Momentum Strategies: A Mass Review

As a devout mean-reversion trader, I detect Mike Dever's novel majority "Jackass Investing" unexpectedly well-argued in addition to readable.

You see, momentum in addition to mean-reversion traders alive inwards 2 split upwardly universes, in addition to they are oftentimes mutually incomprehensible to each other. Dever, every bit a CTA, inhabits the momentum universe. Example: my favorite functioning measure, the Sharpe ratio, has been brusquely dispatched every bit a bad standard of risk, in addition to drawdown becomes king. But all for skillful reasons: Dever argues that Sharpe ratio measures solely the daily volatility of returns, only disregarded the "black swan" events, which are much amend captured yesteryear the maximum drawdown. I handgrip alongside the writer on this point, only at that spot are other uses of Sharpe ratio: a high Sharpe ratio strategy does signal high statistical significance of the trading strategy, a claim that momentum strategies tin seldom make. I oftentimes scream upwardly of momentum strategies every bit beingness long options: you lot cause got to proceed paying premium until 1 day, you lot brand them all dorsum alongside a dwelling run. But when you lot are backtesting a strategy, how would you lot know that the rare, statistically insignificant, dwelling run was non due to information snooping bias? Unless of course, similar the author, you lot cause got key insights into the traded instruments.

Fundamental insights are inwards fact 1 of the delicious highlights of this book. Dever describes his orangish juice futures strategy using the "marginal cost of production" every bit a key valuation tool. He argues that orangish juice cannot live on sold below this cost, since farmers would cause got no incentive for production otherwise. And he was right: orangish juice futures started to rebound from the 27-year depression of 55 cents/pound inwards May 2004, to almost xc cents/pound inwards September (thanks partly to hurricanes hitting Florida). Dever went long at lxx cents. Oh, how nosotros quantitative traders would beloved to cause got the confidence that such insights inspire!

Of course, I don't handgrip alongside everything written inwards the book. For example, though the writer rightly pointed out that the distribution of returns oftentimes cause got a positive kurtosis, he uses that every bit bear witness of trending behavior. While I handgrip that toll trends tin indeed arrive at positive kurtosis, nosotros tin surely fix mean-reverting toll serial alongside occasional catastrophes that cause got the same kurtosis. To us mean-reversion traders, positive kurtosis is non an invitation to "follow-the-trend", only every bit a alarm sign to detect run a endangerment management measures that protect us from catastrophes. 

Even though momentum strategies inwards full general are inwards a acre of trauma correct directly (more on that later), Dever notwithstanding makes a skillful representative why nosotros should include them every bit piece of occupation of our portfolio of strategies. Comparing the S&P500 index (SPX) alongside the S&P Diversifed Trends Indicator (DTI, a unproblematic trend-following strategies on 24 futures), he finds that the Sharpe ratio (though of course of report he refuses to utilisation that hated term) of the DTI is to a greater extent than than double that of the SPX, alongside solely virtually 1/3 of the maximum drawdown. But earlier you, the reader, decides to bring together the momentum bandwagon, I invite you lot to cause got a aspect at a plot of DTI's values since inception:

S&P DTI index

Since its high watermark inwards 2008/12/5, this representative momentum strategy has been inwards a relentless drawdown. Why? This is due to to a greater extent than or less other well-studied in addition to troubling property of momentum strategies: they ever performed poorly for several years after a fiscal crisis.

Are Quant Strategies Inward Problem All The Same Again?

There were reports that quant strategies convey been suffering 1 time again inward January, given the marketplace set turmoil generated partly past times the Societe Generale scandal. Mr. Matthew Rothman of Lehman Brothers pinned the blame on momentum strategies (Hat tip: previous post, Dec has been a disastrous calendar month for value (or mean-reverting) strategies, based on both populace commentaries in addition to personal experience. Yet, every bit always, mean-reverting strategies bounced dorsum inward Jan in addition to all the hurting is gone. In fact, the Societe Generale scandal in addition to the subsequent 1/22 Fed bailout has been a huge bonanza to mean-reversion traders, but similar the August disaster had been. (Remember: mean-reversion traders net turn a profit from providing liquidity during marketplace set panic.) Meanwhile, though Dec has been a skilful calendar month for momentum strategies, Jan has acquire increasingly inhospitable to them. But 1 should non live on surprised at all. As I convey explained before, momentum strategies by in addition to large tend to live on to a greater extent than unstable in addition to convey lower Sharpe ratios than reversal strategies. Any wise quantitative portfolio managers would ever allocate a lower proportion of working capital missive of the alphabet to momentum strategies than to reversal strategies. Hence it is no excuse at all to say that a quant portfolio has been wound past times losses inward momentum trading -- they are to live on expected quite frequently!

Momentum Strategies Inwards Futures Together With Forex

I bring long establish that it is easier to uncovering practiced (i.e. high Sharpe ratio) mean-reverting strategies than practiced momentum strategies. Partly, that is because I was mainly a stock trader instead of a futures/currencies trader, in addition to private stocks mean-revert most of the time. There are exceptions, such every bit later on special corporate events such every bit earnings announcements, in addition to I bring tested momentum strategies based on these events. But the success of fifty-fifty these event-driven strategies has been uneven, specially since to a greater extent than traders larn aware of them.

