A Neural Network based trading strategy

I always dreamed about the machine which tells me to enter long right before the market starts to go up. Might a neural network be this machine? Using Tradesignal and the free Python Neural Net library Pyrenn it is easy to find out…

Part one: Classification of data

The first step in the process is to tell the Neural Network when it should give me a go. Therefore I designed me small indicator which returns 1 whenever the market has been rising for a given number of bars without falling back in between. This should have been an easy environment to make money and so I want the neural network to analyse the bars before this signal and see, if it can detect a pattern.



Part 2: Feeding data to neural network

After the classification indicator is working, the script which will do the trading has to take this information and prepare the inputs for the neural net.

data inputs to nn

data inputs to nn

I opted for a neural network with 5 inputs. These inputs will describe the market behaviour before the signal occurred by giving the %change of the market prior to the signal over 1,3,5,10&15 days. Be creative, the way you describe the market will massively influence the ability of the neural network to learn something from the past.

Beside the preparation of the training data in lines 12 to 19 the script also prepares the input data for the live trading in lines 23 to 27. These inputs, when applied on the trained neural net, will then hopefully give me a signal before the market has some good days.

Part 3: Create and train the neural network

The codes above run on every bar of the chart and thus build a history of signals. On a specific date on the chart I want to use this data and train the network. Using the Pyrenn neural network module and the data prepared before, this is done with the following lines of code.

As defined in line 37 this is a network with 5 inputs, one output and 2 hidden layers with 3 neurons each.

Lines 44 to 49 transfer the data collected in Tradesignal to the Python environment.

Finally in line 49 the training is done. The network is trained until the max number of iterations or the minimum error has been reached.

Neural Net training

Neural Net training

Part 4: Testing the signals with a trading strategy

nn test

nn test

After the training has been done the neural net is fed with live data (lines 59 to 62) to calculate the prognosis for tomorrow. If the bars before today hint that I should buy, the neural net should return 1, otherwise 0.

The most simple test for the quality of the output is a simple trading strategy. It buys if the neural net signals a buy (1) and closes the position after the number of expected positive days (as demanded by classification script) have passed.

Part 5: Results for daily S&P500 Index data

To obtain the results shown below the NN was trained with 2000 bars of daily data, prior to 2018. The out of sample trading simulation starts in 2018. About 68% of the trades have been positive, leading to a profit factor of 2.64. Not too bad for such a simple approach.

nn results

nn results

The strategy shows a low trading frequency, and as the drawdowns show, a more sophisticated exit strategy should have advantages and bring down the magnitude of the losing trades.

Profit from large daily moves

Whenever the market shows an exceptional day ranges it is time to take bite. See how you can profit from large daily market moves.

Open-Close Range

When looking at any chart, you will surely notice that the large candles tend to close near the high or low. This is due to herding. Once the market is moving significantly, everyone hops on and the large move becomes even larger. This is true for daily, weekly and intraday candles.

The chart shows an indicator which plots the daily move. Every opening is set to zero and the absolute move of the day is drawn. Around these normalised candles a long term 2 standard deviation volatility band is drawn.  Right now the 2 standard deviation volatility for SPX is about +/- 46 points.

Take a bite before the market closes

As you can see this +/-46 point barrier above/below the opening of the day is a wonderful entry point. If you enter long 46 points above the opening and go short 46 points below the opening nearly all entries would have lead to a profitable trade. To get an even higher probability of success you can volume as a confirmation. Large moves must also show high volume. The exit is done at the end of the session. This analysis does not give any indication for the next days move. So be fast, take your bite and go home with a small profit and no overnight position.

No free lunch

On the chart it looks easy, but be careful. As an example the last bar shown on the chart first crossed the band to the downside, reversed and crossed above the upper band. So you will need to use a trailing stop to lock in profits and avoid to take the full -46 to +46 points trade as a loss!





How to detect unwanted curve fitting during backtest

Whenever you develop an algorithmic trading strategy, unwanted curve fitting is one of the most dangerous hazards. It will lead to substantial losses in real time trading. This article will show you some ways to detect if the performance of your algorithmic trading strategy is based on curve fitting.

Curve fitting – what is it?

Every algorithmic trading strategy will have some parameters. There is no way around it. You will have to decide what length your indicators have, you will have to specify a specific amount for your stop loss or profit target. Beside the actual rules of your strategy the chosen parameters will usually significantly influence the back-test performance of your strategy. And with any parameter you add the danger of curve fitting rises significantly. Continue reading

The Edge of an Entry Signal

When developing a new trading strategy you are usually confronted with multiple tasks: Design the entry, design the exit and design position sizing and overall risk control. This article is about how you can test the edge of your entry signal before thinking about your exit strategy. The results of these tests will guide you to the perfect exit for the tested entry signal (entry-exit combination)

Quality of an Entry Signal

When you develop a new idea for an entry signal there are two things you would like to see after the entry: no risk and fast profits. This would be the perfect entry with the highest possible edge. In reality the market response to your entry will be risk and chance. With a good entry the upside would outnumber the downside. Continue reading

S&P500 – when to be invested

The stock market shows some astonishingly stable date based patterns. Using a performance heat map of the S&P500 index, these patterns are easily found.

