Agree with this. I have yet to see any legit performance numbers for these algo systems... It's really nothing that you cannot read about in 15 year old AI papers. I flat out do not believe the story: "I'm not an experienced trader... But I'm a software genius... Blah, blah, blah". Black boxes can be ** an adjunct ** to a classic trading operation... But cannot substitute for one... That's just too easy.
The trading world is filled with wannabee Jesse Livermores. They dredge up things that experienced traders rejected long ago, as if they have found the answer. Hasn't anyone ever heard of something called "finding an edge" rather than trying to find a technology?
Yes... that is the correct order. (1) "Find an edge"... Usually something creative... Something relatively few people are doing... By definition... this means exploiting a market inefficiency. (2) Trade profitably using your "edge" for months or years... Becoming a great trader over time. (3) Optimize, optimize, optimize. (4) Automate, automate, automate. If you are a computer genius and skip steps #1 and #2... You will likely have a very sub-optimal black box system... And will be competing against algo systems built by professional trading firms... Firms with multi-million dollar tech budgets... And a zillion man-years of hardcore trading experience.
I use NN for one reason and one reason only-- to train an oscillator to predict one or two bars (only) into the future. It's very simple and automated. Just another confirming tool and should be used wisely. Smoothed momentum in this chart is optimized two bars and trained on two days data. Predict is blue running slightly ahead. Slight edge, sometimes it's all one needs.
There is one thing I don't understand when people say "find an edge". I can think of two possible "edge" types. One is fundamental and other is technical. I imagine fundamental edge as something based on fundamental, relatively subjective data, like investigating company's results before buying its stock, something like that. Technical edge is based on technical and/or statistical analysis of price data, like "if condition X is present, then there is probability P that event Y will happen". So when one says "find an edge", what does he mean? Statistical significance by objective analysis or some obscure subjective analysis (i.e. "gut feeling", intuition, discretion, etc.)?
infolode, can you explain this a little more? Is the blue line the prediction of the NN? Is the blue line shifted forward? It does not appear so. Ron