some methodology or statistics to justify a decision, but are unaware of all the subtle biases that can cause false results. In this episode we’ll cover many of the ways that you can be wrong without knowing it in trading and finance.


Episode 2 - Seeking Alpha? Try Alpha Factors
Guests: Dr. Jessica Stauth and Delaney Granizo-Mackenzie

Factors are at the core of a modern quant equity workflow. We’ll introduce the notion of alpha and risk factors at a high level, and delve into some of the use cases which include: understanding how the market is moving, understanding how a portfolio is exposed to sources of risk, and turning ideas for price forecasting into encapsulated alpha factors.


Episode 3 - Seeking Alpha? Try More Alpha Factors
Guests: Jonathan Larkin and Delaney Granizo-Mackenzie

In practice, no one trading model will ever be that good on its own. Luckily statistics has come up with a lot of theory about how you can combine weaker models to create better overall predictions. We’ll discuss how to combine many different trading signals into overall models and some of the practical considerations in doing so.


Episode 4 - Portfolio Optimization: Risk Preferences go in, Trades Come Out
Guests: Scott Sanderson and Delaney Granizo-Mackenzie

When one has a price model that they think will work well for forecasting returns, the next step is to actually trade it. This isn’t that simple for a variety of reasons. For one thing, you need to define how much risk you’re okay with taking on in a portfolio, and then try to maximize your returns while staying within those boundaries. This is the foundation of modern portfolio theory, and we’ll discuss some real life issues with this.


Episode 5: Good and Bad Uses of Machine Learning in Finance
Guests: Max Margenot and Delaney Granizo-Mackenzie

Machine learning is a very hot topic these days, with a lot of people wondering how it could be used in finance. Used naively, machine learning poses a great deal of risk. We’ll discuss why that’s the case and also some good ways to use it carefully.


Episode 6: Q&A
Guest: Delaney Granizo-Mackenzie

Thanks for all the great questions, we answered as many as we could here.


The material on this website is provided for informational purposes only and does not constitute an offer to sell, a solicitation to buy, or a recommendation or endorsement for any security or strategy, nor does it constitute an offer to provide investment advisory services by Quantopian. In addition, the material offers no opinion with respect to the suitability of any security or specific investment. No information contained herein should be regarded as a suggestion to engage in or refrain from any investment-related course of action as none of Quantopian nor any of its affiliates is undertaking to provide investment advice, act as an adviser to any plan or entity subject to the Employee Retirement Income Security Act of 1974, as amended, individual retirement account or individual retirement annuity, or give advice in a fiduciary capacity with respect to the materials presented herein. If you are an individual retirement or other investor, contact your financial advisor or other fiduciary unrelated to Quantopian about whether any given investment idea, strategy, product or service described herein may be appropriate for your circumstances. All investments involve risk, including loss of principal. Quantopian makes no guarantees as to the accuracy or completeness of the views expressed in the website. The views are subject to change, and may have become unreliable for various reasons, including changes in market conditions or economic circumstances.

9 responses

Super, also check out Better System Trader podcast.

We just released the 3rd episode and are now at the halfway point. Remember to post your questions here or at, which is a special link which will be up only for the duration of this series.

Thanks Delaney - have been eagerly following the podcast.

Some questions below, particularly number 1.

  1. Alpha decay - are factor ranking strategies really still viable moving forward if everyone & their dog is now running them? (I note they have not had the greatest performance over the past year relative to backtests but thats a generalistic assumption.). Also if machine learning models are automatically picking out the top performing factors, how would anyone compete? I feel there would now be a lot of sharks taking advantage (front running) all the funds/users implementing these factor strategies which would eat your returns considerably. How would you monitor for alpha decay & when would you decide that a strategy is no longer viable? If you are rebalancing & returns are not as expected for how many months? 6-12? 2 Years?
  2. Competitive strategies for retail traders/investors - where & what are specific strategies that retail traders & investors can find a real, consistent edge? I.e. strategies on more volatile smaller cap stocks? The big benefit of factor strategies for example is that they are scalable & easy to use for large institutions, but many retail traders/investors (the target market for Quantopian) do not have access to the funds to efficiently deploy these kinds of strategies.
  3. When should you be satisfied with your strategy & system ? - I know Sharpe has been mentioned in the latest podcast. I have a returns profile of Sharpe - 1.6, Ann returns 17%, MaxDD% <10%. Is this good? Would this be considered high enough to attract institutional capital? Is there a certain threshold or benchmark to aim for to say right... this is a good strategy & you should deploy it etc...

Keep up the good work

Great questions, we'll try to get to them. Also, episode 4 is now out.

Hi, when are you posting lecture 6?

We'll be recording episode 6 sometime this week most likely. We'll then release it as soon as Aaron has time to get it edited. I would look out for it in 2-4 weeks. We had a lot of good questions get sent in, so I'm looking forward to the recording.

The entire series is now available, including the Q&A episode. Thanks to everyone who listened, and extra thanks to everybody who sent in questions.

I really liked this series; it allowed me to better understand many things about your platform and more generally on algorithmic trading. Good job. Thank you.

Thank you, Giuseppe. We're very happy it was helpful.