AI Trades Stocks Using Fundamentals Data with FinRL

Поділитися
Вставка
  • Опубліковано 15 жов 2024
  • Hey, thanks for clicking on the video.
    JOIN NEWSLETTER: witty-motivato...
    I talk about coding, python, technology, education, data science, deep learning, etc. If you enjoyed the video please like or subscribe. It is one of the best ways to let UA-cam share similar content to you and others interested in this topic. Many thanks
    GET THE CODE colab.research...
    CHAPTERS
    Load Data - 2:30
    Market Valuations - 13:00
    Market Env - 14:00
    Train Agent - 19:25
    Back Test - 21:54
    My goal is to create a community of like-minded people for a mastermind group where we can help each other succeed, so browse around and let me know what you think. Cheers!
    Keyword for the algorithm: data science finance deep learning finrl python algorithmic trading reinforcement learning fundamentals finance analysis yahoo finance investing

КОМЕНТАРІ • 9

  • @BoHorror
    @BoHorror 4 місяці тому +1

    Random question here, not sure if you’ve thought of it. Why not try list the different adjustable parameters for the model and make use of Bayesian Optimization in order to try and squeeze the most possible performance out of the model ?

  • @quantumsoftware1424
    @quantumsoftware1424 6 місяців тому +2

    i dont have any luck at all using ml to trade stock. Many forecasting sample show 98% accuracy but it doesn't work at all when a test it out. Not only that, all the rl agent also quite dumb compared to classical buy at oversold and sell at overbought.

    • @eminsh
      @eminsh  6 місяців тому

      Yes this is also my experience. The best results I've seen are from ensemble models.

    • @quantumsoftware1424
      @quantumsoftware1424 6 місяців тому

      @@eminsh almost any strategy published online also have very poor performance. I think you have to do a lot of experiment and customization to see whether it can work or now. similarly if you experiment and customize a tradinional stratgey. It will work also and takes less time

    • @eggelisback
      @eggelisback 6 місяців тому

      @@quantumsoftware1424 i am new to the field, but belief we have strategy or features that can work for both LSTM and RL. Using indicators cannot and will not be the best. Price action is tbe only way I believe

  • @marcoz4167
    @marcoz4167 6 місяців тому

    How about making a model using macro / economic data ?

  • @eggelisback
    @eggelisback 6 місяців тому +1

    Hi @Eminshall,
    I asked this in a previous video, but do you have a discord or would like to create/join one where we can find likeminded individuals on this same journey

    • @eminsh
      @eminsh  6 місяців тому

      Yeah this is something that I'm trying to work on. I don't really like discord even though it's really popular. I'd like to build a custom solution. Slow going since me and my family got really sick this winter.

    • @eggelisback
      @eggelisback 6 місяців тому

      @@eminsh i will send you an email