Mark Aron Szulyovszky

Building a unique product in the quantitative finance space (in stealth mode).

[Captain Crypto Hindsight @CapCHindsight]

It looks like you were trying to send a market order in PEPE perps on OKX at 12:35 UTC. Would you like help with that?

(Too late. Takers paid 34x their usual slippage, 4.0 bps on average.)

Next time, consider a limit order. Or a different minute.

[Mark Aron Szulyovszky @almostintuitive]

So the future is... that we'll give up understanding and just go with the flow, right?
At least you have Lean when you're a mathematician.
All we got is: "multiple-testing-adjusted" t-stat...

[Tibo @tibo_maker]

AI was supposed to make us work less

I've never been this tired in my life

most days I have up to 10 agents running at the same time. one fixing a bug, one writing pages, one refactoring something I already forgot I asked for, 3 other I have no idea what they are doing but i suppose i ask it?

and I jump from conversation to conversation all day

compared to 5 years ago, I probably context switch 100x more

by the end of the day my brain is fried. completely toasted. nothing left, not even for the people I love

I call it the fried brain effect

thought it was just me but almost every founder I talk to lately says the exact same thing

we got superpowers, and somehow the pressure only went up. if you can ship 10x more, you feel like you have to ship 10x more. every single day

I don't have a solution

honestly I have no idea where this goes from here

anyone else feeling this?

[Aperiodic.io @aperiodic_io]

A year ago this week, at 20:50 UTC on Friday 10 October 2025, Trump posted that the US would impose an extra 100% tariff on Chinese imports from 1 November.

Wall Street had already closed and crypto was the only market still open.

[Mark Aron Szulyovszky @almostintuitive]

We built the infrastructure @aperiodic_io for ourselves, because we couldn't find a vendor that served PIT microstructure / liquidity / flow metrics we needed, with full universe coverage.

It's a unique, serious offering that just got a lot stronger: with raw data itself!

[Aperiodic.io @aperiodic_io]

I've kept a comparison of crypto data vendors since July. Here it is as a tier list: raw market data vs derived metrics, ranked for systematic research.

Disclosure: I run Aperiodic (we sell both), so we're on it but unranked.

Full 37-criteria comparison in the thread.

[Ruizhe Jia @RuizheJia]

Binance is arguably the world's largest crypto exchange.

Feb 2026: Polymarket lists a small 5-minute Bitcoin contract. Since then, Binance order flow spikes in the final seconds before settlement; prices revert soon after.

New paper with David Dai and Shihao Yu ( @ShihaoY ): Settlement Manipulation in Prediction Markets (https://t.co/L4fFsnXLhW)🧵

The finding, up front:

Traders push Bitcoin's price in the final seconds to decide the contract. That push makes the price less informative, yet Bitcoin's market more liquid. Market makers are largely insulated; ordinary traders lose $7.6M in two months.

[Daniel Szemerey @szemyd]

It can be lonely being a quant; ie especially if you are behind large walls that forbid sharing info (for good reasons though).
I think the biggest added benefit of running a service like aperiodic or aperiodic factors is that we get to talk to a lot of teams on a daily basis

[Daniel Szemerey @szemyd]

Buying makes more buying likely: not for seconds, but for days. It seems the tape doesn't actually forget the morning, it simply fades it out slowly.

[Mark Aron Szulyovszky @almostintuitive]

Putting together the content for Aperiodic has been a nice excuse to read and re-read some of the most interesting market microstructure papers. I also wanted to write about the (great) variance in the quality of these papers, but I'll save that for another day!

[Mark Aron Szulyovszky @almostintuitive]

I thought I had a good intuition what "spread" is, but digging through the literature turned out to be surprisingly enlightening.

[Mark Aron Szulyovszky @almostintuitive]

We also serve something we call Spread/depth ratio: low values means genuinely cheap liquidity. High ratio means a narrow quote is only the surface, and it will not survive contact with real flow.

[Mark Aron Szulyovszky @almostintuitive]

why did I choose handles and company names I could never properly spell or type without making a mistake?

it's only muscle memory that saves me, I could not deliberately type out any of them.

probably dyslexia, right?

[Mark Aron Szulyovszky @almostintuitive]

Try basis, order book imbalance, flow metrics. We cut headaches by 90%, and found reliable alpha that we can build upon, without worrying about whether any of it is actually traceable.

[Mark Aron Szulyovszky @almostintuitive]

Why did we end up specializing in market microstructure / liquidity / flow metrics?

When we originally started exploring crypto, we tried every data source imaginable: on-chain, social sentiment, etc. We got pretty deep, and had working pipelines to ingest data from...

[Mark Aron Szulyovszky @almostintuitive]

In the end, the operational overhead could never justify the alpha we could find: not saying on-chain metrics are not fun, but derivatives in crypto are 80% of the volume.