When I click on the download link, my system shows a security warning. Is it safe to download and install your software?
The safety and quality of our products are our major priorities. If you are downloading from our website, it should be no problem. We use a secure web hosting. Also our products are well tested (including several industry-leading security solutions); we fix any reported bugs fast. If you have any trouble with our software, please use our on-line form to send an instant message or email us at email@example.com
I got the error message "The application failed to initialize properly..." after installation. Any advice?
If you are receiving this error message, you need to install the MS .NET Framework on your PC. Please make sure that you follow properly the pre-installation procedure described on Addaptron Software download page.
How back-test and forward-test accuracies are calculated?
Back-test accuracy shows how well the predicted results (prices) generated by the model are close to the actual historical results (prices). The back-test accuracy is used to optimize the model. However, the optimized model on the past periods may not demonstrate the same predictive ability on future periods. That is why it is important to monitor forward-test accuracy.
The forward-test accuracy indicates the predictive ability of the model on the periods that were not used for model optimization. In other words, forward-test shows the most realistic predictive ability of the model. Both back-test and forward-test accuracies are calculated using the same formula:
where p.Oj, p.Hj, p.Lj, and p.Cj - predicted Open, High, Low, and Close prices; a.Oj, a.Hj, a.Lj, and a.Cj - actual Open, High, Low, and Close prices; n - the number of back(forward)-test points.
The formula maximum possible value is 100% (absolute predictive ability). The closer its amount to 100, the better accuracy. The difference applying this formula for back-test and forward-test is the following. In case of back-test accuracy, the predicted prices result from testing the model on historical period (used for optimization). In case of forward-test accuracy, the predicted prices result from testing the model on future unknown period.
Any additional info about the methods implemented in your software?
The principles of technical analysis or prediction methods can be found on the Internet. Most prediction methods implemented in our tools are based on statistics and probabilities. To be more specific, some links as examples to read more about Neural Networks:
Can such predictions be useful for investing or trading? Any tool in human hands has own purpose and limitations. A tool cannot be used effectively without understanding the limitations and where and when a particular method can be used. This understanding comes from the theory, as well as from the testing and statistical analysis of the results.
Does Addaptron Software provide users with input data?
Users can download some EOD historical quotes files from Addaptron Software server for free. Normally, these selected symbols are big ETFs and their number is limited to 20.
I subscribed to your software but unable to run it, please help
If you still can see "lease expired" message, the most probable reason is a mismatch of your ID as a payer and user. So that the automatic system is unable to match the name (or/and email address) that was entered during the software registration and the name (or/and email address) that was entered during creating recurring payment. It can be fixed if you send us the name and email address that you can get via the main menu item "License"
What are your Neural Networks abilities to predict stocks?
Our tools maximize using Neural Networks (NN) up to the limit what we can get from NN. But the problem of predicting shares prices is not in NN abilities. Any statistical method works well if the future is predetermined by historical data. Even the best NN with a huge input of historical prices cannot predict all the time very well if the historical factor becomes weaker than other ones.
Have you done any forward testing?
When people say "forward testing" in trading systems, as a rule, it means that the system with indicator buy/sell signal was optimized on past periods and then was tested on future periods. In NN forecasting, a program is trained/optimized on past periods and then tested by comparing predicted and actual prices (these actual prices are excluded from prior optimization). However, it is called "back testing" to emphasize that it was tested on a past period relatively to users (but it is a future period relatively to the program). This past period is not used to train NN for back-testing (and it is called out-of-sample).
We encourage our users to perform back/forward (out-of-sample) testing on their own for unbiased results.
I noticed that other stock cycle software packages compute a Bartel's test statistic to assess the statistical significance of each cycle. Does your software do that?
The Bartels Test is used to measure the stability of the amplitude and phase of each cycle. It is a good approach to study a stable system with a certain set of cycles. The stability of cycles can be important. However, please be aware, the stock market is more like as a evolving semi-cyclic system.
Our module Cycles fits curve by assigning higher weights for the most significant and stable cycles. It starts fitting process by searching for the cycles with constant period and phase, and with constant and biggest amplitude. So that one can analyze the cycles significance by their position on the list. As well as, the software displays the deviation between each solution (extracted cycle) and actual curve. The deviation is in inverse proportion to statistical stability.