New Algotrading Platform

Fig1

 

Systematic Strategies is pleased to announce the launch of its new Algo Trading Platform.  This will allow subscribers to follow a selection of our best strategies in equities, futures and options, for a low monthly subscription fee.

There is no minimum account size, and accounts of up to $250,000 can be traded on the platform.

The strategies are fully systematic and trades are executed automatically in your existing brokerage account, or you can open an account at one of our supported brokers, which include  Interactive Brokers, NinjaTrader, CQG, Gain Capital, AMP, Garwood, and many others.

 

Fig2

 

 

Find Strategies

Short LineFig3

 

Find Strategies

 

Short Line

FAQ1 FAQ2

 

More

 

Short Line

SYSTEMATIC STRATEGIES LLC

Systematic Strategies is an alternative investments firm utilizing quantitative modeling techniques to develop profitable trading strategies for deployment into global markets. Systematic Strategies seeks qualified investors as defined in Regulation D of the Securities Act of 1933. For information please contact us at info@ systematic-strategies.com or visit www.systematic-strategies.com.

 

RISK DISCLOSURE

This web site and the information contained herein is not and must not be construed as an offer to sell securities. Certain statements included in this web site, including, without limitation, statements regarding investment goals, strategies, and statements as to the manager’s expectations or opinions are forward-looking statements within the meaning of Section 27A of the Securities Act of 1933 (the “Securities Act”) and Section 21E of the Securities Exchange Act of 1944 (the “Exchange Act”) and are subject to risks and uncertainties. The factors discussed herein could cause actual results and development to be materially different from those expressed in or implied by such forward-looking statements. Accordingly, the information in this web site cannot be construed as to be guaranteed.

A Simple Momentum Strategy

Momentum trading strategies span a diverse range of trading ideas.  Often they will use indicators to determine the recent underlying trend and try to gauge the strength of the trend using measures of the rate of change in the price of the asset.

One very simple momentum concept, a strategy in S&P500 E-Mini futures, is described in the following blog post:

http://www.quantifiedstrategies.com/buy-when-sp-500-makes-new-intraday-high/

The basic idea is to buy the S&P500 E-Mini futures when the contract makes a new intraday high.  This is subject to the qualification that the Internal Bar Strength fall below a selected threshold level.  In order words, after a period of short-term weakness – indicated by the low reading of the Internal Bar Strength – we buy when the futures recover to make a new intraday high, suggesting continued forward momentum.

IBS is quite a useful trading indicator, which you can learn more about in these posts:

http://jonathankinlay.com/2016/06/the-internal-bar-strength-indicator/

http://jonathankinlay.com/2016/06/quick-note-internal-bar-strength-stationarity/

 

I have developed a version of the intraday-high strategy, using parameters to generalize it and allow for strategy optimization.  The Easylanguage code for my version of the strategy is as follows:

Inputs:
nContracts(1),
ndaysHigh(5),
IBSlag(1),
IBStrigger(0.15);

Vars:

IBS(0.5);

If H[IBSlag] > L[IBSlag] then
Begin
IBS=(H[IBSlag]-C[IBSlag])/(H[IBSlag]-L[IBSlag]);
end;
If (IBS <= IBStrigger) and (H[0] >= Highest(High, ndaysHigh)) then
begin
Buy nContracts contracts this bar on close;
end;

If C[0] > H[1] then
begin
Sell all contracts this bar on close;
end;

The performance results for the strategy appear quite promising, despite the downturn in strategy profitability in 2018 to date (all performance results are net of slippage and commission):

 

Fig1 Fig3

Fig2

 

SSALGOTRADING AD

Robustness Testing with Walk Forward Optimization

We evaluate the robustness of the strategy using the  Walk Forward Optimization feature in Tradestation.  Walk forward analysis is the process of optimizing a trading system using a limited set of parameters, and then testing the best optimized parameter set on out-of-sample data. This process is similar to how a trader would use an automated trading system in real live trading. The in-sample time window is shifted forward by the period covered by the out-of-sample test, and the process is repeated. At the end of the test, all of the recorded results are used to assess the trading strategy.

In other words, walk forward analysis does optimization on a training set; tests on a period after the set and then rolls it all forward and repeats the process. This gives a larger out-of-sample period and allows the system developer to see how stable the system is over time.

