The NeuroShell Trader is trading system building software. It is not a trading system in its own right, it is a toolkit of both traditional and artificial intelligence (AI) techniques you can combine to form computerized trading models. The models can consist of indicators and rules like traders have used for years, artificial intelligence techniques, or hybrids of both. It will build models for equities, futures, commodities, options, FOREX, indexes and more. You can build models for exchanges all over the world, like the NYSE, AMEX, FTSE, DAX, ASX, TSX, SFE, and many more. To build models you just need to be able to obtain data for the instrument or exchange in which you are interested. Then the models you build will automatically back-test, and continue to give signals into the future as new data arrive.
Advanced degrees and skills not necessary
To use NeuroShell you do not need to be a programmer, a Ph.D., an AI expert, a mathematician, or a statistician. In fact, sometimes it is better that you are NOT one of those things. That is because neural network experts, for example, frequently cannot come to grips with how easy and fast it is to train our neural networks. They are usually tied to the old style neural nets that require lots of “tweaking” to even get a net working. Often they think there must be something inferior about our technology because we have made it simple enough for traders and other novices to use.
Artificial intelligence study not required
Many people think they must have to read books about neural networks, genetic algorithms, and fuzzy logic or take a course before they can effectively utilize our software. That is just not true. We have already done all that studying for you starting in 1988, and created software that allows you to concentrate on the business end, not the science end. Our genetic algorithms, for example, act almost like other traditional optimizers. The main difference is you don’t have to give them search increments, because they don’t search the same way. With our advanced neural nets, you mainly worry about what to feed them, instead of how to get them configured and running. We let you drive with an automatic transmission, power windows, power steering, and power seats instead of making you learn to shift gears and do everything else manually.
Not a “silver bullet“
Although we have made artificial intelligence easier to use, it does not instantly build wonderful trading systems. However, we do provide a number of examples and there are many traditional systems designed by others available in the Trader Tips from Stocks and Commodities library section of the support site. The NeuroShell DayTrader Professional is like the NeuroShell Trader Professional, except that it reads and displays intraday (real time) data bars. There are also some additional indicators to define time based events. For example you can specify you only want to trade between 10 am and 11am.
Everything is chart based
Charts are the major component of NeuroShell. You may open many charts at one time, either new ones or ones you have previously built and saved. When you create a new chart, you specify their periodicity with which you want to see and process the data, as well as how far back in time you want to load the data. Next you specify the related instruments whose historical data should be loaded into the chart. They are the target instruments for which you wish to create trading signals. Multiple instruments in the chart show up in their own chart page. For the rest of the discussion in this document, let’s say you load IBM, DELL, HPQ, and AAPL as your target instruments. (They don’t have to be stocks; they can be FOREX pairs, commodities, E-minis, options, etc).
Charts contain data streams, which can be plotted or hidden. Of course, the first data streams loaded will be open, high, low, close, volume, and possibly more raw data for the target instruments. You can also insert other data streams called other instrument data that will be available in each chart page, like indexes or Data Sources for other stocks. This other instrument data is information you want to use to create trading signals. For discussion, let’s say you believe that the Dow Jones US Computer Index ($DJUCR on eSignal) and INTC will be useful for deciding how the target computer stocks should be traded. You would then load these as other instrument data so that they will be available data streams in all chart pages.
The next data streams you will want to include will probably be indicators. Models generally are built using indicators based upon the raw data and the other instrument data. Let’s say you believe that the following indicators will be useful in models that will produce trading signals, because you have heard people in your investment club talking about them:
1. The spread between each target stock and INTC
2. The relative strength between each target stock and $DJUCR
3. A stochastic %k indicator applied to each target stock
Therefore, the next thing you might do is insert the indicators above into your chart using the Indicator Wizard.
Sometimes you may have in mind indicators that are too complex even for our Indicator Wizard to construct. In that case, you can program your own in standard languages.
You may or may not have a clue about what the indicators above do – read on.
Once the chart loads up with the requested data, you are ready to define one or more models in the chart. Any model that you build in the chart automatically applies to all instruments in the chart. Your model can be optimized the same for all chart pages, or custom optimized for each chart page. Models can be either Trading Strategies or Predictions.
You may or may not have a clue about how the indicators you have chosen work. If you do, you probably have some idea about how they would be used to generate trading signals, rules like “Buy when the relative strength between the stock and the $DJUCR is high, and the spread with INTC is low.” In this case you will want your model(s) to be Trading strategies, even if you are unsure what values should be considered high and low above. The genetic algorithm optimizer will find the values for you.
If you either have no clue about how the indicators work, or no clue about appropriate rules for them, you will probably want to build a Prediction with a neural net for your model(s), because neural nets find their own rules.
Note that you can insert several models in a chart. Once you insert a model, it automatically applies to all chart pages.
The Trading Strategy Wizard is a fast mechanism for entering trading rules without having to type messy formulas or write in some algorithmic programming-like language. The Wizard is all point and click. You just list the rules for long entry, long exit, short entry, and short exit (cover). Each of these rules is in fact an indicator you build just like any other indicator – with the Indicator Wizard. You can also enter indicators for stop and limit price levels, including trailing stops.
If you want to optimize your trading strategies, the genetic algorithm optimizer will do these things for you:
1. Find which of the rules you have listed should be used in combination
2. Find out what the parameters of the indicators in your rules should be set to
3. Perform 1. and 2. above at the same time (we call this full optimization)
Even your stops and limits can be optimized.
When the Trading strategy is complete, it will show you historical buy and sell signals. As new data is entered into the future, those buy and sell signals will continue to appear with each new bar. You can insert a variety of indicators to plot how your profit is growing.
Predictions are neural nets made with the Prediction Wizard. That’s what our standard neural nets do, they make predictions about the future value of a data stream, usually a price or change in price, but any data stream can be predicted.
Here is basically all you have to do to make a prediction model:
1. Choose some inputs – data streams, usually indicators, that you believe are leading indicators of the market
2. Decide what you want to predict, usually change or percent change of the open or close
3. Decide how much historical data will be used to train the neural net
4. Decide how much historical data you want to use to test how well the neural net has learned
If you want to optimize your prediction, the genetic algorithm optimizer will do these things for you:
1. Find which of the inputs you have listed should be used in combination
2. Find out what the parameters of the indicators in your inputs should be set to
3. Perform 1. and 2. above at the same time (we call this full optimization)
4. Find neural network thresholds for trading
When the prediction is complete, it will show you historical buy and sell signals. As new data arrive in the future, those buy and sell signals will continue to appear with each new bar. You can insert a variety of indicators to plot how your profit is growing.
Sometimes when you build traditional models, neural net models, or optimized models of any type, it is possible to make a model so good that it does not hold up with future market conditions. This is called over-fitting. Therefore, NeuroShell contains facilities that will automatically backtest with out-of-sample data for you, so you can gain confidence that your model will hold up in the future.
NeuroShell lets you take almost any condition, not just trading signals, and define an alert to let you know when that condition has just occurred.
Your next step should be to view the training videos that we have provided. They are just a few minutes each and will make learning NeuroShell so much easier than trying to learn from our help file. After you have watched the videos a few times, load our example charts in order and read the accompanying explanations carefully.