Date based performance

The chart below shows the profit factor of a long only strategy investing in the S&P500. Green is good, red is bad. The strategy is strictly date based. It always buys and sells on specific days of the month. Continue reading

Noisy Data strategy testing

Adding some random noise to historic market data can be a great way to test the stability of your trading strategy. A stable strategy will show similar profits with noisy and original data. If the noise has a great impact on your results, the strategy might be over fitted to the actual historic data.

Synthetic market data?

Generating completely synthetic market data to test algorithmic trading strategies is a dangerous endeavour.  You easily lose significant properties like classic chart patterns or the trend properties of your market. Continue reading

Factor investing in portfolio management

Factor investing has been around in portfolio management for some years. Based on algorithmic rules it became the big thing in trading and the ETF industry. But is there still some money to be made? Is small beta still smart or just beta? This article will give you a Tradesignal framework to test the factor investing ideas by your own.

Factor investing

Buy and hold has been a profitable approach in investing. But customers ask for more. So technical analysis came around and held up the promise that market timing is possible. As the returns did not match this promise, algorithmic trading was invented. Clearly defined rules made it possible to backtest any given strategy, and if done properly, the returns equal the ones promised during the backtest. But this requires a lot of intellectual power and relies on cheap execution, so these returns are usually not available to the public. Continue reading

Technical vs. Quantitative Analysis

“The stock market is never obvious. It is designed to fool most of the people, most of the time” Jesse Livermore

Technical Analysis

Technical analysis is a form of market analysis based on historic price patterns. The basic assumption of technical analysis is, that human behaviour does not change over time, and thus similar historic market behaviour will lead to similar future behaviour. Technical analysis is a predictive form of analysis, a technical analyst will try to estimate what the market might most probably do over the next period of time. Continue reading

An Algorithmic Stock Picking Portfolio

In this article I will discuss a simple algorithmic stock picking approach based on momentum and volatility. The goal will be to generate excess returns versus a capital weighted stock basket.

Alpha and Beta

Investing in assets with low volatility and high return is on a lot of peoples wish list. Portfolios which archive this goal will have a high Sharpe ratio and in the end get the investors money. By reverse engineering this criteria, one can find promising stocks to invest in and out perform a given capital weighted index.

Alpha and beta are measures to describe an assets performance relative to its index. Both are used in the CAPM – capital asset pricing model.

Alpha is a measure for an assets excess return compared to an index. Continue reading

NASDAQ 100 long term candlestick scanner

A short update on the long term Candlestick Scanner.

The Candlestick Scanner scans the Nasdaq 100 stocks for long term bullish or bearish reversal patterns.

The basic idea is to search for hammer and hanging man candlestick patterns. Usually these patterns work nicely on daily charts. My Candlestick Scanner searches for these two patterns on every time frame, from a 1 day per bar compression up to a  250 days per bar compression. This enables me to use a simple, well defined and documented pattern as a description of short to long term reversal setups.

But see for yourself which Nasdaq stocks seem to change the direction according to the long term Candlestick Scan. The list gives you the duration of the reversal formation (expect about the same time to either reach the target or get stopped out) The detected pattern becomes a valid entry signal if a new high (hammer) or low (hanging man) is established.

Bullish reversals on the left side, bearish reversals on the right side.

read more about how to detect your own chart pattern in this article

Position sizing – the easy way to great performance

Working on your position sizing algorithm is an easy way to pimp an existing trading strategy. Today we have a look at an energy trading strategy and how the position sizing can influence the performance of the strategy.

The screenshot shows you the returns of the same trading strategy, trading the same markets, the same time frames and using the same parameters. The returns on the left side look nice, making money every year. The returns on the right side are somehow shaky, and you would have to love volatility of returns if you would think about trading this basket. The only difference between the basket on the right and on the left side is the position sizing.

The energy basket:

The basket trades German power, base and peak (yearly, quarterly, monthly), coal, gas, emissions. All instruments are traded on a daily and weekly time frame chart, using the same parameters. If the daily trading uses a 10-period parameter, the weekly trading would use a 10-week parameter. This limits the degrees of freedom I have when doing the strategy-time frame-parameter merge, thus minimizing the curve fitting trap.

Continue reading

Opening Range Breakout

Das Opening Range Breakout System wurde im Magazin “Technical Analysis of Stocks&Commodities” im Juli 1994 besprochen, und wie es scheint, funktioniert es, zumindest ohne slippage uns Speasen, noch immer.

Ein Opening Range Breakout System von Perry Kaufmann.

