In this chart, you can see multiple ARM2 signals firing in the direction of trend.

ARM2 worked extremely well on stocks that exhibit smooth changes in trend.

Note: ARM2 is no longer used by members (since ARM3 is more accurate), but we have preserved it on our Nirvana Club web site for members to download and experiment with, at their option.

About ARM2 R3

ARM2 was designed around the concept of relating Market Factors (such as the current retracement percentage for a move) with Clues (e.g., volume increasing) to predict the accuracy of a given Signal using Artificial Intelligence methods.

After launching the Nirvana Club in 1996, we built a Genetic Algorithm to find combinations of Factors and Clues that formed "rules" in a Knowedge Base, such as "If MACD is rising and Volume is increasing and today's Open is above yesterday's Close, there is a 70% chance of the security going up."

This process involved many thousands of processing hours. We networked all our machines together and let them "cook" each night to find these rules.

In 1998 we released the first Knowledge Bases to members, calling it ARM2 Release 2 (Release 1 was experimental). ARM2 R2 improved accuracy by about 10 points. That was a great start, but we had a way to go. So we continued looking for better ways to do the same job.

ARM2 R3 - Our First Neural Network

In 1999 we released ARM2 R3 using a commercial Neural Network. We discovered that Neural Networks are better suited to our problem (though we later re-invented the Genetic Algorithm component when we created ARM3.) Market Factors and Clues were fed as "inputs" into a the Nerual Network to find relationships in the data.At each Signal event, a Neural Network was consulted to determine the likelihood of the security rising or falling based on the trained Neural Network. The Network issued a "Thumbs Up" or "Thumbs Down" indication on each Signal. Signals were then either passed to the Vote Line or not based on this determination.The ARM2 Release 3 Neural Networks increased the accuracy of OmniTrader's buy/sell signals by 10 to 20%. An OmniTrader profile that generated an average Forward Test accuracy of 55% could generate accuracies on the order of 65 to 70 percent. This was a phenomenal achievement so early in the Club's life.

How is ARM2 different?

An important aspect of all ARM2 (and ARM3) strategies is the fact that optimization is not used. Standard OmniTrader profiles (like Default) work by optimizing every Symbol individually to find the best parameters for the Systems being used. This is a good way to tune a System, but has the disadvantage that as soon as a new Back Test is run, the Signals will change as new parameters are chosen.

With ARM2 and ARM3, System Parameters are fixed and do not vary, which in turn means the signals will not change. Signals that are passed to the Neural Network either "make it" to the Vote Line or filtered out the same way regardless of how when the Back Test is run. The same Signal will always be seen in the Chart. This behavior definitely makes it easier to "trust" the Signals in real trading.

The Next Generation ARM2

This was very important in our understanding of how to apply Artificial Intelligence technology to the market problem. Using this knowledge, we developed the next generation of A.I. tools for members that takes advantage of OmniTrader's Strategy Builder paradigm - ARM3. ARM3 is our current Nirvana Club Signal Technology. Click here to learn more about ARM3.

ARM2 R3 Charts

The Charts on this page were generated by ARM2 Release 3. We have replaced ARM2 with ARM3 in our work for the Nirvana Club. These charts were captured shortly after ARM2 Release 3 was delivered to members (May 2003.) More recent charts are available in the ARM3 section.

ARM2 did a great job of firing signals at key reversal points. You can see the excellent Short signals in December and January in this example of ADIC.

Another stock, Aeroflex with ARM2 signals firing at excellent opportunity points to go Long and Short in the first four months of 2003.

ATMI generated more signals at key opportunity points.

Here, we see ATML forming a saucer bottom in March and April (and firing a Long at the right side of the chart). Again, note the powerful Short opportunity identified in early December of '02.

AVID Technology had several nice swings in the January through March timeframe, before the outstanding Long signal which was generated in mid-March.

Beasley tends to move in nice runs once it gets going.

Here we see a number of reasonable entry points on Benchmark (however, we would probably avoid this stock due to its extreme volatility).

Biosite is a very nice trading stock, due to the smooth moves it tends to exhibit. Here you can see a great Long in December, followed by a waterfall Short in late January 2003 - all ARM2 Release 3 signals.

Continental is another smooth mover. We had some very nice opportunities to make money on this low-priced stock in late December and mid January, before volatility increased in March.

Right away, we see the fabulous Long generated on Chiron in early March (following a nice Short from mid-January).

More great signals on Chattem.

Digimarc had several nice swings from December to March.

Dionex Corporation is a volatile stock that we would probably not trade. However, a we did see a VERY profitable Long generated in January 2003.

We picked up a nice, long trend in Drugstore.com from February, after a shorter, but very profitable Long in late December.

EDS had a waterfall decline in January, which ARM2 alerted us to. It then recovered in a big way in March. Note the ARM2 signal at almost the exact bottom.

These charts were captured shortly after ARM2 Release 3 was delivered to members (May 2003.) More recent charts are available in the ARM3 section.

We see two nice runs in Ford that ARM2 picked up, beginning with the stellar Short in late January 2003 and ending with the equally fabulous Long in April.

Genencor shows two nice ARM2 signals in January 2003 (Long) and February (Short).

Grey Wolf is another volatile stock, but we did see some nice ARM2 signals generated on it.

IDEC Pharmaceuticals had a great Short signals in late January 2003, after an exhaustion gap.

IONA Technologies is a smooth moving stock, even through it was trading around $1.00.

