I. How to keep receiving this newsletter
It’s really simple: just tell us when your email address changes! If you like this newsletter, remember to call or email to tell us if you change your email address. Otherwise, you’ll stop hearing from us.
II. Announcing the “Fuzzy Pattern Recognizer” Trader add-on
How many times have you wished you could just let your software scan a price series and let you know when it has found a particular pattern that you like? You have in your mind a special pattern of moves that you believe could precede a strong change in the market, but you’d like the software to just monitor the incoming bars looking for your pattern. Well now you can do just that with the Fuzzy Pattern Recognizer add-on for the NeuroShell Trader series! And you can do it using fuzzy logic!
Fuzzy logic was invented by Lofti Zadeh, and written about extensively in books by Bart Kosko. Fuzzy logic has been used successfully in machines and software around the world, even in “smart” household appliances. Now you can add this smart control to your trading, and it is easy to use because we’ve done the hard work for you!
The Fuzzy Pattern Recognizer is a fuzzy logic engine which lets you describe your pattern in “fuzzy” rules (approximate rules of thumb). It is really a series of indicators that show you, on a scale of 0 to 1, how closely the current price series matches your pattern. Turn on an alert in the DayTrader Professional and the Fuzzy Pattern Recognizer will scan your incoming bars looking for all of your favorite patterns. The alert will sound when the match is above .6, .8, or any value you select.
Fuzzy rules are rules that are general in nature, not exactly specified. We describe price or indicator curves with the following fuzzy (verb) rules:
1. rises sharply
2. rises
3. remains steady
4. drops
5. drops sharply
Here are some example rules written in English which can be specified in the Fuzzy Pattern Recognizer add-on:
1. The close rises sharply, then stays steady, then rises sharply again.
2. The RSI rises, then drops, then rises, then rises sharply.
3. The high remains steady, then drops, then rises, then remains steady, then drops, then drops sharply, then remains steady.
4. The close drops sharply.
Here are some additional highlights of the Fuzzy Pattern Recognizer:
1. If you don’t have any favorite patterns, you can let the genetic algorithm find them for you if you own the NeuroShell Trader Professional, or DayTrader Professional.
2. You can specify that you want to look for two or more patterns, and then use the “Fuzzy OR” indicator to specify that any of your patterns are acceptable.
3. You can specify that you want to look for two or more patterns, and then use the “Fuzzy AND” indicator to specify that all of your patterns must be present.
4. “Fuzzy OR” and “Fuzzy AND” indicators can be combined for complex searches.
5. As you can see from the example rules, patterns can be found not only in a price stream, but in most indicators such as stochastics, moving averages, etc. as well.
6. You specify the number of bars in which a fuzzy verb such as “rises” applies. In other words, you determine that “rises” means over a duration of, say 10 minutes or ten days.
7. You can also set the maximum expected variation, i.e., what you consider the maximum “sharp rise” to be. In that way, you can specify fuzzy rules, and then later apply those same rules to less or more volatile issues without recoding the indicator. All you have to do is reset the maximum expected variation.
8. Although one use for Fuzzy Pattern Recognizer indicators is in Trading Strategy rules (conditions), you can also feed them into neural nets or other indicators.
There are 8 “fuzzy (verb) rule” indicators in the add-on, Fuzzy1, Fuzzy2, … , Fuzzy8. Fuzzy1 handles “1 segment” rules such as “close rises” or “open drops sharply”. Fuzzy2 handles “2 segment” rules such as “close rises, then drops sharply”. Fuzzy3 is for “3 segment” rules such as “open rises, then drops, then remains steady”, etc.
There are 3 FuzzyOR rules and 3 FuzzyAND rules: FuzzyOR2, FuzzyOR3, FuzzyOR4, FuzzyAND2, FuzzyAND3, FuzzyAND4. As previously mentioned, these combine rules. For example, suppose you are looking for either a pattern that rises sharply then drops sharply, or a pattern that rises sharply, then remains steady, and then drops sharply. Then you would use a FuzzyOR2 indicator which takes as arguments a Fuzzy2 indicator and a Fuzzy3 indicator, each specifying their respective rules.
FuzzyOR and FuzzyAND indicators may take other FuzzyOR and FuzzyAND indicators as arguments, as long as the lowest level indicators are “rule” indicators such as Fuzzy2.
There are also 8 FuzzyGA indicators, which allow the genetic optimizer to tune the fuzzy logic engine better.