Now that I am focusing to a greater extent than on trading futures in addition to currencies, I bring gradually been introduced to the basis of momentum investing. There is a practiced mass inward this expanse that deserves to last improve known: Joe Duffy's The Ultimate Trading Robot, which is an nearly step-by-step direct to constructing futures trending strategies that rely on prices alone. Another instance would last the London Breakout strategy mentioned past times our reader Bernd inward the comments here. After studying these examples, I realized why my previous, rather desultory, search for momentum strategies inward the futures in addition to FX markets had been inward vain: the overnight gap inward these markets seems critical. For futures, the overnight gap is obvious, simply inward the instance of the London Breakout strategy, for example, the trader has the chore defining for herself what the optimal closing in addition to opening times are inward club to compute the gap. Intraday tendency without an overnight breakout does non appear persistent plenty to last traded profitably. I likewise wonder if at that topographic point is a to a greater extent than elegant (i.e. mathematical) style to quantify such breakout phenomena without using the traditional technical indicators.

If yous know of ideas for practiced momentum strategies, yous are most welcome to portion in addition to hash out them here!

Looking For Momentum? Banking Concern Lucifer Exterior The Us

Momentum vs. mean-reversion has been a perennial subject inward investing, non to the lowest degree quantitative investing. My disceptation has ever been that momentum strategies are by together with large less reliable than mean-reversal strategies. (See here or here.) My reader Mr. J. Rigg told me virtually a recent article inward the Financial Times suggesting that momentum strategies are hold out together with well, according to the research yesteryear Prof. Elroy Dimson et al at the London Business School. The strategy is really simple: purchase the stocks amongst the highest returns in, say, the terminal 12 months, brusk the ones amongst the lowest returns, together with concur for, say, 1 month. If y'all run this strategy for the summit 100 Great Britain stocks from 1900 to 2007, the average annualized homecoming earlier costs is virtually 10%.

There are, however, a publish of caveats worth noting inward this study:

First, it is really transaction-costly to implement momentum strategies for small-scale or fifty-fifty mid-cap stocks. If y'all element inward costs, 10% tin easily move 5% -- non an impressive publish fifty-fifty for a dollar-neutral strategy. (Though i should complaint that the infrequent rebalancing renders transaction costs consideration less important.)

Second, the drawdown durations are quite lengthy -- sometimes exceeding two years. This is non acceptable functioning for many hedge funds. Such lengthy drawdowns induce got been a mutual characteristic of many momentum strategies that I induce got personally studied together with traded.

Third, together with most interestingly, inward the menstruum 2001-2007, this momentum strategy has stopped working altogether for the U.S.A. market, acre continuing to deliver positive returns inward other markets!

What may hold out the argue for this dichotomy betwixt U.S.A. together with international markets? Momentum strategies by together with large derive their ability from the dull diffusion together with analysis of information: if all investors are simultaneously aware of all the relevant fiscal data virtually a companionship together with tin analyze the significance of the data instantaneously, they volition induce got come upwards to a consensus fair marketplace position value instantaneously together with no momentum inward the cost volition result. Hence mayhap the disappearance of momentum inward the U.S.A. equity marketplace position way what most people know already: that it is the most efficient equity marketplace position of all.

What Tin Quant Traders Larn From Taleb's Antifragile?

It tin dismiss appear a flake ironic that nosotros should live on discussing Nassim Taleb's best-seller "Antifragile" here, since around algorithmic trading strategies involve predictions as well as won't live on met alongside blessing from Taleb. Predictions, equally Taleb would say, are "fragile" -- they are prone to diverse biases (e.g. information snooping bias) as well as the occasional Black Swan consequence volition wipe out the small-scale cumulative profits from many right bets. Nevertheless, underneath the heap of diatribes against diverse luminaries ranging from Robert Merton to Paul Krugman, nosotros tin dismiss observe a few gems. Let me start from the obvious to the subtle:

1) Momentum strategies are to a greater extent than antifragile than mean-reversion strategies.

Taleb didn't tell that, but that's the starting fourth dimension idea that came to my mind. As I argued inwards many places, hateful reverting strategies receive got natural lucre caps (exit when toll has reverted to mean) but no natural halt losses (we should purchase to a greater extent than of something if it gets cheaper), then it is real much plain of report to left tail risk, but cannot accept payoff of the unexpected skilful fortune of the right tail. Very frail indeed! On the contrary, momentum strategies receive got natural halt losses (exit when momentum reverses) as well as no natural lucre caps (keep same seat equally long equally momentum persists). Generally, real antifragile! Except: what if during a trading halt (due to the daily overnight gap, or circuit breakers), nosotros can't move out a momentum seat inwards time? Well, you lot tin dismiss ever purchase an pick to copy a halt loss. Taleb would sure enough approve of that.

2) High frequency strategies are to a greater extent than antifragile than depression frequency strategies.

Taleb equally good didn't tell that, as well as it has zippo to produce alongside whether it is easier to predict short-term vs. long-term returns. Since HF strategies let us to accumulate profits much faster than depression frequency ones, nosotros withdraw non apply whatever leverage. So fifty-fifty when nosotros are unlucky plenty to live on asset a seat of the incorrect sign when a Black Swan hits, the harm volition live on small-scale compared to the cumulative profits. So spell HF strategies produce non precisely produce goodness from right tail risk, they are at to the lowest degree robust alongside observe to left tail risk.

3) Parameter estimation errors as well as vulnerability to them should live on explicitly incorporated inwards a backtest functioning measurement.

