Using Machine Learning for discretionary trading

Good topic here. I tried to build ML model using TensorFlow (Python) and Golang to generate CSV input data. I used historical data and calculated RSI, MACD, SMA, EMA, and BUY/SELL/HOLD signals for each data point like this:

and other technical indicators (over 25 in total). I trained a model for each ticker (though I don't have much data) and run forward testing, so not too bad actually (look into screenshot)....

and then pass to model current data with all tech indicators(RSI etc... as said before), and it basically predicts buy/sell/hold...

So not sure what is the good avg gain for short trades? not perfect to be honest but I can play with other indicators and feed probably more data (kind of limited now).

 

%%
YES;
Stock Traders Almanac defines it reasonably well.
But so much of that stuff in there changes
Discretion helps, AI or machine learning never would have been done without discretion.

 

Yup, you can do much more than that.

Here's a read that can provide you some food for thought: https://blog.quantinsti.com/artificial-intelligence-machine-learning-trading/

Of course, this was just a beginner-level blog to help you understand the scheme of things.

Hope it helps!

 

I’m currently using machine learning for price prediction.

 

Really interesting points about translating discretionary trading into machine learning logic. I’ve been experimenting with hybrid approaches myself, but no matter how smart the system is, poor position sizing ruins everything