IMPAX Labs had two nice Longs, one in January 2003 and the next in March.

Iron Mountain had several swings in the beginning of the year, all of which were identified by ARM2 R3.

Lexicon Genetics had several nice moves. The Long in mid December 2002 was particularly potent. Note this stock declining in February while the previous stock (IRM) increasing in the same time period. We saw ARM2 R3 signals fire on both, in the correct directions.

This is one of the powerful things about our ARM technology - it allows us to diversify across multiple stocks by trading ARM Signals in both directions.

Longview generated an interesting, smooth chart after the Sell signal in mid January, leading up to the Buy in mid March 2003. Because this stock is so low priced, both signals generated huge returns.

Three nice Shorts on Moore Ltd., with a new Long on the right side of the chart.

Newpark is another volatile stock, but we had a relatively clean Long signal generated at the lows in February 2003.

Nextel is a beautiful trading range stock. Note the swings, up and down, beginning January 2003. Each was properly identified by ARM2 Release 3.

We see a near perfect V-bottom signal on ONYX Pharmaceuticals in early February 2003, following two clear Short opportunities.

Here are additional examples of ARM2 Release 3 charts. These charts were captured shortly after ARM2 Release 3 was delivered to members (May 2003.) More recent charts are available in the ARM3 section.

Here we see some interesting patterns on Pharmacopeia. ARM2 caught the 20% run in early March 2003.

American Italian Pasta had several nice Longs in the move up from 36 in early 2003.

PMI Group had several nice Shorts in the decline from a $33 high.

Transocean is a fairly volatile stock, but we did see a few clean signals fire on it - particularly the Shorts in January and March.

Symbol Technologies gave us two nice Short opportunities, one in mid January and the next in early March 2003.

Here, we see some fabulous signals on Sungard.

ARM2 generated some very nice signals on SEI Investments in early 2003.

On some charts, ARM2 only fires a few signals, as was the case on SWS. The good news is, they occurred right at the bottoms.

Syntel is a volatile stock, but we did see some nice signals early in 2003.

Take-two did just that as it dropped form its December 02 high, signaled by ARM2. We also caught the rebound in early March.

UST Inc. has several nice, smooth signals. However, after the stock became volatile in early March 2003 it would have been best to avoid. There are 10,000 stocks to choose from - find another one!

Three picture-perfect signals on Watchguard Technologies.

Valid Trend Lines are essentially sloping support and resistance lines, as shown here on AGN.

Here, we see Valid Trend Lines forming across swings in AIG.

Citigroup shows shorter swings, with good lines.

About ARM2 R4

ARM2 Release 4 is based on ARM2 Release 3, with the addition of Valid Trend Lines (VTLs) to boost accuracy and performance. This technique provided a SUBSTANTIAL boost in performance.

What is a Valid Trend Line?

Valid Trend Lines are essentially tight lines drawn across price action, with specific factors measured to create the best possible lines, such as correlation, angle of line, break bars for the line, and so on.

To the right, you can see a few examples of this method. Valid Trend Lines essentially form sloping support/resistance lines that are very powerful.

When a strong line is violated, the odds of a move following the break are higher, leading to some of the most highly confirmed reversal signals possible.

Using Valid Trend Lines to confirm ARM2 signals

The Valid Trend Line system is a powerful "confirmer." When used in conjunction with ARM2, it helps to isolate those signals which are firing at key reversal points and have additional, favorable characteristics - resulting in greatly increased accuracy, as described below.

Valid Trend Lines can be added to just about any reversal (swing) strategy to improve it. Many Nirvana Club embers are experimenting with various hybrid concepts, and posting great results to the Nirvana Club Forums daily.

ARM2 Release 4 Accuracy *

With the introduction of ARM2 Release 4, Club Members were able to establish the accuracy they want to see in their signals for the first time.

Valid Trend Lines have a setting called "Correlation". This setting defines how well the lines fit the data in the chart. By simply cranking up the value of this setting, you can get more and more accurate signals out of ARM2. This was an important advancement that led to the creation of ARM3.

Here are some performance reports from ARM2 confirmed with Valid Trend Lines, on the S&P 100 over 500 bars. It is important to note here that ARM2 profiles are not optimized - you will get the same Signals whether you look at Forward Test or Back Test results. ARM2 Release 4 Signals were typically 70%-80% accurate. *

S&P 100

Accuracy = 74% * correlation at .90 ▼

Accuracy = 82% * correlation at .99 ▼

Tuning Performance

You can see from these performance numbers that, as accuracy increased from 74% to 82%, profit per trade doubled. However, the number of trades decreased to 1/10 the initial value. Some users will want more signals. For them, the former setting is preferable. Others will want the highest accuracy possible, and run thousands of symbols through the system. For them, the latter setting is preferable.

ARM3 Evolution

ARM2 R4 was released in 2003. In 2004, we wanted to increase signal count while maintaining accuracy. This was achieved by creating multiple Knowledge Bases and Neural Networks that are tuned to specific indicators and systems.

ARM3 improved on the ARM2 Release 4 concept by making available the Neural Network Scores and a "cutoff" setting. Users can do the same kind of performance turning with ARM3 that they did in ARM2 Release 4, by adjusting the cutoff setting in the Strategy. See ARM3 for complete information.

* We measured accuracy differently for ARM2 than ARM3. For a detailed description of how we measured the accuracy of ARM2, please see How Accuracy is Measured.