Suppose your trading model has a few parameters which you lot estimated/optimized using about historical information set. Based on these optimized parameters, you lot compute the Sharpe ratio of your model on this same data. No uncertainty this Sharpe ratio volition live on real good, due to the in-sample optimization. If you lot apply this model alongside those optimized the parameters on out-of-sample data, you lot would in all probability acquire a worse Sharpe ratio which is to a greater extent than predictive. But why halt at but ii information sets? We tin dismiss observe northward unlike information sets of the same size, calculate the optimized parameters on each of them, but compute the Sharpe ratios over the N-1 out-of-sample information sets. Finally, you lot tin dismiss average over all these Sharpe ratios. If your trading model is fragile, you lot volition observe that this Sharpe ratio is quite low. But to a greater extent than of import than Sharpe ratios, you lot should compute the maximum drawdown based on each laid of parameters, as well as equally good the maximum of all these max drawdowns. If your trading model is fragile, this maximum of maximum drawdowns is probable to live on quite scary.

The scheme I described higher upwards is called cross-validation as well as is well-known earlier Taleb, though his mass reminds me of its importance.

4) Notwithstanding 3) above, a truthful approximate of the max drawdown is impossible because it depends on the approximate of the probability of rare events. As Taleb mentioned, fifty-fifty inwards illustration of a normal distribution, if the "true" touchstone departure is higher than your approximate past times a mere 5%, the probability of a 6-sigma consequence volition live on increased past times five times over your estimate! So actually the solely means to ensure that our maximum drawdown volition non orbit a sure  limit is through Constant Proportion Portfolio Insurance: trading risky assets alongside Kelly-leverage inwards a express liability company, putting coin that you lot never desire to lose inwards a FDIC-insured bank, alongside regular withdrawals from the LLC to the depository fiscal establishment (but non the other means around).

5) Correlations are impossible to estimate/predict. The solely affair nosotros tin dismiss produce is to brusk at +1 as well as purchase at -1.

Taleb hates Markowitz portfolio optimization, as well as 1 of the reasons is that it relies on estimates of covariances of asset returns. As he said, a dyad of assets that may receive got -0.2 correlation over a long catamenia tin dismiss receive got +0.8 correlation over about other long period. This is particularly truthful inwards times of fiscal stress. I quite handgrip on this point: I believe that manually assigning correlations alongside values of  +/-0.75, +/-0.5, +/-0.25, 0 to entries of the correlation matrix based on "intuition" (fundamental knowledge) tin dismiss generate equally skilful out-of-sample functioning equally whatever meticulously estimated numbers.The to a greater extent than fascinating query is whether in that location is indeed mean-reversion of correlations. And if so, what instruments tin dismiss nosotros move to lucre from it? Perhaps this article volition help.

6) Backtest tin dismiss solely live on used to spend upwards a strategy, non to predict its success.

This echoes the indicate made past times commenter Michael Harris inwards a previous article. Since historical information volition never live on long plenty to capture all the possible Black Swan events that tin dismiss occur inwards the future, nosotros tin dismiss never know if a strategy volition neglect miserably. However, if a strategy already failed inwards a backtest, nosotros tin dismiss live on pretty sure that it volition neglect 1 time to a greater extent than inwards the future.

===

The online "Quantitative Momentum Strategies” workshop that I mentioned inwards the previous article is straightaway fully booked. Based on pop demand, I volition offering a "Mean Reversion Strategies" workshop inwards May. Once again, it volition live on conducted inwards real-time through Skype, as well as the pose out of attendees volition live on similarly express to 4. See here for to a greater extent than information.

Momentum Crash Together With Recovery

In my book I devoted considerable attending to the phenomenon of "Momentum Crashes" that professor Kent Daniel discovered. This refers to the fact that momentum strategies by in addition to large function real poorly inward the immediate aftermath of a fiscal crisis. This phenomenon obviously spans many property classes, in addition to has been to a greater extent than or less since the Great Depression.  Sometimes it lasted multiple decades, in addition to at other times these strategies recovered during the lifetime of a momentum trader. So how bring momentum strategies fared later on the 2008 fiscal crisis, in addition to bring they recovered?

First, let's hold off at the Diversified Trends Indicator (formerly the S&P DTI index), which is a fairly generic trend-following strategy applied to futures.  Here are the index values since inception (click to enlarge):

in addition to hither are the values for 2013:



After suffering relentless refuse since 2009, it has finally shown positive returns YTD!

Now hold off at a momentum strategy on the soybean futures (ZS) that I bring been working on. Here are the cumulative returns from 2009 to 2011 June:

in addition to hither the cumulative returns since then:

The deviation is stark!

Despite evidences that indeed momentum strategies bring enjoyed a full general recovery, nosotros must play the business office of skeptical fiscal scientists in addition to hold off for option theories. If whatsoever reader can tell us an alternative, plausible explanation why ZS should commencement to display trending behaviour since July 2011, precisely non before, delight ship service that inward the comment area. The prize for the best explanation: I volition expose inward mortal to a greater extent than details nearly this strategy to that reader. (To claim the prize, delight include the finally four digit of your band release inward the ship service for identification purpose.)

===
Upcoming events:

1. I volition live instruction an online workshop on Momentum Strategies from July thirty - August 1. Registration information tin ambit the sack live flora here.
2. My friend doc Haksun Li is offering a Certificate inward Quantitative Investment serial of courses.





