I'm aware of one guy (with rather impressive business and software credentials) who succeeded in developing a non-trivial algorithm but the only way he could make money on it was trading with his own money since the barrier to accepting money from others for trading purposes puts you into a league where you have to essentially set up an investment fund and that's several million dollars sunk costs to do it correctly.
On Tue, Sep 27, 2022 at 6:38 PM Giovanni Santostasi <[email protected]> wrote: > By the way, given we started this topic and there are a lot of intelligent > and experienced people in this group. > Are you aware of any trading system based on AI (any approach including > Deep Learning), something you developed or read about in a paper, that can > give a solution that is not the TRIVIAL solution: today price = tomorrow > price. > My experience is that when you train an AI to predict price movements it > always gives you variations of the TRIVIAL answer. Basically, you look at > the prediction and it looks like the price chart moved ahead (so basically > lagging) by one bar. Are you aware of anything that does slightly better in > the long run? > Giovanni > > > On Tue, Sep 27, 2022 at 4:07 PM Giovanni Santostasi <[email protected]> > wrote: > >> Stefan, >> I have mentored and taught for more than 30 years. I have students that >> befriended me and follow me on FB for decades and still thank me for the >> impact I had in their life. >> Learning starts with realizing what you don't know or at least realizing >> you don't know much about a field you are trying to learn and get familiar >> with. >> Your post was grandiose and naive. >> There was no hint you were joking or making fun of yourself. >> It was also based on the idea that what you want to do is not already >> been tried. >> Anybody with even a small trading experience would have noticed >> immediately. >> I even took the time to understand what you were trying to do, that is >> basically: find some entry points and get out when you have a certain >> profit or loss. That is just a basic trading idea that is used all the time >> in trading. >> You didn't propose any interesting method to determine the entry points >> that is the critical thing. >> I didn't insult you or put you down in any way just pointed out what the >> issues were, like dealing with slippage and all kind of trading >> inefficiencies. I gave you practical advice like recalculating your >> performance using many different time scales to see how cost impacts your >> trading. Believe me, if I wanted to be insulting I will have used a >> completely different tone and language. I just wanted to give you a taste >> of reality. >> It seems to me that everything else came from you. >> You are easily offended and super defensive. You will need much harder >> skin to be a successful algotrader. >> The Market is the harshest mistress I have encountered in terms of >> intellectual challenge and I worked in astrophysics, neuroscience, and >> other hard science fields. One can bullshit in other fields but not in >> trading, or what you do works or not and you find out quickly. >> Giovanni >> >> >> >> On Tue, Sep 27, 2022 at 11:01 AM stefan.reich.maker.of.eye via AGI < >> [email protected]> wrote: >> >>> On Tuesday, 27 September 2022, at 12:21 AM, James Bowery wrote: >>> >>> You'll avoid most of the amateur pitfalls by following this simple >>> procedure: >>> >>> 1) Get an Alpaca account. >>> >>> Thank you, I will keep it in mind. >>> >>> @Giovanni: You may not be aware of the impact of your actions. I did not >>> derive any immediately actionable insight from all you wrote. The emotional >>> impact was just to discourage me. I'm relaying this as it is, and I don't >>> have a reason to lie about it. >>> >>> Your actual point - that I am naive about crypto trading - yeah sure, >>> it's probably true. I did some copy trading and some manual trading, won >>> some, lost some in the process. >>> >>> I will definitely make this bot, and it may turn out lucrative or not >>> lucrative. Sure. >>> >>> I just advise you that you should be aware of what reaction/emotion you >>> cause in people. You later said, you want to see me succeed. That even took >>> me by surprise because you gave the opposite impression at first. >>> >>> Think about how a coach treats their students. Do they call them naive? >>> No. They observe the progress, encourage and guide if necessary. >>> >>> Yeah the bot name ("Money Printing Machine") is grandiose, but are you >>> not able to take things lightheartedly? Who cares? If the bot is a flop, >>> I'll laugh about it, be happy to have made it and go back to image >>> recognition. If the bot works, we'll have a source of income and endless >>> fun watching it trade. >>> >>> Cheers >>> Stefan >>> >> *Artificial General Intelligence List <https://agi.topicbox.com/latest>* > / AGI / see discussions <https://agi.topicbox.com/groups/agi> + > participants <https://agi.topicbox.com/groups/agi/members> + > delivery options <https://agi.topicbox.com/groups/agi/subscription> > Permalink > <https://agi.topicbox.com/groups/agi/Ta2a8c93c499a68be-Mb730509fa82a0750fa3e447e> > ------------------------------------------ Artificial General Intelligence List: AGI Permalink: https://agi.topicbox.com/groups/agi/Ta2a8c93c499a68be-Maffba4f4301902546bc30f16 Delivery options: https://agi.topicbox.com/groups/agi/subscription