The  image below illustrates the walk forward analysis procedure. An optimization is performed over a longer period (the in-sample data), and then the optimized parameter set is tested over a subsequent shorter period (the out-of-sample data). The optimization and testing periods are shifted forward, and the process is repeated until a suitable sample size is achieved.

 

WFO

 

Tradestation enables the user to run a battery of WFO tests, using different size in-sample and out-of-sample sizes and number of runs.  The outcome of each test is evaluated on several specific criteria such as the net profit and drawdown and only if the system meets all of the criteria is the test designated as a “Pass”.  This gives the analyst a clear sense of the robustness of his strategy across multiple periods and sample sizes.

A WFO cluster analysis summary for the momentum strategy is illustrated below.  The cluster test is designated as “Failed” overall, since the strategy failed to meet the test criteria for a preponderance of the individual walk-forward tests.  The optimal parameters found in each test vary considerably over the sample periods spanning 2003-2018, giving concerns about the robustness of the strategy under changing market conditions.

Fig4

 

Improving the Strategy

We can improve both the performance and robustness of our simple momentum strategy by combining it with several other trend and momentum indicators. One such example is illustrated in the performance charts and tables below.  The strategy has performed well in both bull and bear markets and in both normal and volatile market conditions:

 

Fig5 Fig6

Fig7

A WFO cluster analysis indicates that the revised momentum strategy is highly robust to the choice of sample size and strategy parameters, as it passes every test in the 30-cell WFO analysis cluster table:

Fig8

 

Conclusion

Momentum strategies are well known and easy to develop using standard methodologies, such as the simple indicators used in this example. They tend to work well in most equity index futures markets, and in some commodity markets too.  One of their big drawbacks, however, is that they typically go through periods of poor performance and need to be tested thoroughly for robustness in order to ensure satisfactory results under the full range of market conditions.

Finding Alpha in 2018

Given the current macro-economic environment, where should investors focus their search for sources of alpha in the year ahead?  By asking enough economists or investment managers you will find as many different opinions on the subject as would care to, no doubt many of them conflicting.  These are some thoughts on the subject from my perspective, as a quantitative hedge fund manager.

SSALGOTRADING AD

Global Market Performance in 2017

Let’s begin by reviewing some of the best and worst performing assets of 2017 (I am going to exclude cryptocurrencies from the ensuing discussion).  Broadly speaking, the story across the piste has been one of strong appreciation in emerging markets, both in equities and currencies, especially in several of the Eastern European economies.  In Government bond markets Greece has been the star of the show, having stepped back from the brink of the economic abyss.  Overall, international diversification has been a key to investment success in 2017 and I believe that pattern will hold in 2018.

BestWorstEquityMkts2017

BestWorstCurrencies2017

BestWorstGvtBond

 

US Yield Curve and Its Implications

Another key development that investors need to take account of is the extraordinary degree of flattening of the yield curve in US fixed income over the course of 2017:

YieldCurve

 

This process has now likely reached the end point and will begin to reverse as the Fed and other central banks in developed economies start raising rates.  In 2018 investors should seek to protect their fixed income portfolios by shortening duration, moving towards the front end of the curve.

US Volatility and Equity Markets

A prominent feature of US markets during 2017 has been the continuing collapse of equity index volatility, specifically the VIX Index, which reached an all-time low of 9.14 in November and continues to languish at less than half the average level of the last decade:

VIX Index

Source: Wolfram Alpha

One consequence of the long term decline in volatility has been to drastically reduce the profitability of derivatives markets, for both traders and market makers. Firms have struggled to keep up with the high cost of technology and the expense of being connected to the fragmented U.S. options market, which is spread across 15 exchanges. Earlier in 2017, Interactive Brokers Group Inc. sold its Timber Hill options market-making unit — a pioneer of electronic trading — to Two Sigma Securities.   Then, in November, Goldman Sachs announced it was shuttering its option market making business in US exchanges, citing high costs, sluggish volume and low volatility.

The impact has likewise been felt by volatility strategies, which performed well in 2015 and 2016, only to see returns decline substantially in 2017.  Our own Systematic Volatility strategy, for example, finished the year up only 8.08%, having produced over 28% in the prior year.