Really, Beware Of Depression Frequency Data

I wrote inwards a previous article about why nosotros should backtest fifty-fifty end-of-day (daily) strategies amongst intraday quote data. Otherwise, the functioning of such strategies tin dismiss hold upward inflated. Here is some other vivid instance that I came across recently.

Consider the stone oil futures ETF USO together with its evil twin, the inverse stone oil futures ETF DNO*. In theory, if USO has a daily return of x%, DNO volition lead maintain a daily supply of -x%. In practice, if nosotros plot the daily returns of DNO against that of USO from 2010/9/27-2016/9/9, using the commons consolidated end-of-day information that yous tin dismiss detect on Yahoo! Finance or whatever other vendor,

nosotros meet that though the gradient is indeed -1 (to inside a touchstone fault of 0.004), in that location are many days amongst pregnant divergence from the direct line. The trader inwards us volition right away retrieve "arbitrage opportunities!"

Indeed, if nosotros backtest a uncomplicated hateful reversion strategy on this couplet - simply purchase equal dollar amount of USO together with DNO when the amount of their daily returns is less than forty bps at the marketplace close, concur 1 day, together with vice versa - nosotros volition detect a strategy amongst a decent Sharpe ratio of 1 fifty-fifty afterwards deducting v bps per side every bit transaction costs. Here is the equity curve:

Looks reasonable, doesn't it? However, if nosotros backtest this strategy 1 time again amongst BBO information at the marketplace close, taking assist to subtract one-half the bid-ask spread every bit transaction cost, nosotros detect this equity curve:

We tin dismiss meet that the occupation is non exclusively that nosotros lose coin on practically every trade, but that in that location was seldom whatever merchandise triggered. When the daily EOD information suggests a merchandise should hold upward triggered, the 1-min bar BBO information tells us that inwards fact in that location was no divergence from the mean.

(By the way, the returns inwards a higher house were calculated earlier nosotros fifty-fifty deduct the borrow costs of occasionally shorting these ETFs. The "rebate rate" for USO is nearly 1% per annum on Interactive Brokers, but a steep 5.6% for DNO.)

In instance yous retrieve this occupation is peculiar to USO vs DNO, yous tin dismiss travail TBT vs UBT every bit well.

Incidentally, nosotros lead maintain simply verified a golden dominion of fiscal markets: apparent divergence from efficient marketplace is allowed when no 1 tin dismiss profitably merchandise on the arbitrage opportunity.

===
*Note: according to www.etf.com, "The issuer [of DNO] has temporarily suspended creations for this fund every bit of Mar 22, 2016 pending the filing of novel paperwork amongst the SEC. This activity could do odd or excessive premiums— an growth of the marketplace cost of the fund relative to its fair value. Redemptions are non affected. Trade amongst care; cheque iNAV vs. price." For an explanation of "creation" of ETF units, meet my article "Things You Don't Want to Know nearly ETFs together with ETNs".

===

Industry Update

• Quantiacs.com simply lately registered every bit a CTA together with operates a marketplace for trading algorithms that anyone tin dismiss contribute. They besides published an educational spider web log post for Python together with Matlab backtesters: https://quantiacs.com/Blog/Intro-to-Algorithmic-Trading-with-Heikin-Ashi.aspx

• I volition hold upward moderating a panel give-and-take on "How tin dismiss funds leverage non-traditional information sources to displace investment returns?" at Quant World Canada inwards Toronto, Nov 10, 2016. 

===

Upcoming Workshops

• October 22 together with 29, Saturdays, Quantitative Momentum Strategies online workshops. 

Momentum strategies are for those who desire to benefit from tail events. I volition hash out the substitution reasons for the beingness of momentum inwards diverse markets, every bit good every bit specific momentum strategies that concur positions from hours to days.

H5N1 senior managing director at a major depository fiscal establishment wrote me: "…thank yous 1 time again for the Momentum Strategies preparation course of report this week. It was real beneficial. I constitute your explanations of the concepts real clear together with the examples good developed. I similar the rigorous approach that yous lead maintain to strategy evaluation.”

Stop Loss, Profits Cap, Survivorship Bias, In Addition To Dark Swans

I accept long espoused the sentiment that nosotros should non impose stop-losses on mean-reverting strategies, nor profits caps on momentum strategies. My sentiment on the latter has non changed, but it has evolved on the former.

My master copy argue for opposing stop-losses on mean-reverting strategy is this. Say yous believe your specific cost serial is mean-reverting, in addition to tell yous accept entered into a long position when the cost is low. Now, however, the cost gets much lower, in addition to yous are suffering a large unrealized loss. Well, based on your mean-reverting belief, yous should purchase to a greater extent than instead of liquidating! Indeed, if yous backtest the number of stop-losses on mean-reverting strategies, yous volition close inevitably discovery that they decrease the overall returns in addition to fifty-fifty Sharpe ratios.

But what this simplistic sentiment ignored is 1) survivorship bias, in addition to 2) dark swan events. (Hat tip: Ben, who prompted me to reckon these ii issues.)

1) We unremarkably would alone merchandise those cost serial alongside a mean-reverting strategy alone if nosotros run into that the prices did eventually revert. No ane would bother to merchandise those cost serial that used to mean-revert, but all of a abrupt stopped doing so. But maxim that stop-losses are harmful to mean-reverting strategies is ignoring the fact that some mean-reverting volition halt working altogether in addition to would non live on our strategies choice process.

