Log in

Neural Networks: Myths and Reality

http://www.safehaven.com/article/6203/neural-networks-myths-and-reality

This is a nice article, I think the Myth 5 is very interesting to read. That is why I think the Eliotware approach is interesting. At least it helped me to make those neural nets softwares work out of sample. This is to read together with the market state analysis. When I fail at least I know why. 

This is a small light in the tunel, I hope you would benefit from it.

Myth 5: The Quality of the Forecasting Result Depends Solely on the Quality of the Network Used

The quality of the forecasting results does depend on the quality of the network you apply, but for not more than 10-15 %. The rest depends on how well the trader has prepared the data sets the network works with. The data sets must be sufficiently representative. They must include all the important influencing factors. Besides, the application of a neural network must be combined with Money Management and classical filters.