<t>QuoteOriginally posted by: JediWarriorI do not want to sound symplistic, but both NN and HMM sound like correlation_relationships + moving averages, trying to find non-linear relationships. Don´t you agree?That does sounds simplistic to me.QuoteOriginally posted by: JediWarriorOf course, you have...

<t>QuoteOriginally posted by: muxControlQuoteOriginally posted by: msperlinQuoteMany papers published tend to use similar data set to allow fair comparisons on the basisof MSE, returns, number of transactions, etc. And you see this as a good thing ?Unless their data is very long and very big (eg. 10...

<t>QuoteOriginally posted by: JediWarriorI want to do a little research to find out an algorithm to help with my trading decisions. I am interested in intraday trading, of the market making type. Which method could be more relevant for this time frame?Choosing a particular modeling algorithm will be...

<t>QuoteOriginally posted by: bhamadicharefI think that one cannot say whether one method is better than another, it all depend on the specific application.I agree and think the literature demonstrates this amply.QuoteOriginally posted by: bhamadicharefI think that one cannot say whether one method ...

<t>I'll put myself down as Semi-Strong. Empirical research suggests that Strong EMH is false, and I'm not sure what structural or causal reason one might have for believing it. It isn't hard to believe that the market is at least weakly efficient, with so many people and machines looking desperately...

<t>QuoteOriginally posted by: exneratunriskIsn't "entropy ranking" used to create ID3 decision trees?Entropy is used in many machine learning methods, including as you say, ID3, to assess the quality of a candidate solution. Roughly, the idea is to minimize the conditional entropy of the target vari...

<t>QuoteOriginally posted by: rmax<Anecdotal tale> The US decided use a Neural Net to try and identify Soviet Hardware. They trained the network using a set of photos depicting US hardware, and then trained it using a set of photos of Soviet hardware. When they then tried to use it, the network didn...

<t>QuoteOriginally posted by: DaGuyA friend argues that neural nets are just the greatest tool and that most financial researchers deprive themselves of using this panacea that "can solve any nonlinear problem". That's a bunch of huey, but I need to substantiate my argument better. Hence, I ask. Has...

<t>QuoteOriginally posted by: kanukatchitSPLUS is way better [than MATLAB] for Statistics.That depends on what statistical analysis needs to be performed. Mathworks toolboxes and third-party software aside, the base MATLAB includes a number of basic statistical tools (mean, median, regression, etc.)...

<t>I am not a quant, but currently work as a data miner for a bank and MATLAB is my main workhorse. I currently have licenses for both the Curve Fitting Toolbox and the Statistics Toolbox. I rarely use the Curve Fitting Toolbox anymore, having written my own curve-fitting routine, and use a small nu...

<t>QuoteOriginally posted by: exneratunrisk(we) data miners say: if any behaviour has a "law of nature" behind and if you have historic (i/o) data, which represent it well, we create (approximative, predictive, interpretable, computational) models from this data automatically. The right bouquet of m...

<t>QuoteOriginally posted by: CuchulainnQuoteOriginally posted by: chentailHi!I am interested in fuzzy logic modeling.can some one recommand me websites and books?The books by Bart Kosko are good.More specifically, some of what Kosko has published is more technical (Fuzzy Engineering, Neural Network...

<t>QuoteOriginally posted by: ReflexI know this is a beginner question, so thanks for taking the time.I've been recently looking at PCA . I've browsed the forums for the many thread on this subject already, but I think I'm missing a simple point somewhere. Probably because of the current horrible st...

Clearly, data mining works, but sometimes the result is "I can't find anything".-Will Dwinnellhttp://will.dwinnell.com

<r>QuoteOriginally posted by: Pannini(1) The ideal degree of fuzziness: the "fuzziness" of the clustering is determined by the exponent m. In older research, you will see the unstated assumption that m = 2. In practice you must perform a grid search over values of m between 1 and infinity, and you m...