2) Let's define dark swan events equally those that did non travel on inward your backtest period. For example, let's tell yous never had a loss of 20% inward a unmarried day. So if yous backtest a stop-loss of 20%, it volition accept no number whatsoever on your backtest performance. However, no ane tin tell for sure that it won't travel on inward the future. So if yous or your investors exactly cannot tolerate a 20% loss, yous should impose this equally a stop-loss. (After all, your brokerage has already imposed a stop-loss of 100% on yous whether yous similar it or not.)

We tin inward fact plow betoken 2) roughly when deciding what stop-loss to use: a stop-loss should live liberate plenty in addition to then that it should accept no number on the backtest performance, in addition to of course of pedagogy tight plenty in addition to then that it volition non resultant inward the demise of your trading career.

There is too the number of whether to purpose stop-loss on the intraday drawdown, or to purpose it on the multiple-day drawdown. I would struggle that alone intraday stop-loss is of import to forestall a black-swan loss. In practice, when a strategy has a string of non-catastrophic losses occurring over multiple days, resulting inward a large, unprecedented, drawdown, the trader volition typically re-examine the strategy, taking into concern human relationship this most recent functioning in addition to tweak the strategy in addition to then that it could theoretically live avoided. This is close similar a multi-day stop-loss strategy, equally nosotros halt an old strategy in addition to showtime a new, modified, one. (Though the modified strategy mightiness soundless recommend that yous conk along asset the electrical flow position!)

Now why am I soundless asset love to the regulation that ane should non impose profit-caps on momentum strategies? Why, the possibility of dark swan events again! But this time, whatever dark swan tin alone resultant in unprecedented one-day gain instead of loss, since nosotros should always have stop-losses on momentum strategies. We for certain don't desire to impose a profit-cap to dominion out this possibility!

The Perils Of Momentum Strategies

Not as well as then long agone I was an agnostic with honour to choosing betwixt mean-reverting as well as momentum models: I felt that depending on the item model or environment, each tin live profitable. Lately, however, I am increasingly skeptical nigh the long-term profitability of momentum models. The principal ground is the increasing contest with traders, algorithmic or otherwise.

As I mentioned inward my previous post, when to a greater extent than as well as to a greater extent than traders create upwards one's psyche to adopt mean-reverting strategies, all they exercise is to eliminate the trading opportunity. The marketplace becomes efficient, as well as nobody makes whatever money, but nobody loses either. In contrast, when to a greater extent than as well as to a greater extent than traders create upwards one's psyche to adopt momentum strategies, the momentum volition live established sooner as well as sooner. For e.g. inward the instance of event-driven strategies which are mostly momentum-based, the novel equilibrium cost volition conduct keep been established almost instantaneously afterwards the number is publicly disclosed. Under this circumstance, whatever momentum trades that are entered merely a footling fleck belatedly volition non alone endure zilch profit, but volition probable endure losses equally mean-reversion almost inevitably takes over. But how before long exercise nosotros take away to motility into inward gild to avoid this fate? (It can't live likewise before long either because frequently a tendency take away to live established outset inward gild to trigger an entry signal.) It is unfortunately a moving target equally contest increases: 1 24-hour interval before mightiness move now, but may non live sufficient a few months from now. (The move out merchandise also suffers the same problem, equally nosotros don't know how long the momentum volition last.) It is a unsafe game to play.

Indeed, fourth dimension is frequently a friend of the mean-reversion trader: the longer s/he waits, mayhap the to a greater extent than profitable the trading opportunity. And if s/he enters likewise early on as well as suffers a loss, s/he tin e'er double the position. As I explained inward a previous article, stop-loss should to a greater extent than frequently than non not live applied to mean-reverting trades on a brusque time-scale. So fifty-fifty if the trader does non double-up the position, an eventual re-couping of the loss is to a greater extent than than likely. On the other hand, fourth dimension is an enemy of the momentum trader: if s/he loses the first-mover payoff as well as suffers heavy loss, I argued inward that article that a stop-loss is advised, as well as therefore the loss is forever locked-in.

Given this asymmetry, it is no wonder that algorithmic traders conduct keep been alarm me long agone that it is difficult to discovery a profitable momentum trade. And I was giddy plenty non to pay psyche to them until now.

Mean Reversion, Momentum, As Well As Volatility Term Construction

Everybody know that volatility depends on the measuring frequency: the criterion divergence of 5-minute returns is dissimilar from that of daily returns. To endure precise, if z is the log price, as well as then volatility, sampled at intervals of τ, is 

volatility(τ)=√(Var(z(t)-z(t-τ)))

where Var agency taking the variance over many sample times. If the prices actually follow a geometric random walk, as well as then Var(τ)≡Var((z(t)-z(t-τ)) ∝ τ, as well as the volatility just scales amongst the foursquare beginning of the sampling interval. This is why if nosotros mensurate daily returns, nosotros require to multiply the daily volatility by √252 to obtain the annualized volatility.

Traders too know that prices hit non actually follow a geometric random walk. If prices are hateful reverting, nosotros volition notice that they hit non wander away from their initial value every bit fast every bit a random walk. If prices are trending, they wander away faster. In general, nosotros tin terminate write

Var(τ)  ∝ τ^(2H)

where H is called the "Hurst exponent", as well as it is equal to 0.5 for a truthful geometric random walk, but volition endure less than 0.5 for hateful reverting prices, as well as greater than 0.5 for trending prices.

