#ProductivQuarantine
Been following @dmuthuk Sir for quite some time and I must say that I have learned a lot.
Everyone knows about his love for the ITC stock.
1/n
Been following @dmuthuk Sir for quite some time and I must say that I have learned a lot.
Everyone knows about his love for the ITC stock.
1/n
I became curious just like everyone and thought as well to apply some portfolio theory and data analysis concepts to ask data itself about what it wants to say.
2/n
2/n
It turns out that even the data tends to agree with him very much. Cheers, Sir. 
I primarily wrote code to find the minimum variance portfolio for now. Will be working on more models just to see what else I can derive out from it.
3/n

I primarily wrote code to find the minimum variance portfolio for now. Will be working on more models just to see what else I can derive out from it.
3/n
Results can be seen in this picture below.
The name of the company followed by the weight of it in the portfolio for min variance/risk.
23.9% of your portfolio should be in ITC for that.
4/n
The name of the company followed by the weight of it in the portfolio for min variance/risk.
23.9% of your portfolio should be in ITC for that.
4/n
@dmuthuk Sir shared his latest portfolio on 20th March and I did the entire modeling by focusing around that only.
https://twitter.com/dmuthuk/status/1240864380327096321?s=20
5/n
https://twitter.com/dmuthuk/status/1240864380327096321?s=20
5/n
The range of data used spans exactly 2 years. It starts from 4th April 2018 and ends on 4th April 2020. Will increase the amount of data as I work on it more and see if there are considerable changes in the results or not.
6/n
6/n
Another interesting thing that needs to be worked upon is the issue of negative weights. I guess optimization techniques need to be applied here to settle that issue.
7/n
7/n
Entire code can be found on my GitHub using the following link.
https://github.com/ConstantTime/Portfolio-Theory-on-Real-Life-Data
8/n
https://github.com/ConstantTime/Portfolio-Theory-on-Real-Life-Data
8/n
Looking forward to your comments and suggestions below.
9/n
9/n