One side-effect of low levels of index volatility has been a fall in stock return correlations, and, conversely, a rise in the dispersion of stock returns.   It turns out that index volatility and stock correlation are themselves correlated and indeed, cointegrated:

http://jonathankinlay.com/2017/08/correlation-cointegration/

 

In simple terms, stocks have a tendency to disperse more widely around an increasingly sluggish index.  The “kinetic energy” of markets has to disperse somewhere and if movements in the index are muted then relative movement in individual equity returns will become more accentuated.  This is an environment that ought to favor stock picking and both equity long/short and market neutral strategies  should outperform.  This certainly proved to be the case for our Quantitative Equity long/short strategy, which produced a net return of 17.79% in 2017, but with an annual volatility of under 5%:

QE Perf

 

Looking ahead to 2018, I expect index volatility and equity correlations rise as  the yield curve begins to steepen, producing better opportunities for volatility strategies.  Returns from equity long/short and market neutral strategies may moderate a little as dispersion diminishes.

Futures Markets

Big increases in commodity prices and dispersion levels also lead to improvements in the performance of many CTA strategies in 2017. In the low frequency space our Futures WealthBuilder strategy produced a net return of 13.02% in 2017, with a Sharpe Ratio above 3 (CAGR from inception in 2013 is now at 20.53%, with an average annual standard deviation of 6.36%).  The star performer, however, was our High Frequency Futures strategy.  Since launch in March 2017 this has produce a net return of 32.72%, with an annual standard deviation of 5.02%, on track to generate an annual Sharpe Ratio above 8 :

HFT Perf

Looking ahead, the World Bank has forecast an increase of around 4% in energy prices during 2018, with smaller increases in the price of agricultural products.   This is likely to be helpful to many CTA strategies, which will likely see further enhancements in performance over the course of the year.  Higher frequency strategies are more dependent on commodity market volatility, which is seen more likely to rise than fall in the year ahead.

Conclusion

US fixed income investors are likely to want to shorten duration as the yield curve begins to steepen in 2018, bringing with it higher levels of index volatility that will favor equity high frequency and volatility strategies.  As in 2017, there is likely much benefit to be gained in diversifying across international equity and currency markets.  Strengthening energy prices are likely to sustain higher rates of return in futures strategies during the coming year.

Trading Bitcoin

At Systematic Strategies we have developed a brilliant, new investment strategy.  We call it buying Bitcoin.  It works like this:  you take some of your hard-earned fiat and use it to buy Bitcoin.  Then, a week or two later, you do the same thing all over again.   So far the strategy is up around 400% YTD.  Genius.

It’s such a successful strategy that we are tempted to clone it.  Buying Litecoin, or Ethereum, spring to mind.

As freshly-minted, bona-fide cryptocurrency entrepreneurs, it is perhaps timely to ponder the roots of this success story and share our discoveries with other, perhaps more rational investors, who may be inclined to treat the whole cryptocurrency malarky as a tulip-Ponzi scheme.  First, there is a back-story to this.  During tulipmaniathe mid 1990’s I was teaching computational finance at Carnegie Mellon to some very bright students who were, naturally enough, playing the market on the side.  This was the time of the internet boom with tech stocks like Amazon, Ebay, Sun Microsystems, et al, leading the charge to ever higher levels in the market.  The multiples that some of these stocks were trading at were truly astonishing.  I had seen something similar just before the crash in the Japanese market towards the end of the 1980’s, when stocks were trading at three-figure multiples.  So by around 1997/98 I was becoming increasingly nervous that the tech boom might be at the point of imminent collapse.  I conveyed these sentiments to my students, expressing concern that they should not over-commit themselves to what might turn out to be a bubble.  My advice was roundly ignored and for the next couple of years I suffered the almost daily humiliation of watching the market indices reach even higher levels, to the joy of dot com investors.  When the crash came many lost most, if not all, of their investment.  It was like a funeral in the Hamptons that summer. Teary-eyed students asked me for advice as to what they should do to salvage what was left of their investment nest egg.  I didn’t have the stomach for gloating.  The only piece of advice I could think to offer them was:  “learn”.  I hope they did.  Because here we are again.