If nosotros annualize the volatility of a mean-reverting cost series, it volition terminate upwardly having a lower annualized volatility than that of a geometric random walk, fifty-fifty if both accept precisely the same volatility measured at, say, 5-min bars. The reverse is truthful for a trending cost series.  For example, if nosotros attempt this on AUDCAD, an plainly mean-reverting fourth dimension series, nosotros volition larn H=0.43.

All of the higher upwardly are well-known to many traders, as well as are inwards fact discussed inwards my book. But what is to a greater extent than interesting is that the Hurst exponent itself tin terminate alter at some fourth dimension scale, as well as this alter sometimes signals a shift from a hateful reversion to a momentum regime, or vice versa. To come across this, let's plot volatility (or to a greater extent than conveniently, variance) every bit a exercise of τ. This is oft called the term construction of (realized) volatility. 

Start amongst the familiar SPY. nosotros tin terminate compute the intraday returns using midprices from 1 minutes to 2^10 minutes ( 17 hrs), as well as plot the log(Var(τ)) against log(τ). The fit, shown below,  is excellent. (Click figure to enlarge). The slope, divided past times 2, is the Hurst exponent, which turns out to be 0.494±0.003, which is really slightly mean-reverting.

But if nosotros hit the same for daily returns of SPY, for intervals of 1 twenty-four hours upwardly to 2^8 (=256) days, nosotros notice that H is now 0.469±0.007, which is significantly mean reverting. 

Conclusion: hateful reversion strategies on SPY should run amend interday than intraday.

We tin terminate hit the same analysis for USO (the WTI unsmooth fossil oil futures ETF). The intraday H is 0.515±0.001, indicating pregnant trending behavior. The daily H is 0.56±0.02, fifty-fifty to a greater extent than significantly trending. So momentum strategies should run for unsmooth fossil oil futures at whatsoever reasonable fourth dimension scales.

Let's plough at nowadays to GLD, the golden ETF. Intraday H=0.505±0.002, which is slightly trending. But daily H=0.469±0.007: significantly hateful reverting! Momentum strategies on golden may run intraday, but hateful reversion strategies for certain run amend over multiple days. Where does the transition occur? We tin terminate examine the term construction closely:

We tin terminate come across that at or thence 16-32 days, the volatilities depart from immediately business extrapolated from intraday frequencies. That's where nosotros should switch from momentum to hateful reversion strategies.

One side banking concern complaint of interest: when nosotros compute the variance of returns over periods that straddle ii trading days as well as plot them every bit exercise of log(τ), should τ include the hours when the marketplace was closed? It turns out that the answer is yes, but non completely.  In fellowship to hit the nautical chart higher upwardly where the daily variances initially autumn on the same immediately business every bit the intraday variances, nosotros accept to count 1 trading twenty-four hours every bit equivalent to 10 trading hours. Not 6.5 (for the the States equities/ETF markets), as well as non 24. The precise position out of equivalent trading hours, of course, varies across dissimilar instruments.

===

Industry Update

• Nick over at mintegration.eu discusses the novel intraday databases at Quandl as well as Kerf.
• Factorwave.com (Euan Sinclair's creation) started a novel forum: slack.factorwave.com. It has some really active as well as in-depth discussions of many trading as well as investing topics.
• Prof. Matthew Lyle at Kellogg School of Management has a novel newspaper out that relates fundamentals to variance guide chances premiums: http://papers.ssrn.com/sol3/papers.cfm?abstract_id=2696183.

Upcoming Workshops

• April 20-21: Mean Reversion Strategies. 

There are a lot to a greater extent than to hateful reversion strategies than just pairs trading. Find out how to thrive inwards the electrical flow depression volatility environs favorable to this type of strategies.

Interview Alongside Euan Sinclair

I bring been a large fan of options trader too writer Euan Sinclair for a long time. I bring cited his highly readable too influential book Option Trading in my ain work, too it is ever inside slowly accomplish from my desk. His to a greater extent than recent mass Volatility Trading is some other must-read. I ran into him at the Chicago Trading Show a few months agone where he was a panelist on volatility trading, too he graciously agreed to last interviewed past times me.

What is your educational background, too how did you lot start your trading career?

I got a Ph.D. inward theoretical physics, studying the transition from quantum to classical mechanics. I ever had intended to larn a professor but the thought became less appealing ane time I saw what they did all day. At this fourth dimension Nick Leeson was making tidings past times blowing upwards Barings Bank too I thought I could produce that. I hateful merchandise derivatives non blowing upwards a depository fiscal establishment (although I could in all likelihood deal that equally well).

Do you lot recommend a novel graduate amongst a similar educational background equally yours to pursue finance or trading equally a career today?

I don't recollect I would for a few reasons.

The globe of derivatives too trading inward full general is instantly hence much to a greater extent than visible than it was too at that topographic point are instantly far improve ways to prepare. When I started, physics Ph.D.s were hired exclusively because they were smart too numerate too could pick things upwards on their own. My get-go trading trouble solid had no preparation program. You only had to figure materials out on your own. Now at that topographic point are many expert MFE courses or you lot could produce a fiscal economic science Ph.D.

Further, it would real much depend on precisely what form of physics had been studied. I did a lot of classical mechanics which is genuinely geometry. This form of "pure" theory isn't nearly equally useful equally a background heavy amongst stats or simulation.

