Advice on dissertation: ML portfolio management

Hi all, I made a post about 4 months ago, before I started summer break properly, asking for introductory material on trading. I bought a book called TA explained by pring. I read about 70 pages in until lockdown restrictions eased… so I didn't read much. But I've got deadlines coming up and I need to make a decision on what topic im doing it on.

So what i'm asking is: I'm aware there are existing papers on this topic but will this be viable in say a 5 month time frame and with little background? And, can you point me in the right direction?

I'm 3rd yr comp sci student, with little financial experience and a little more ml experience. We're currently doing clustering and regression training in our ML module. However I've done a little bit of reading and would be aiming to get a model that is continuous(Or runs on a daily basis) and could be given different time frames. additionally I want to make it multi objective so maximizing profit and minimizing risk. Am I thinking about this is the right way?

My Ml skills are weak but that should come with time and as we get through the course, but my financial skills will not. I do plan on finishing the book I bought but does anyone have a better book or any resources that relate to risk or existing ways of optimizing risk/profit. Also when I read papers they use a lot of mathematical notation, is there any where I can brush up on that.

my original idea was to do a trading bot, but my lecturer suggested a portfolio manager since it has been done before but is also challenging. I hope somebody can offer advice, thanks either way.

Submitted October 26, 2020 at 10:23AM by yode8
via https://ift.tt/2Tr4ou3

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s