MKTSTK

I’m Shutting Down MKTSTK

He’s gone, and we couldn’t do nothing about it.

What do you mean?

He’s gone. He’s gone. And that’s it.

Well, its been a whole lot of fun, but MKTSTK is getting shot in the head in a Bensonville basement.

No party. No waiting to die. Its gone. Real greaseball shit.

I’m really happy that I started this blog. I have to give special thanks to everyone who gave me feedback and made running this thing…

Tether is Breaking its “Peg” to the Dollar

The market is losing faith in the third most actively traded cryptocurrency in the world. Known as Tether (USDT), this token was designed to have a 1-1 peg with the US Dollar. Supposedly, each Tether is backed by a US Dollar held in trust. There has always been skepticism about this claim, and the market has been abuzz with the news that the company behind Tether recently broke off its…

FOMC Minutes: A Day Like No Other?

Yesterday seemed like any other day until FOMC minutes. Then the markets began to seize. Given the limited trading intensity we’ve witnessed so far in 2017, one could be forgiven for thinking the world was about to end.

But at the end of the day, how different was yesterday from any other day? Was it really that crazy? To investigate, I started by grabbing all the 1-minute data for the SPY from…

What are the Best & Worst Times of Day to Buy the Stock Market?

I awoke this morning to find the S&P 500 futures down about 11 points. My immediate thought was “oh goodie, there’s some candy for the old early morning BTFD’ers to enjoy” [translation, “I’ll be the market goes up from here”]. This instinct was based on many such mornings of observing and interacting with the stock market. But how good is this intuition, and more importantly are there times of…

A Dead-Simple Hedge Ratio API

As the title suggests, I created a dead simple hedge ratio API called Risk Hedger. Also its free and the Python client is open source. So if you’re in to that kind of thing feel free to read on:

What is a Hedge Ratio?

Traders and investors buy/sell hedges when they want to reduce the risk of their portfolio. Additionally, certain strategies such as Pairs Tradingrely on accurate estimation of…

Searching for Answers… with Volatility

Pretty random alternative datapoint for you to ponder. But here goes…

My first post ever on this blog was a tirade about how I think that SVXY and XIV were / are designed to fail. Despite the ribbings I have received from trading compatriots for this viewpoint I still believe them to be crazy bottle rocket rides that will end poorly. But thats not the point.

I was noticing that today its my most…

Simulating Correlated Random Walks for the S&P 500

Waaaaaay back in the day, I showed how to simulate correlated random walks using copulas….

I was really thinking about the application to pairs trading back then… which was fine, because one of the limitations was that the method could only simulate two random variables at a time.

If you wanted to do some large universe like the S&P 500 you had to do everything pairwise, and then you weren’t…

A Regime Switching Model: Momentum vs Mean Reversion

Today I wanted to share a link to my first post on Quantopian, in which I describe a strategy that uses social data to switch between mean reversion and momentum based trading regimes.

This feat is accomplished using a new social factor I’ve created. I believe this strategy presents a novel approach to regime switching. This strat represents a departure from my HFT roots, as the rebalance period…

Unbalanced Classes in Machine Learning and the Stock Market

Many assets exhibit bull or bear trends which persist for long periods of time. This presents an interesting problem  for anyone trying to predict the future return of an asset: a lack of diversity in your training set. This problem is known as unbalanced classes in the machine learning field.

The basic issue is that many classification methods work best when your training data is roughly…

A Curious Correlation between Social Media and Volatility

Those who have followed this blog for some time know that Social Data is something that interests me greatly. As this blog continues to attract viewers, I can only assume research on social data and the financial markets is of interest to you all as well!

So I wanted to pass on a link to a blog post I contributed to showing a rather curious correlation between volatility and social media message…

How to Value Nadex Bull Spreads?

Exotic options have always been a hobby of mine. One of the curious things about Dodd-Frank was it started to push swap trading onto exchanges. As such, a cottage industry of exchange traded exotics (in the US they’re technically swaps) has popped up over the last few years. The biggest of these markets by volume seems to be Nadex so I recently became a member and started playing around with some…

The Conundrum of Trade Strategy Sizing

When you have a strategy that is doing well, you want to size it up! But sizing up isn’t always a straightforward proposition, as we must take liquidity into account. MKTSTK investigates this conundrum in this week’s podcast.

[soundcloud url="https://api.soundcloud.com/tracks/254457464" params="visual=true&auto_play=false&hide_related=false&show_comments=true&show_user=true&show_reposts=false"…

Limits of Machine Learning Part 2

Last week’s podcast was pretty negative on the value of machine learning in trading, so this week I wanted to provide my own counterpoint and explore life within the limits I identified earlier.

Specifically, I wanted to begin mapping the things machine learning algorithms might really be great at doing in the world of trading and finance. 

This podcast is presented in a slightly different manner…

Some Limits of Machine Learning in Trading

Aka my first podcast.

Sorry I’ve been AWOL for so long; I’ve been deep in the lab working on my creation.

As my work-life balance has careened towards work, I have found it difficult to sit down a write like I used to, so I am giving this whole podcast thing a try…

So without further ado, I present a thought which occurred to me whist gazing at the bay, why is machine learning so hard in trading?

Classical Conditioning in the Markets

Long ago I had a junior trader, let’s call him M, who worked the overnight shift for me trading interest rates. M was an awesome person to have around (fyi regarding the past tense, he’s not dead, just we’ve both moved on to bigger things at different places, god speed buddy!). M worked insanely long hours and produced quality work; if you set a bar for him to jump over, he figured out a way to…

There are many professions that can ultimately lead to financial freedom in the future. Very few, however, allow for freedom along the journeyto this goal as well. Many times, professionals find themselves beholden to a boss, a client, or someone else that controls the power to sign paychecks and affect general well-being. Even though bank accounts may grow, professionals may see their real…

Signal to Noise: Humans as Bayesian Filters

Bayesian Filters are everywhere in Quant Trading. the most ubiquitous is the Kalman Filter. Trading without a filter is like bringing a knife (or spoon?) to a gun fight.

Humans behave a lot like collections of filters. We constantly make expectations, then revise our expectations and take actions as a result of new information. We can think of our expectations as an collection of internal beliefs.