I recollect I could all the same brand the transition, but it is no longer only about the ideal background.

You bring been a well-known options trader amongst a long rails record: what produce you lot recollect is the biggest obstruction to success for a retail options trader?

Trading costs. Most selection trading ideas are all the same built on the Black-Scholes-Merton framework too the thought of dynamic hedging (albeit heavily modified). Most pro firms bring stat arb similar execution methods to cut the effective bid-ask they pay inward the underlying. They also pay practically no ticket charges too in all likelihood larn rebates. Even then, their average turn a profit per selection merchandise is real pocket-size too has been steadily decreasing.

Further, a lot of positional selection trading relies on a large universe of possible trades to consider. This way a trader needs expert scanning software to uncovering trades, too a decent risk organization because she volition tend to bring hundreds of positions on at ane time. This is all expensive equally well. 

Retail traders can't play this game at all. They bring to expect for situations that require piffling or no rebalancing too that tin last express to a much smaller universe. I would recommend the VIX complex or equity earnings events.

As an options trader, produce you lot tend to brusk or long volatility?

I am brusk nearly 95% of the time, but nearly 35% of my profits come upwards from the long trades.

Do you lot uncovering it possible to fully automate options trading inward the same way equally that stocks, futures, too FX trading bring been automated?

I encounter no argue why not. 

You bring of late started a novel website called FactorWave.com. Can you lot order us nearly it? What prompted the transition of your focus from options to stocks?

FactorWave is a laid of stock too portfolio tools that produce analysis inward price of factors such equally value, size, character too momentum. There is a lot of inquiry past times both academics too investors that shows that these (and other) factors tin laissez passer on marketplace beating returns too lower volatility.

I've been interested inward stocks for a long time. Most of my selection sense has been amongst stock options too some of my best inquiry was on how these factors affected volatility trading returns.Also, equity markets are a cracking house to ready wealth over the long term. They are a far to a greater extent than suitable vehicle for retirement planning than options!

I genuinely recollect the distinction betwixt trading too investing is fairly meaningless. The exclusively departure seems to last the fourth dimension scale too this is real subject on the someone involved equally well, amongst long-term pregnant anything shape months to inter-generational. All I've ever done equally a trader is to expect for meaningful edges too I flora a lot of these inward options. But I've never flora anything equally persistent equally the stock factors. There is over a hundred years of statistical evidence, studies inward many countries too economical too behavioral reasons for their existence. They acquaint some of the best edges I bring ever found. That should last appealing to whatever trader or investor.

Thank you! These are genuinely valuable insights.

====

My Upcoming Workshop

Oct 28-29: Quantitative Momentum Strategies. 

Momentum strategies bring performed superbly inward the recent marketplace turmoil, since they are long volatility. This course of instruction volition embrace momentum strategies on a diversity of property classes too amongst a make of trading horizons.

====

QTS Partners, L.P. has a internet provide of 1.25% inward August (YTD: 10.44%).

====

Reader Burak B. has converted some of the Matlab codes from my mass Algorithmic Trading into Python codes too made them open-source: https://github.com/burakbayramli/quant_at.

====

Follow me on Twitter: @chanep

Nonlinear Trading Strategies

I own got long been partial to linear strategies due to their simplicity as well as relative immunity to overfitting. They tin move used quite easily to turn a profit from mean-reversion. However, at that topographic point is a serious problem: they are quite fragile, i.e. vulnerable to tail risks. As nosotros motility from mean-reverting strategies to momentum strategies, nosotros straight off innovate a nonlinearity (stop losses), simply simultaneously remove certain tail risks (except during times when markets are closed). But if nosotros desire to relish anti-fragility as well as are going to innovate nonlinearities anyway, nosotros mightiness also acquire full-monty, as well as reckon options strategies. (It is no surprise that Taleb was an options trader.)

It is slowly to encounter that options strategies are nonlinear, since options reward curves (value of an option as part of underlying stock price) are apparently nonlinear. I personally own got resisted trading them because they all look as well as so complicated, as well as I detest complexities. But lately a reader recommended a picayune mass to me: Jeff Augen's "Day Trading Options" where the Black-Scholes equation (and indeed whatever equation) is mercifully absent from the entire treatise. At the same time, it is suffused alongside qualitative ideas. Among the juicy bits:

1) We tin discovery distortions inward the 2D implied volatility surface (implied volatility equally z-axis, expiration months equally x, as well as nail prices equally y) which may hateful revert to "smoothness", thus presenting arbitrage opportunities. These distortions are introduce for both stock as well as stock index options.

2) Options are underpriced intraday as well as overpriced overnight: thus it is oft a proficient sentiment to purchase them at the marketplace seat opened upwardly as well as sell them at marketplace seat closed (except on roughly exceptional days! See iv below.). In fact, at that topographic point are certainly days of the calendar week where this distortion is the nearly drastic as well as thus favorable to this strategy.

3) Certain cash instruments own got unusually high kurtosis, simply their corresponding selection prices consistently underprice such tail risks. Thus structures such equally strangles or backspreads tin oft move profitable without incurring whatever left tail risks.

4) If at that topographic point is a long weekend earlier expiration solar daytime (e.g. Easter weekend),  the fourth dimension decay of the options value over three days is compressed into an intraday decline on the final trading solar daytime earlier the weekend.