Es wurde im Magazin “Technical Analysis of Stocks&Commodities” im Juli 1994 besprochen, und wie es scheint, funktioniert es noch immer. (ohne slippage) Auch Tony Crabel schrieb zu diesem Opening Breakout System im selben Magazin

Das System wartet die erste Handelsstunde ab und geht dann bei Erreichen eines neuen Hochs oder Tiefs  long oder short.  Die Einstiegs Order (Stop Buy / Stop Sell) wird nicht exakt auf das Hoch / Tief gelegt, sondern ein paar Punkte darüber /darunter. (hier 20 Ticks)

Tradesignal Programmierung des Opening Range Systems

Durch das laden von drei Zeitreihen, 10min, Stunden- und Tagesdaten gestaltet sich die Programmierung sehr einfach. Dies schränkt jedoch die Flexibilität deutlich ein.

Prinzipiell ist die Strategie der Afternoon Trader Strategie sehr ähnlich, sie weist auch mehr Flexibilität in der Programmierung auf. Auch der Artikel über Range Breaks im intraday Markt basiert auf einer ähnlichen Idee.

TSM(S) 1st hour breakout detail

Da die hier vorgestellte Systemversion  ursprünglich für dieTradestation 2000i in Easy Language geschrieben wurde, ist das Laden von 3 Zeitreihen ein wenig kompliziert gelöst. Aber es funktioniert.

Strategie Backtest mit adjustiertem DAX Future:

TSM(S) 1st hour breakout backtest

zum Opening Range Tradesignal Equilla Code Passwort “code”

Selbstlernende Handelssysteme

Ein jeder kennt die klassischen Indikatoren wie RSI oder Stochastic. Und ein jeder kennt die dazugehörigen Handelsanweisungen: Long, wenn überverkauft, Short wenn überkauft. Und zumindest im Lehrbuch funktioniert das auch. Aber wie sieht das ganze am realen Chart aus? Würden Sie dem Lehrbuch vertrauen und Ihren Kunden auch einen baldigen Kauf empfehlen wenn der RSI unter 20 liegt?

Testen anstatt zu studieren

Schön, wenn ein Indikator im Lehrbuch funktioniert, doch will ich hier ein Verfahren darstellen, bei dem der Indikator selbst angibt ob, wann und wie gut er funktioniert! Dazu habe ich mir für diesen Beitrag den RSI Indikator vorgenommen.

Zunächst wird der Wert des Indikators betrachtet, sowie, ob er steigt oder fällt. Mit diesen beiden Kriterien lässt sich der RSI einfach klassifizieren.

RSI Prognose

Dann erfolgt der eigentliche Backtest: Innerhalb der letzten 1000 Bars wird nun geschaut, wie sich der Markt bei einem gleichen Indikatorstand (zwischen 90 und 100) und Richtung (über Triggerlinie) verhalten hat.


Am Bild kam dies innerhalb der letzten 100 bars 36 mal vor. Dabei war die durchschnittliche Bewegung innerhalb der darauffolgenden 5 min DAX Futures Kerze -0.03%. Der RSI hat beim aktuellen Stand also eine negative Kurs Prognose.

Dass es auch nach dem nächsten bar statistisch nach unten geht, sieht man an den 5 Prognose Punkten am Chart. Sie zeigen, wie sich der Markt statistisch innerhalb der nächsten 5 Bars verhalten hat, unter der Bedingung, dass der RSI den aktuellen Stand und Richtung hatte.

Markt Performance als Indikator

Der obige Screenshot zeigt den Indikator und die Prognose für den kommenden bar (sowie die 4 darauf folgenden). Er zeigt jedoch nicht, wie sich diese Prognosen in der Vergangenheit verhalten haben, in welchen Bereichen der Indikator in der Vergangenheit seine höchste Aussagekraft hatte. Dies ist am nächsten Chart dargestellt.

RSI Prognose

Am Bild ist unter dem eigentlichen RSI seine aktuelle prognose für den nächsten Bar dargestellt. Um diese prognose ist ein Bollingerband gelegt, um so die Bereiche zu definieren, an welchen der RSI seine höchste Aussagekraft hat (= die stärkste Bewegung vorhersagt)

Continue reading

Reality vs. Robert W. Colby, CMT

Dont`t believe!

Papier ist geduldig, darum ist es oft besser wenn man selbst testet bevor man ein veröffentlichtes Handelssystem mit seinem Geld ausprobiert. Heute geht es hier um einen Handelssystem out of sample Test

Ein schönes Beispiel dafür ist eine Strategie aus Robert Colbys Buch “The Encyclopedia of Technical Market Indicators“, 2nd edition, 2003, page 791ff.

Darin wird ein einfaches moving average crossover Systeme vorgestellt, welches anscheinend seit beinahe 100 Jahren phänomenale Gewinne verspricht.

Hier eine Kopie aus dem Buch:

colby wma strategy


Tradesignal Backtest

Continue reading