this is my quant

once you realize the markets are rigged by big, rich hedge funds, you almost have no choice but to JOIN MY COURSE

where you will:
-start trading on day 1!!
-make 11.5% in 13 days!!
-trade crack spread as retail alongside the best commods pods!!

hedge funds HATE this one course

This is quantymacro.

In 2024 alone, he managed to grow his net worth from 0 to 1,000,000¥.

One of the best paycheck collector we have seen in the history of humanity.

His secret to success?

Ridge Regression

Here’s his story: 🧵

yes bestie pls fit those regressions on prices bestie you can do it bestie look at the R2 bestie omg its so big bestie you like the big ones dont you bestie and no bestie your beta won’t converge to the ratio of the two drift terms of the time series bestie thats fake news bestie

As the Regent’s Park Chief of Ridge Regression, it is my utmost duty to make you believe in Ridge and lead all of you to glory. The Harkonnens non-believers will meet their fate soon. Ignore at your own peril.

I know I’m not supposed to say it here as a quantfluencianista, but so far I have very little interest in the computer science/software aspects in trading. Admittedly I haven’t put enough effort into learning it tho. Hopefully it won’t hurt me (too much)

the male urge to name drop Boyd and Vandenberghe Convex Optimisation and Multi-Period Optimisation on Twitter despite never even taken a single optimisation class >>>>>

starting a new tradition: Wisdom Of The Crowd

what have you learned recently about trading/quant?
what are you currently learning/planning to learn about?

giving away access to an article of their choice or 25% lifetime subscription discount to pseudo-random answers🥳

a good q. the simple answer is: linear regression is linear in *parameters*, it doesn’t need to be linear in variables. there are other complicated answers for sure.

a good reason why we all should do less of import sklearn and more of reading a regression textbook at a park :)

when you ask someone who uses cointegration hurst exponent ADF test for pairs trading why the pairs haven’t converged even after 4 years:

look at all the pathetic souls on a Sunday afternoon. mindlessly strolling around Regent’s Park like sheep taking pictures of flowers. they don’t have even the slightest idea that Ridge Regression dominates OLS for a range of values even when there is zero multicollinearity.

don’t take quant recs seriously (esp mine). esp the ones that speak in an authoritative tone “this is how you do X” etc. it’s crazy how the smartest ppl always give tons of disclaimers but the LARPers speak with huge conviction on top of ironically contradicting their past claims

when the macro PM asks the junior quant to put down the regression book and start reading about the Fed’s history:

I’m not even a hundredth as smart as gappy is but allow me to take pride in sharing the same problems that keep me awake at night

Some good stuff in here!

quantymacro elPythonQuantador i really liked your ridge regression thing you sent today 🙏

received my first refund request. I’m not upset rather I’m surprised ppl are subscribing even when their finances are tight (pls dont do that its too much pressure lol). anyways its a good feedback to make my writing more accessible, but keeping the same level of rigour 💪