I am working on stock market analysis and prediction using machine learning methods, especially with reinforcement learning. I am trying to predict short, long and flat. (buy, hold, sell) . (any suggestion or material is appreciated), currently, I am giving historical data into my agent and agent predict buy, sell or hold signal. my question is how to measure stock quantity. e.g. if my model gives a buy signal, how to measure how much stock I should buy.
I think that should be a variable in your model. It may depend on how strong the buy signal is and it will probably depend on how many assets you have available to buy stocks. An individual will most likely not have the assets on hand to buy stocks that Berkshire Hathaway would. It is interesting to note that if large purchases are being made by Berkshire Hathaway the price actually changes when people find out or even if they suspect. That is a dynamic that you could ignore for smaller purchases.