We believe that Fuzzy Pattern Recognizer indicators open a whole new world of possibilities in trading with artificial intelligence. We think it will be our most popular add-on yet!
The Fuzzy Pattern Recognizer add-on costs $249 plus shipping. It requires the new release 3.2, however, which is still not quite ready. Therefore, we can’t ship the Fuzzy Pattern Recognizer until we are shipping release 3.2. However, if you want to backorder the add-on and pay for it now, we will include a free set of release 3.2 CDs when we ship. (Note: release 3.2 will be free anyway if you download it from the web, but otherwise a set of Trader update CDs costs $30 plus shipping.)
Be the first on your block to order this important new add-on.
III. Live from the forum
If you have been participating in our Trader Discussion Forum on www.ward.net recently, you have seen traders like you discussing:
a. techniques of two traders who shared their methods
b. favorite end of day data sources
c. reliable internet brokers for futures
d. issues and opinions on TradeStation Pro (R)
e. Adaptive Turboprop2 issues
These and other threads are still on the Trader Forum if you are interested. The Forum becomes more and more useful as more of you participate. Please note that everyone can participate in SOME way, and you don’t have to use your real name unless you want to. Although a registered user of any of our products can “lurk” there, you do have to be a registered Trader user to add comments to the Trader Forum. Because of this, you can be assured that you are communicating with a limited, select community, an assurance you don’t have in other forums or chat rooms on the web, where you could be talking to anybody!
IV. Researcher uses WSG neural networks in the study and treatment of rheumatoid arthritis
Long time user Guirish Solanki is a researcher at the Department of Surgical Neurology, The National Hospital, Queen Square, London. Since the mid-nineties he and his colleagues have published several impressive papers describing use of our neural networks in the study and treatment of rheumatoid arthritis (RA).
Solanki describes his work in his own words:
“Beginning with the ability to differentiate a non-rheumatoid patient from a rheumatoid patient, hitherto requiring at least 6 months for confirmation, now just with 4 basic inputs the ANN can tell you the answer! We then went further to see if the ANN could predict at which stage the patient was in the spectrum of disease. In this regard, particularly, was it possible to predict when a patient would require surgery?”
“By combining 2 large databases of evidence one containing rheumatoid patients in their early stage and another consisting of severely advanced disease who had undergone surgery, we pinpointed just a handful of inputs that determined which patients were in their early stages (non-surgical) and those that were surgical cases. This study has profound logistical and outcome modifying implications when dealing with patients with this dreadful disease. If surgery is delayed too long (the patient is bed-bound) surgery is ineffective and mean survival is in months. Yet if surgery is carried out at an earlier time there is a more than reasonable chance of several years of disease-controlled survival.”
Here are a few of Solanki’s papers:
Glasgow Outcome Scale following Aneurysmal Subarachnoid Haemorrhage: Improved prediction using a neural network with genetic optimisation
G. Solanki, J. Grieve, H. Ellamushi, T. Paleologos, S. Beales, N. Kitchen
Society of British Neurological Surgeons, 31 August -3 September 1999, Cork.
Artificial Intelligence Neural Networks: Diagnosis and Outcome Prediction in Rheumatoid Cervical Disease
G. Solanki, T. Watson, A. Singh, A. Young, H.A. Crockard
BRITSPINE 99 Meeting, 3 – 5th March 1999, Manchester
Artificial Neural Networks: Diagnostic Prediction in Rheumatoid Arthritis of the Cervical Spine.
Solanki G, H A Crockard. Presented at the British Cervical Spine Research Society Meeting, The Copthorne Hotel, Newcastle-upon-Tyne, 8-9/11/96
Diagnostic Prediction in Rheumatoid Arthritis using Neuronal Net Models.
Solanki G.
Presented at the Postgraduate Research Meeting, Institute of Neurology, University of London, 19 September 1996.
Artificial Intelligence: Can It Identify The Rheumatoid Neck ? Solanki G, Watson T, Singh A, Tammam A, Young A, Crockard H A.
British Journal of Neurosurgery Vol. II (5), pp 481, 1997
Artificial Intelligence Neural Networks: Diagnosis and Outcome Prediction in Rheumatoid Cervical Disease
G. Solanki, H Alan Crockard.
Proceedings of BRITSPINE 99 Meeting, 3 – 5th March 1999, Manchester (In Print JBJS (UK))
Glasgow Outcome Scale following Aneurysmal Subarachnoid Haemorrhage: Improved prediction using a neural network with genetic optimisation
G. Solanki, J. Grieve, H. Ellamushi, T. Paleologos, S. Beales, N. Kitchen
Proceedings of the Society of British Neurological Surgeons, 31 August -3 September 1999, Cork, (In print British Journal of Neurosurgery)
We present here a synopsis of one of one paper by G SOLANKI and HA CROCKARD:
Dept of Surgical Neurology, The National Hospital, Queen Square, London WC1N 3BG
ARTIFICIAL INTELLIGENCE: PREDICTING POST-SURGICAL FUNCTIONAL OUTCOME IN THE ADVANCED RHEUMATOID NECK.
