Search results

Hi Shiko. I did not read all your posts. My advise - stop trading, stop losing money. Seriously, you do not understand what you are doing. If I do not count my losing days - I would be millionair. But nobody can predict in advance will this day be profitable or not. You shifted your mind, you...

Hi guys, I was born in Dushanbe, now live in Moscow. It is unbelievable you are still in Tajikistan. I suppose there is no Internet there :).

Thanks for your reply, I agree that data preprocessing is the core of datamining. But after that you need to find the stable global minimum, there are too many parameters you can vary. Could you please share your comparative results of NN vs SVM?

I suggest you to run these profitable patterns on other markets, similar to QQQQ, like CL, ER2, ES and GC. If they are profitable on other markets - chances are high they will work realtime. As for QQQQ, you need to run test yourself. You may divide your 12000 historical data into several...

I use say Momentum5 (M5[0]), then M5[-1] which was 1 bar in behind, then M5[-2] and so on Then I may compare it to M3[0], M5[0], M7[0], M11[0], M13[0] and M17[0] In my tests there were no differencies. May be I should run more OOS tests. Then my point is there is NO differencies whether you...

I used free libraries to predict intraday data. NN = FANN SVM = libsvm and tinysvm RVM = dlib the data preprocessing and analysis was on C++. With intraday data you have many samples to train on and you can get higher correlation on the OOS. But there are too many tricks to get the best...

Do you mean "lack of degrees of freedom" problem and overtraining? Which other approaches did you use? I tried NN, SVM and RVM. SVMs in theory allow to find global minimum, but you need to choose Gamma and C coefficients. It takes time to go through the G, C grid and calculate CV...

This is the classical overtraining problem. You need train your NN to generalize on data, not to fit your data. Don't know the good solution, I use Cross-Validation set. Big NN does not neccessary means overtraining, but you need to have many many data to train it on.

Predicting 5 min bar is just the part of the strategy. I use it to calculate levels to enter the market. When other strategies have signals to go long, I use this calculated level to place BuyLimit order. There is no magic in prime numbers, as well as in Fibonacci. While they could help to...

I use time series of 5min price difference. I don't think momentum of multiple time frames will improve my results. In fact I tried similar approach earlier. Which market is more technically traded in your opinion? For me it was also very strange. I may have several different NN, each one...

I predict next_price - current_price or "speed" of the price and volatility. I can predict 5 min speed with correlation around 0.64 for e-mini Russell 2000. And volatility can be predicted even better. But it does not give me a profit, market is quite effective.

http://www.maxdama.com/2008/12/trading-system-description.html

I used SVM, libsvm in C++ project to predict the market. Unfortunately I did not succeed. Before SVM I used NeuralNetworks for the same reason. What I found that SVM is slow in learning (you optimize couple of parameters G and C). The prediction is also very slow, in comparison with NN. And the...

Yes it did not open at the bottom limit because Bernanke lowered rate and there was a pullback in prices just before the opening bell. After the open prices went lower but did not reach the low for the day. When was the second time of limit down?

As far as I remember, last time the limit for ES was on that day when Societe General liquidated its long position. It was a Monday, US holiday. The next day on Tuesday before the opening bell the ES market reached the limit, as well as NQ, Russell2000 and YM contracts. The price was not allowed...

You do not understand probabilities. Let us consider an example. You enter the trade at 1000, place TakeProfit at 1025 and StopLoss at 999.75. Your MaxWin = 25 points. Your MaxLoss = 0.25 points. The Ratio = 100. Why don't you trade such a strategy? If market is fully random then math...

I agree with you, but MOST traders lose money not because of black-swan events, but because of they do not have an edge.

I read your "method". The very basic model about the market is "market is random". So when you enter the market with TP = 3 points and SL = 3 points the chances of heating TP and SL are equal. In fact when ES hits TP it may be not filled. But when ES hits your SL it is 100% get filled and may...

Algo, you speak about black-swan events. But this is only one of the reasons why traders lose money. Generally people lose money during normal market conditions. 1a2b3cppp had a good strike in his favour during the choppy market. I wonder how will he trade when there come trends. And thouse...

But if you risk only 1% per trade, you would NOT earn 340k with the Acrary' example, but something around 194k (in 1.75 times lower).