Real time agent question

huseinzol05 / Stock-Prediction-Models

Gathers machine learning and deep learning models for Stock forecasting including trading bots and simulations

Apache License 2.0

7.96k stars 2.81k forks source link

Real time agent question #60

Open ai559031 opened 5 years ago

ai559031 commented 5 years ago

Hello!

I really love your works!! It's fantastic!!

I have a question on the real-time agent. When I run the app.py, there is nothing shows up in my console. Then I run the request.ipynb, it shows the current time prediction. But it seems that it won't continuously request the new stock data and the agent also not take actions in the next timestamp.

Is this because my usage way was wrong?

Thanks!!

IISuperluminaLII commented 4 years ago

you will have to give the streaming data into the .trade() function with preferably an API call to a data warehouse. and for each incoming tick the real-time bot will advance in trades. I would say implement this in PURE python and then see how the algorithm works before hosting it as a Flask app, since that requires you to configure the streaming data within the requests module and if you want to visualize your trades then you will need to serve your FLASK app with your own JS charts and what not....