SSALGOTRADING AD

What concerned me back in ’98 was not that I didn’t understand the importance of the new internet paradigm:  on the contrary, I was an early adopter of the new technologies.  I fully understood the potential benefits that a digital business like Amazon enjoyed versus bricks and mortar rivals.  But it’s also the case that I under-estimated the potential of a company like Amazon, in several important ways.  For instance, I did not foresee how useful and important customer reviews would become (facilitated by the digital medium); nor did I anticipate Amazon being as successful as it has been in broadening the scope of its services from books (then) to just about everything (now); and I also under-estimated the challenge that the new entrants would pose to traditional rivals, who struggled (and often failed) to adapt their hitherto successful business strategies.  In other words, my concern didn’t stem from a lack of appreciation of the potential of the new tech  companies, although I certainly under-estimated that potential in some cases.  Rather, my thinking was that it had gone too far, too fast and that the blistering pace of the market melt-up would inevitably slow.  I was right, but way too early.  It is notoriously difficult to get the timing of the bubble-popping right, even if the call is correct.

Bitcoin Chart

 

Chaotic trading marks new surge in bitcoin price

In one wild 20 minute period, the price of bitcoin soared $2,000 per coin to more than $19,000 only to drop to $15,000 on the Coinbase trading venue.  – Financial Times, Dec 8th, 2017

 

 

 

 

So to Bitcoin, which is undergoing a similar melt-up.  Again, the rationale for the popularity of cryptocurrencies is not hard to fathom, given all the central bank shenanigans of the last decade and the poor reputation that several major banks have earned as serial manipulators of markets in fiat currency substitutes, like gold, or silver.  Once again, it appears to me, the entities whose well established business models are most threatened by the arrival of cryptocurrencies have been slow on the uptake and most, like JP Morgan, for instance, are still in denial.  The chief threat from cryptocurrencies lies in their potential to dis-intermediate the banks, by allowing users to transact directly with one another, and also Governments, who stand to lose considerable sums in tax revenue.  No doubt they will eventually wake up to the scale of threat that Bitcoin poses and respond accordingly in due course – i.e. expect an avalanche of new regulation and government propaganda seeking to equate ownership of Bitcoin with “money laundering”, whatever that preposterous phrase might actually mean. I am not convinced that the genie can be stuffed back into the bottle so easily.

Given the value and scale of the market that cryptocurrencies are in the process of disrupting, i.e. global banking and taxation, the upside potential is indeed enormous. I fully expect the surge to continue for some time.  But we can expect a great deal of volatility and several corrections of 20%, or more, along the way.  The first of these might arrive next week, as Bitcoin futures start trading, enabling speculators to initiate short positions against the cryptocurrency.  Other adverse events are likely to include increased scrutiny by government agencies like the IRS and market regulators like the SEC, although it remains to be seen how effectively they are able to operate in this sphere.

Bitcoin-trading

So, with all that said, here are some thoughts on how to play the market, if you must:

  1.  Check out this useful Beginner’s Guide to Trading Bitcoin
  2. Invest no more than 10% to 20% of your net worth.  Losing this will hurt, but not kill you.  Yes, you probably won’t become a Bitcoin billionaire, but neither will you end up in the poor house.  Do not, under any circumstances, sell all your assets and plunge in.  If you lose your home and the college fund, your wife and kids will never forgive you.
  3. Wait to see if we get a decent pullback after futures trading starts before you buy (more).  If that doesn’t happen, it’s up to you to decide whether  you want to wait it out or get aboard the train immediately.  There is no right answer.  At some point you are going to lose at least 20% of the value of your investment.  It could be on day one, or six months from now.  There is no way to know.
  4. I have read a few articles by traders threatening to short the heck out of the futures market as soon as it opens.  For some of them this appears to be revenge for having missed a golden opportunity to buy Bitcoin when it was worth a fraction of the price it trades at today.  Please don’t do this.  It will be like trying to stop a freight train with your hand.   You might get lucky, once or twice, but sooner or later you are going to get run over.  And it will hurt a lot.
  5. If you want to trade the short side, or trade the long side more conservatively, consider a pairs trade.  By this I mean, for instance, if you do decide to sell Bitcoin futures, consider hedging the position by buying another cryptocurrency like Ethereum or Litecoin.  For a detailed description of how to approach this in a more sophisticated way, see these posts:

http://jonathankinlay.com/2017/03/pairs-trading-copulas/

 

http://jonathankinlay.com/2015/02/developing-statistical-arbitrage-strategies-using-cointegration/

