Hi everybody, first a word of introduction. I am new to this forum and to the forex trading as a whole. After reading several books, playing a bit with a demo account on forex.com and trying several other platforms I started my first mini account with them.
Two days ago I found this forum and liked the contents and the discussions very beneficial.
I am currently studying bioinformatics and I thought of several systems that I might program to analyze the markets, as the field of bioinformatics is in fact dealing with the same problems as much of the technical analysis - discerning signal out of noise using statistical methods. I wanted to know your opinion whether it actually is worth my while (I mean not necessarily in terms of lots of gained gained money, but more in terms of scientific interest (although if I found a nice scalping system that would provide me with just 10 pips a day I would be a millionaire in <5 years)).
The systems I thought of trying to build should be first of all robust, i.e. they should work among as diverse market conditions as possible - and I also want to ensure their evolvability. What I mean by this that those systems should change their strategies as we go along. The implementation I think should be very computation-intensive and I am not sure that the problem is not NP-complete. The key I thought of would be implementing some kind of a genetic algorithm that the selection function would be measured most of all through robustness.
Now another idea I thought of that might contribute a lot to developing my system is simulating pseudo-market conditions. Tell me what you think of this:
A) Measuring the different parameters of a market and building pseudo-data with those same conditions using random variations on the same theme.
B) Maybe looking for HMMs in the market data and trying to rebuild the data with those same HMMs.
C) some kind of smart shuffling of the data.
Do you think that using those parameters would still overfit the best strategy? Just because it would find my parameters by which I constructed the market data?
I would be very interested in hearing (reading) your comments to the ideas above.
Two days ago I found this forum and liked the contents and the discussions very beneficial.
I am currently studying bioinformatics and I thought of several systems that I might program to analyze the markets, as the field of bioinformatics is in fact dealing with the same problems as much of the technical analysis - discerning signal out of noise using statistical methods. I wanted to know your opinion whether it actually is worth my while (I mean not necessarily in terms of lots of gained gained money, but more in terms of scientific interest (although if I found a nice scalping system that would provide me with just 10 pips a day I would be a millionaire in <5 years)).
The systems I thought of trying to build should be first of all robust, i.e. they should work among as diverse market conditions as possible - and I also want to ensure their evolvability. What I mean by this that those systems should change their strategies as we go along. The implementation I think should be very computation-intensive and I am not sure that the problem is not NP-complete. The key I thought of would be implementing some kind of a genetic algorithm that the selection function would be measured most of all through robustness.
Now another idea I thought of that might contribute a lot to developing my system is simulating pseudo-market conditions. Tell me what you think of this:
A) Measuring the different parameters of a market and building pseudo-data with those same conditions using random variations on the same theme.
B) Maybe looking for HMMs in the market data and trying to rebuild the data with those same HMMs.
C) some kind of smart shuffling of the data.
Do you think that using those parameters would still overfit the best strategy? Just because it would find my parameters by which I constructed the market data?
I would be very interested in hearing (reading) your comments to the ideas above.