Algorithmic Quant Trading (Machine Learning + Stat-Arb) 25 replies
Forex with Machine Learning Software Project 1 reply
Machine Learning + Retail Forex = Profitable? (Quant) 1 reply
Potential new machine learning style software. 79 replies
My most recent advancements into machine learning 16 replies
Dislikedwow!!!!!!!! subscribed! where do you get the technology to conduct these tests and modules?Ignored
QuoteDislikedOP joined the Forum like 30mins ago, he sounds alot like EurUsd hmmmnnn:thinkin g:
DislikedI think if we know next candle either bullish or bearish with high probability we can build a thousand of successful strategy as we know the first step and the last step with high probability go a head my friend algotraderjo ...Ignored
DislikedThis model that I mentioned: if TP comes first =+1, if SL comes first =0, could also be modeled using logistic regression, but with what predictor variables ? I personally don't knowIgnored
Disliked{quote} You would think that! However it depends heavily on how your right/wrong answers are distributed. Knowing the net directionality of candles that have little movement is of little use, while being wrong in candles that have large values is a bad problem. This is actually why you'll see that two models may have very similar accuracy in predicting the next day's directionality but one model may be much more successful than the other. This is a reason why the K-NN and linear mapping models showed before have such different results. Their accuracy...Ignored
DislikedHi Jo, Thanks for starting this thread I am particularly interested in ML techniques but my coding skills are not there to implement by myself. Have you done any work with Bayesian networks? Most of what I have previously read on the net (there is not that much unfortunately) people have been using inappropriate ML network designs for this application. IMHO, most important feature of the successful ML network is the design, followed closely in second place by preparation/presentation of the raw data.Ignored
Disliked{quote} Oh yes, you can attempt to train to predict trade exit targets. Which is something very interesting as well (this is somewhat how some of the strategies I trade live actually work). I will continue exploring the case of daily bar predictions to get a little more into the world of machine learning and then we'll move into things along these linesIgnored
Disliked{quote} I look forward to your exit target predictions.. I use genetic programming , decision trees(random forest etc.) svm and self training NN.My project is still in development phase.But out of sample results with GP is very encouraging.It took me couple of years with GP to find very good results( > 85% winnig rate with low drawdown).So inputs are very important.Dont expect to get very good results just using RSI ,MACD etc.. as inputs. There are some very good free open source libraries :scikit in python: http://scikit-learn.org/stable/...Ignored
Dislikednice thread. this is right in my neck of woods. hope you dont share too much :-) j/k what do you think of using deep learning for financial predictions. as you have probably seen, DL has emerged as a winner for most learning problems and has out performed pretty much every other method. researchers are already claiming that DL will outdate everything else. look forward to having a thoughtful discussion.Ignored
DislikedYou can google ''Applying Deep Learning to Enhance Momentum Trading Strategies in Stocks'' for deep learning.Ignored
We can use other type of classifiers to compliment the K-NN (besides the linear mapper we tested at first). We can attempt to use a Support Vector Machine (SVM) to compliment the trading of our K-NN. An SVM model built with a C=10 and gamma=0.01 gives the result showed below in black. You can see clearly that although the SVM does suffer from the same problem near the end of the test, this model does reach an equity high at a much later date than the K-NN strategy.
DislikedOP this is a very nice and intelectual thread, i need to read it again, im a lazy reader and hate reading technical stuff that i have no full understanding of but thats about to change.. my questions are: 1.how long have you been trading this way and how long have you been succesful, if you have been succesful. 2. I was talking to my friend the other day, he told me he is testing a strategy that is doing fantasticaly well this year, past 12 months it has made alot of money, but when they created an EA to backtest it further back it actualy was a...Ignored