DISCLAIMER

As always, readers are entirely responsible for making their own investment decisions and for any and all consequences arising from them.  The author bears no responsibility for any action or decision taken, or not taken, by any investor pursuant to this or other articles and disclaims any responsibility for investment decisions taken by readers of this blog.

Systematic Futures Trading

In its proprietary trading, Systematic Strategies primary focus in on equity and volatility strategies, both low and high frequency. In futures, the emphasis is on high frequency trading, although we also run one or two lower frequency strategies that have higher capacity, such as the Futures WealthBuilder. The version of WealthBuilder running on the Collective 2 site has performed very well in 2017, with net returns of 30% and a Sharpe Ratio of 3.4:

Futures C2 oct 2017

 

In the high frequency space, our focus is on strategies with very high Sharpe Ratios and low drawdowns. We trade a range of futures products, including equity, fixed income, metals and energy markets. Despite the current low levels of market volatility, these strategies have performed well in 2017:

HFT Futures Oct 2017 (NFA)

Building high frequency strategies with double-digit Sharpe Ratios requires a synergy of computational capability and modeling know-how. The microstructure of futures markets is, of course, substantially different to that of equity or forex markets and the components of the model that include microstructure effects vary widely from one product to another. There can be substantial variations too in the way that time is handled in the model – whether as discrete or continuous “wall time”, in trade time, or some other measure. But some of the simple technical indicators we use – moving averages, for example – are common to many models across different products and markets. Machine learning plays a role in most of our trading strategies, including high frequency.

Here are some relevant blog posts that you may find interesting:

http://jonathankinlay.com/2016/04/high-frequency-trading-equities-vs-futures/

 

http://jonathankinlay.com/2015/05/designing-scalable-futures-strategy/

 

http://jonathankinlay.com/2014/10/day-trading-system-in-vix-futures/

A Winer Process

No doubt many of you sharp-eyed readers will have spotted a spelling error, thinking I intended to refer to one of these:

Fig 1

 

But, in fact, I really did have in mind something more like this:

 

wine pour

 

We are following an example from the recently published Mathematica Beyond Mathematics by Jose Sanchez Leon, an up-to-date text that describes many of the latest features in Mathematica, illustrated with interesting applications. Sanchez Leon shows how Mathematica’s machine learning capabilities can be applied to the craft of wine-making.

SSALGOTRADING AD

We begin by loading a curated Wolfram dataset comprising measurements of the physical properties and quality of wines:

Fig 2

A Machine Learning Prediction Model for Wine Quality

We’re going to apply Mathematica’s built-in machine learning algorithms to train a predictor of wine quality, using the training dataset. Mathematica determines that the most effective machine learning technique in this case is Random Forest and after a few seconds produces the predictor function:

Fig 3

 

Mathematica automatically selects what it considers to be the best performing model from several available machine learning algorithms:

machine learning methods

Let’s take a look at how well the predictor perform on the test dataset of 1,298 wines:

Fig 4

We can use the predictor function to predict the quality of an unknown wine, based on its physical properties:

Fig 5

Next we create a function to predict the quality of an unknown wine as a function of just two of its characteristics, its pH and alcohol level.  The analysis suggests that the quality of our unknown wine could be improved by increasing both its pH and alcohol content:

Fig 6

Applications and Examples

This simple toy example illustrates how straightforward it is to deploy machine learning techniques in Mathematica.  Machine Learning and Neural Networks became a major focus for Wolfram Research in version 10, and the software’s capabilities have been significantly enhanced in version 11, with several applications such as text and sentiment analysis that have direct relevance to trading system development:

Fig 7

For other detailed examples see:

http://jonathankinlay.com/2016/08/machine-learning-model-spy/

http://jonathankinlay.com/2016/11/trading-market-sentiment/

 

http://jonathankinlay.com/2016/08/dynamic-time-warping/