Does that even make sense? How large is the data set that you base your conclusions on with the 70% to 99%? And which currencies does that cover? How does your algorithm adjust when literally anybody would start using your system?
we test project since may and apprx. accuracy for Alpha free version around 75-82 percent depends on chart and currency . Please visit forecats page to check that yourself
https://neurobot.trading/forecasts. BTC, ETH, LTC, XRP, DASH, XMR. If you want to ask real users about there expirience join in our telegram group
https://t.me/joinchat/CNzks0L-X3IDzHgKIDHU9Q . in January Beta versiont starts all forecasts will be chared with NEB Token, that means that information will be closed from the general public . Algorism is learning algorith, it ll be beter in time, especially when we implement neural market news analysys in the algorithm.
Building strong neural networks requires an incredible amount of expertise. Otherwise you end up building a system following the good old "garbage in - garbage out" theory. I see a few problems with projects claiming enormous rates of accuracy based on rather small data sets. And I would be really interested what happens if people use your system and everybody follows the predictions. How is that going to influence the accuracy? Is it making it better? Will we reach some sort of equilibrium (which I don't think because people will keep looking for the alpha)? Difficult question and I don't really know the answer.