Cholesky Decomposition and Its Applications in Python

In this video, we go over Cholesky decomposition of symmetric matrices. In terms of solving systems of linear equations, it is very similar to LU decomposition. I will show how to do the decomposition in and how to solve a system of linear equations using Numpy’s and Scipy’s built-in functions. Then we will explore how we can use this to generate correlated random variables. This has applications in finance where one might wish to do a Monte Carlo simulation on two or more correlated stocks.
Github: github.com/kpm...
Tip Jar: patpal.me/kpmo...

[@henrychoi3327]

Hi I am a ph.d. student in South Korea. I learned a lot from this video. Thanks

[@sebymsc6518]

Hello sir, I've just found your youtube channel, and I like the content so far. I guess I could say I found someone who has a vast knowledge when it comes to option trading / institutional trading (you :D). I am a complete beginner, I've heard about option trading for the first time from an ebook recently, in which were covered some of the institutional techniques, delta hedging, gamma scalping, vega hedging & scalping. The book was pretty well stuctured, the author was also talking about the different fields of science that deal with the financial markets, institutional techniques and economic models such as the black sholes model and garch(1.1). I needed this introduction in order to adress some of the questions that I have regarding this profession: The most important one, what degree/qualification do I need in order to learn all of this? Are there specific degrees or courses that deals mainly with financial trading? If I dont bother you with this question, how did you learn everything you know when it comes to trading? Where did u find this information? Perhaps its a silly question, but because of the complexity of this subject, and the different fields of science that deal with it, as a complete beginner, it can be extremly confusing, and i have no idea which path to take in order to learn all of this in a proffesional manner. I have some many questions when it comes to option trading, about volatility, black sholes model, option greeks, broker's platform, and all the calculations that need to be made/taken into account that i would write this comment for hours, so there is no point to ask them now, so instead i adress this question: What is your advice for a complete beginner, that just descovered this complex subject? Where should I start? What path should I take in order to learn to apply the institutional techniques/ to become an option trader? There are so many things that one needs to know, and frankly Im at the point where I dont know what I dont know, and Im seeking guidance in this ragard. Im glad I ve found your channel, you deserve far more subscribers, I ve already learned a lot form you, about different pieces of the puzzle, which dont fit yet due to the complexity of the subject. Congtatulations for the content! I hope you'll answer me :D

[@kpmooney]

Rather than writing out a long reply, I'll answer in a short vidoe. I expect to have it out my the middle of this week.

[@bhargav7476]

@@kpmooney I have a very similar question, a video reply would be really helpful. Thanks for the content ❤️

[@bhargav7476]

@@kpmooney Points you can cover in video would be: 1. Your education and career in Quantitative Finance 2. What would you do differently 3. Advice for graduates and undergraduates to work in QF 4. Careers in QF 5. Master's/Certifications to pursue 6. Best paid/free resources for self-learning 7. Future of QF (Buzzwords vs Reality)

[@Septumsempra8818]

Are there any Kalman filter vids in the making?

[@kpmooney]

I thought about it but haven't planned anything out yet. It'll be a while before I can get to it.

[@Aledupa12]

Why using the Cholesky decomposition while we can use directly the "np.linalg.solve" comand?

[@kpmooney]

Speed. For solving many equations where the matrix doesn't change, but only the b vector in Ax = b changes, this would be much faster.

[@Aledupa12]

@@kpmooney Ah ok. Thx for explanation.