INTRODUCTION: Cervical spine involvement is the second commonest manifestation of Rheumatoid arthritis (RA) and potentially the most serious. Cervical spine instability causes repetitive concussive microtrauma and eventually spinal cord injury. Neurological deterioration ensues and if it is such that the patient is bed-bound, then surgery has been shown to be largely ineffective. Yet, while a pre-emptive surgical strike may be appealing, surgery is not without considerable risk, and the patient may be exposed to unnecessary risk if operated sooner than it should have been. The ideal timing for rheumatoid neck surgery, thus, is a source of considerable debate.
AIMS: Using artificial intelligence neural networks (ANN) technology, develop models that predict the pre and post-surgical functional state and or outcome thereby providing decision support, to determine the optimum time for surgery. By reverse engineering these networks, identify which clinically relevant factors have contributed to the network’s prediction.
MATERIALS & METHODS: Overall 194 surgical rheumatoid cases (37 males and 157 females, aged 13-82, RA 5 to 60 years duration) recruited from the prospective database maintained over 10 years by the senior author and 435 non-surgical RA patients thus far recruited from the ERAS – Early Rheumatoid Arthritis Study – prospective observational database (152 males, 283 females, aged 17-83, RA duration 0 to 10 years) were the subjects of this study. Pre and post operative (in the surgical group) demographic, clinical, radiological and functional profile data was collected. Measurements were made on lateral flexion and extension cervical radiographs. About 90% of the above data profiles were used to train and internally test the 3-layer feedforward with backpropagation, and general regression with genetic optimisation neural models. These were then externally validated on a new set of data not previously exposed to the neural networks (about 10% of the data set). Further validation was obtained using more conventional tests of statistical significance. The validated neural architectures have been programmed into operational neural networks that can be ‘fired’ from applications such as Microsoft Excel, or clinical workstations such as the Reports On Call by the use of dynamic link libraries.
RESULTS: RA Progression Model: Correctly predicted a patient as a surgical case or as a non-surgical case 98% of the time, Spearman correlation = 0.92, r2= 0.85. Pre-Operative Functional Status Model: 88% correct prediction of pre-operative HAQ scores. r =0.88, r2 =0.71. Post-Operative Functional Outcome Model: 80 % Correct prediction of Post-operative HAQ scores r=0.89, r2=0.79.
Reverse engineering of the neural networks showed that the models had applied significance to the inputs similar to those used by clinicians (age, sex, severity of vertical translocation, disease duration and functional state). Models were validated with data not previously exposed to them.
CONCLUSION:
1. Accurate prognostic prediction in rheumatoid cervical spine disease is possible using artificial neural networks.
2. Reverse Net engineering offers insight into clinically significant prognostic factors.
We feel this is an encouraging basis towards predicting the ideal timing of surgery.
V. Support plans for TradeStation Pro
We plan to support the new TradeStation Pro (TS Pro) as fully as we can in the NeuroShell Trader series (NST). At this point, TradeStation Group, Inc. (a.k.a. Omega Research) has not released to us the developer’s details on interfacing with their internet data feed. However, our current end of day interface with TradeStation 2000, which moves data streams from TS charts to NST chart and back, still works with TS Pro. As soon as we learn how to access TS Pro’s data feed, we’ll try to implement that access into NST also. Hopefully, access will include intraday as well as end-of-day data for you DayTrader users.
VI. Clean, historical ASCII intraday data
Tick Data, Inc. is owned by a long time user of NeuroShell neural network trading models. Recently, the firm announced the release of its database of intraday price and volume history on individual equities. This database compliments the firm’s existing futures and index databases which, according to them, “creates the world’s single largest source of clean, reliable intraday data for traders and trading system developers.”
The equity database contains one-minute price and volume history on the largest 1,000 capitalized stocks from January 1, 1991 until present. The data is provided in a compressed format together with a software program, TickWriteT, that enables users to create time intervals of any size, adjust prices for stock splits, and include or exclude pre-market/extended hour trading sessions. Tick Data files can be loaded into the NeuroShell DayTrader. Visit Tick Data at www.tickdata.com for more information. Ask for the 20% discount for NeuroShell users.
