Selecting Methods for Developing a Trading System

By: Murray A. Ruggiero

The following is an excerpt from Cybernetic Trading Strategies

SELECTING METHODS FOR DEVELOPING A TRADING SYSTEM

After you have developed your premise and selected the technologies that can be used to support it, you must prove that your premise is valid and that you actually can use it to predict the market you are trying to trade. 

Another issue that you need to deal with is whether a system that is based on your premise will fit your trading personality.  This issue is often overlooked but is very important.  Let's suppose your premise is based on the fact that the currency markets trend.  This approach will not work for you if you cannot accept losing at least half your trades or are unable to handle watching a system give up half or more of its profits on a given trade.

In another example, you might have a pattern-based premise that produced a high winning percentage but traded only 10 times a year.  Many people, needing more action than this, would take other trades not based on a system and would start losing money. 

Let's now look at several different premises and how they are implemented.  This information, plus the pros and cons of each premise is shown in the table below.

After you have selected your method, you need to test it.  Let's suppose your premise was that T-Bond prices can be predicted based on inflation.  Several different commodities can be used as measures on inflation; for example, the CRB index, copper, and gold can all be used to predict T-Bonds.  Next, you need to test your premise that inflation can be used to predict T-Bonds.  When inflation is rising and T-Bonds are also rising, you sell T-Bonds.  If inflation is falling and so are T-Bonds, you buy T-Bonds.  You can then test this simple divergence premise using either the price momentum or prices relative to a moving average.  Once you have proven that your premise is predictive, you can use a simple reversal system and start to develop your entries and exits.

DESIGNING ENTRIES

The simplest type of system is the classic reversal. For example, the channel breakout system is a reversal-type system.  This type of system can be either long or short – a feature that creates problems because sometimes a reversal-type system can produce very large losing trades.

Having discussed the simplest type of system entry, let's now examine the entries themselves.  There are two major types of entries: (1) simple and (2) complex.  Simple entries signal a trade when a condition is true.  Complex entries need an event to be true, and another "trigger" event must occur to actually produce the entry.  A simple entry will enter a trade on the next open or on today's close, if a given event is true.  For example, the following rule is a simple entry:

If today = Monday and T-Bonds > T-Bonds [5], then buy S&P 500 at open.

The rule's conditional part, before the "then," can be as complex as needed, but the actual order must always occur when the rule is true.  Complex entries use a rule combined with a trigger, for example:

If today = Monday and T-Bonds > T-Bonds [5], then buy S&P 500 at open + .3 range stop.

This is a complex entry rule because we do not buy only when the rule is true.  We require the trigger event (being 30 percent of yesterday's range above the open) to occur, or we will not enter the trade.

For both types of entries, the part of the rule before the "then" states the events that give a statistical edge.  In the above examples, Mondays in which T-Bonds are in an uptrend have a statically significant upward bias.  Triggers are really filters that increase the statistical edge.  Suppose, for day-trading the S&P 500, we use a trigger that buys a breakout of 30 percent of yesterday's range above the open.  This works because once a market moves 30 percent above or below the open in a given direction, the chance of a large-range day counter to that move drops significantly.  This is important because the biggest problem a trading system can have is very large losing trades.  They increase the drawdown and can make the system untradeable. 

The top traders in the world use these types of complex entries; for example, many of Larry Williams' patterns are based on buying or selling on a stop based on the open, plus or minus a percentage of yesterday's range when a condition is true.

Now that you have a basic understanding of developing entries, you need to learn how to test them.  When testing entries, you should use simple exits.  Among the simple exits I use are: holding a position for N bars, using target profits, and exiting on first profitable opening.  Another test of entries is to use a simple exit and then lag when you actually get into the trade.  I normally test lags between 1 to 5 bars.  The less a small lag affects the results, the more robust the entry.  Another thing you can learn is that, sometimes, when using intermarket or fundamental analysis, lagging your entries by a few bars can actually help performance.  Testing your entries using simple exits will help you not only to develop better entries but also to test them for robustness.

When you have found entry methods that work well, see whether there are any patterns that produce either substandard performance or superior performance.  These patterns can be used as filters for your entry rules.