Hopefully a simple one for someone.
I've a pair of stocks A and B. The beta adjusted spreads tell me I need to be selling A and buying B, my beta for B is 1.5, so in order to get a beta neutral pair I need for every Sell 1 of A I need to buy 1.5 B.
Is there a suitable way to scale this with a MinMax normaliser that preserves the signs of each trade. For example I want to have an upper limit of +/-50,000 per dollars stock and when I use sklearn's MinMaxScaler I get some instances where I'm point in the same direction on the same day...
Any pointers would be great as I've struggled to find any examples of how this could effectively work.