VII. Trader’s Tips
Q. What is the difference between “return on trades” and “return on account”? Which one should be used when comparing to “buy and hold”, since they are sometimes so very different?
A. Return on Account is the percentage return over a period of time on your money invested. Another way of saying this is that it is (net profit)/(account size required). Return on Account is very simple and straightforward when considering only one trade, but it can get more complicated if there are several trades at different price levels, as we will see in some examples that follow.
Return on Trades is the cumulative sum of the percentage returns of individual trades. If you make three trades, during which you made 5%, 7%, and 10%, then your Return on Trades is just 5% + 7% + 10% = 22%.
It can be noted here that the percentages 5%, 7%, and 10% above are actually the percentages you’d get if you computed Return on Account separately for each individual trade. However, the Return on Account for the whole series of trades will not be 22% as you will see.
Return on Account is best for comparison with “buy and hold”, which is just the percent change in price. If you compare with Return on Trades you may erroneously conclude that you aren’t beating buy and hold when you may be. That is because return on Trades looks much worse on a trending stock.
Some examples will make the differences between these figures more clear. For purposes of clarity, we will assume no commissions and no slippage in these examples.
—————————————————————
Case 1: You buy 100 shares of a stock at 50 and sell them at 60.
Return on Account:
The required account size is 100 shares * $50 = $5000.
The net profit is 100 * (60 – 50) = $1000.
Therefore Return on Account = 1000/5000 = .2 or 20%
Return on Trades:
The sum of the trade percentages = 20%
Therefore Return on Trades = 20%
—————————————————————
Case 2: You buy 100 shares of a stock at 50, sell them at 80, repurchase them at 80, and then sell them again at 90.
Return on Account:
——————
The required account size is 100 shares * $50 = $5000
The net profit is 100 * (80 – 50) + 100 * (90 – 80) = 3000 + 1000 = $4000.
Therefore Return on Account = 4000/5000 = .8 or 80%
Return on Trades
—————-
We compute the percentages individually:
Trade 1 percentage is 100 * (80 – 50)/(100*50) = 3000/5000 = .6 or 60%.
Trade 2 percentage is 100 * (90 – 80)/(100*80) = 1000/8000 = .125 or 12.5%. Note that the required account size is larger for trade 2, since it cost more to get into the trade.
Therefore Return on Trades = 60% + 12.5% = 72.5%
—————————————————————
Case 3: You buy 100 shares of a stock at 50, sell them at 80, repurchase them at 85, and then sell them again at 90.
Note that this is the same as case 2, except that we repurchased at $85 instead of the $80 at which we last sold the shares. This means that we had to come up with an additional 100*5 = $500 to make the second trade. Therefore, the required account size is now $5000 + $500 = $5500.
Return on Account:
——————
The required account size is $5500
The net profit is 100 * (80 – 50) + 100 * (90 – 85) = 3000 + 500 = $3500.
Therefore Return on Account = 3500/5500 = .636 or 63.6%
Return on Trades
—————-
We again compute the percentages individually:
Trade 1 percentage is 100 * (80 – 50)/(100*50) = 3000/5000 = .6 or 60% as before.
Trade 2 percentage is 100 * (90 – 85)/(100*85) = 500/8500 = .059 or 5.9%. Note that the required account size is larger for trade 2, since it cost more to get into the trade.
Therefore Return on Trades = 60% + 5.9% = 65.9%
—————————————————————
Case 4: You buy 100 shares of a stock at 50, sell them for a loss at 45, repurchase them again after they have risen to 80, and then sell them again at 90.
Note that this is similar to case 3 because we had to come up with an additional $80 – $45 = $35 per share for a total of $3500 to make the second trade. Therefore, the required account size is now $5000 + $3500 = $8500.
Return on Account:
——————
The required account size is $8500
The net profit is 100 * (45 – 50) + 100 * (90 – 80) = -500 + 1000 = $500.
Therefore Return on Account = 500/8500 = .0588 or 5.88%
Return on Trades
—————-
We again compute the percentages individually:
Trade 1 percentage is 100 * (45 – 50)/(100*50) = -500/5000 = -.1 or -10%.
Trade 2 percentage is 100 * (90 – 80)/(100*80) = 1000/8000 = .125 or 12.5%.
Therefore Return on Trades = -10% + 12.5% = 2.5%