I'm currently in a process of building trading bot/trading signal script.
I have bunch of indicators that are giving buy/sell signals – RSI, Bollinger Bands, Stochastics, MACD …
I was thinking that for every daily pricepoint I could create one row in dataframe like this:
RSI_oversold|MACD_oversold_crossover|below_lower_Bollinger_Band|price_increased_after 10_days 1|1|0|True
And then could process it with scikit-learn implementation of decision tree or something like that.
Or do you prefer more advanced methods like LSTM neural networks?
Do you have reasonable results in your signals/trading using machine learning?
Submitted October 11, 2020 at 09:45AM by tcoil_443