On the Robustness of Price Patterns Discovered by APS Automatic Pattern Search by Michael Harris
One frequently asked question about APS Automatic Pattern Search
concerns the future performance of the price patterns the program discovers. Will these patterns stay profitable? I cannot give a general answer to this question but what I can do is to give an example of price patterns discovered by APS that survive the test of time.
In another article
I presented an analysis that showed that QQQQ price patterns discovered by APS in 2002 (the ticker was QQQ then) and published in Active Trader Magazine remained profitable until the beginning of 2005. Specifically, in an article published in September 2002 by this author (See Ref. 1) and in the course of demonstrating the concept of the automatic discovery of price patterns, APS Automatic Pattern Search was used to discover patterns for the NASDAQ-100 Index Tracking Stock. The results obtained at that time for price patterns satisfying the parameters listed in Table 1 are shown in Figure 1 (original figure from the article in Ref. 1).
Trade input |
Open of next day |
Delay |
0 |
Profit target |
7% of entry price |
Stop-loss |
7% of entry price |
Minimum Profitability |
66% |
Minimum Number of Trades |
30 |
Maximum Consecutive Losers |
Less than 4 |
Table 1. Parameters used in the search for price patterns in Ref. 1
APS discovers price patterns that fulfill user-defined performance criteria and risk/reward parameters (See Ref. 2 below) and does that automatically.
Historical price data from 07/11/1990 to 05/07/2002 was used for QQQ. A total of eight (8) long price patterns were found by APS that satisfied the
parameters shown in Table 1. Each line in the results shown in the Figure 1 corresponds to a price pattern and its performance parameters as calculated by APS. Figure 1. Search results for QQQ price patterns (see Ref. 1).
Legend: Trade on
designates whether the trade entry executed on the open or close PL is the percent profitability of patterns suitable for long positions. In this case PS = 100 - PL. PS
is the percent profitability of patterns suitable for short positions. In this case PL = 100 - PS. Trades is the number of trades. CL is the number of maximum consecutive losers. Type
is either Long or short. Target shows the profit target value used in the search. Stop shows the stop-loss value used in the search. C
indicates the type of profit target and stop-loss; "%" stands for percentages of entry price. Source: Automatic Pattern Search (APS)
In a previous article I showed that the patterns in Figure 1 remained profitable in the period from 05/07/2002 to 02/28/2005 I will now repeat the analysis of my previous article
and determine how the patterns in Figure 1 performed since the time of their discovery by APS and the publication of the results in Ref
1. This is achieved by back-testing each pattern in the time period from 05/07/2002 to 09/28/2007. The back-testing function of APS was used for this
purpose and the results for each pattern in Figure 1 are shown (in the same order) in Table 2.
Index |
Index Date |
P (%) |
Trades |
CL |
4 |
20020507 |
69.23 |
13 |
2 |
7 |
20011105 |
75.00 |
8 |
1 |
11 |
20020118 |
60 |
10 |
2 |
12 |
20011112 |
66.67 |
12 |
2 |
5 |
20020412 |
59.94 |
17 |
3 |
6 |
20020123 |
64.71 |
17 |
3 |
5 |
20020214 |
72.22 |
18 |
2 |
4 |
20020305 |
73.85 |
13 |
2 |
Table 2. Back-testing results for the patterns in Figure 1 for the period 05/07/2002 to 09/28/2007.
P is the profitability, CL is the maximum number of consecutive losers.
It is clear from the results in Table 2 that all eight patterns remained profitable during the forward test period considered. This means that a trading system
based on those eight price patterns for QQQQ developed in 2002 using APS would have remained profitable in the following five years. Thus, the back
test results demonstrate the robustness of the specific QQQQ price patterns.
Note that it is not necessary to analyze the results of the test for statistical significance. Obviously, the number of trades of each price pattern in the
forward test is not enough to guarantee statistical significance of each individual price pattern. But when the sum of the trades of each price patterns in
the combined testing periods is considered it turns out that the results are statistically significant.
Next, APS Automatic Pattern Search was used to search for price patterns that fulfill the criteria shown in Table 1 in the combined time period (back-test
plus forward test) starting on 07/11/1990 and ending on 09/28/2007. A total of 15 patterns were found as shown in Figure 2. Some of the price patterns in
this case are identical to those shown in the search results in Figure 1 and some new price patterns have emerged while a few of the original ones do not
appear in the results because they no longer fulfill the performance criteria. Thus, although the range of the historical data used in the simple (not
extended, no delay pattern) search was increased significantly, the number of price patterns that meet or exceed the performance criteria almost doubled.
This is an important result because it shows that in this particular market, the passage of time affects neither the performance of price patterns nor the availability of profitable formations.
Figure 2. Search results for QQQQ price patterns for the period 07/11/1990 to 09/28/2007
Legend: Trade on
designates whether the trade entry executed on the open or close PL is the percent profitability of patterns suitable for long positions. In this case PS = 100 - PL. PS
is the percent profitability of patterns suitable for short positions. In this case PL = 100 - PS. Trades is the number of trades. CL is the number of maximum consecutive losers. Type
is either Long or short. Target shows the profit target value used in the search. Stop shows the stop-loss value used in the search. C
indicates the type of profit target and stop-loss; "%" stands for percentages of entry price. Source: Automatic Pattern Search (APS)
The results presented in this article can be confirmed by anyone with access to QQQQ historical data and a
copy of the demo version of APS (The search and back-test options are fully functional in the demo).References 1. "
Price Pattern Autopilot", by Michael Harris, in Active Trader Magazine
, Sep. 2002, Vol. 3, No 9, pp. 70-742. APS Automatic Pattern Search software by Tradingpatterns.com, http://www.tradingpatterns.com
|