Now, equally quantitative traders, nosotros own got no require to accept his give-and-take on whatever of these assertions. So, onward to backtesting!

(For those who may move stymied yesteryear the lack of affordable historical intraday options data, I recommend Nanex.net.)

===

There are even as well as so two slots available inward my online Mean Reversion Strategies workshop inward May. The workshop volition move conducted live via Adobe Connect, and is express to a sum of iv participants. Part of the workshop volition focus on how to avoid getting wound when a couple or a portfolio of instruments halt cointegrating.

Can A Trader Live On A Do-Gooder?

It occurs to me that the alone means inwards which a trader tin larn to a greater extent than than a completely selfish, self-enriching, narcissistic someone is to merchandise good plenty so that y'all tin care other people's coin too so saving these investors from crooks too charlatans (provided y'all are convinced y'all are non a crook too charlatan yourself).

Other traders get got advanced other arguments inwards favor of trading. But I am non convinced past times them.

They enjoin that nosotros render liquidity to other long-term investors who may quest to liquidate their investments. But then, this applies alone to mean-reversal strategies. Momentum strategies get got away liquidity from the market, too inwards or so cases exacerbating cost bubbles. Certainly non something your grandma would approve.

Others fighting that momentum strategies attention disseminate data virtually companies through quick cost movements. But can't nosotros simply lookout Bloomberg or CNBC? Do nosotros actually quest or so devious insiders to pick out that data to the residual of us through cost movements?

No, I retrieve that independent trading should serve alone i role (besides short-term self-sustenance): equally preparation too preparation to larn a fund manager. Once y'all graduated from independent trading, y'all too so function inwards into the grand challenger amid all fund managers to come across who tin best serve too protect investors' assets, (and endure rewarded according to your standing inwards this contest.)

I know, this is the idealistic means to hold back at things. Serving too protecting appear to endure what policemen should endure doing, non traders. But equally inwards quantitative trading, I retrieve it helps i becomes to a greater extent than successful inwards one's activities past times having a uncomplicated guiding regulation or model. And it doesn't wound that inwards this case, the regulation would also endure conscience-nourishing!

Trading Amongst Estimize In Addition To I/B/E/S Lucre Estimates Data

By Yang Gao

Estimize is an online-community utilizing 'wisdom of crowds' to offering word most market. It contains a broad make of crowd-sourced estimates from over 4,500 buy-side, sell-side in addition to private analysts. Studies (from Deustche Bank in addition to Rice University with others) exhibit estimates from Estimize are to a greater extent than accurate than estimates from traditional sell-side analysts.

The outset strategy nosotros tested is a mean reversion strategy developed past times the quantitative inquiry squad from Deltix using Estimize’s data. This strategy is based on the persuasion that post-earning-announcement prices typically revert from the short-term tendency driven past times the to a greater extent than recent Estimize estimates exactly before the announcement. We backtested this strategy with S&P100 over the menses betwixt 2012/01/01 in addition to 2013/12/31. (Even though Estimize has 2014 data, nosotros create non bring the corresponding survivorship-bias-free toll information from the Center for Research inwards Securities Prices that includes the closing bid in addition to enquire prices.) With 5bp one-way transaction cost, nosotros establish that the backtest shows a Sharpe ratio of 0.8 in addition to an average annual render of 6%.  The next figure is the cumulative P&L of the strategy based on $1 per stock position.

Cumulative P&L of Deltix Mean Reversion Strategy with Estimize 

It surprised us that a mean-reverting instead of a momentum strategy was used inwards conjunction with Estimize data, since earnings estimates in addition to announcements typically generate toll momentum. In guild to exhibit that this render is actually driven past times the information inwards Estimize in addition to non exactly due to toll reversal, nosotros render a benchmark mean-reverting strategy that uses prices lonely to generate signal:

1. Find long menses T in addition to brusk menses T_s, where T is average menses of the reporting of all the quarterly estimates in addition to T_s is average menses of the reporting of the latest 20% of all estimates.
2. Calculate stock render R over T in addition to Rs over T_s, in addition to allow delta = R - Rs
3. Buy stocks with delta > 0 at unopen before an earnings annunciation in addition to locomote out the positions adjacent morn at the opened upward subsequently the announcement.
4. Sell stocks with delta < 0 at unopen before an earnings annunciation in addition to locomote out the positions adjacent morn at the opened upward subsequently the announcement.
5. Hedge internet exposure with SPY during the entire asset period.

This benchmark shows no pregnant positive render in addition to and therefore it does seem that in that place is useful information inwards the Estimize information captured past times Deltix’s mean-reversion strategy.

Next, nosotros compare the traditional earnings estimates from I/B/E/S gathered from sell-side Wall Street analysts to the crowd-sourced Estimize estimates. Backtest showed the same Deltix hateful reversion strategy described inwards a higher house but using I/B/E/S estimates gave negative render over the same S&P100 universe in addition to over the same 2012-2013 period, ane time again supporting the thesis that Estimize estimates may live superior.

Since Deltix's hateful reversion strategy gives negative returns on I/B/E/S data, it is natural to come across if a momentum strategy would run instead: if the short-term average approximate is higher than the long-term average approximate (i.e. analogous to delta < 0 above), nosotros hold back the toll to motility upward in addition to vice verse.

The backtest number of this momentum strategy over the same universe in addition to fourth dimension menses is quite promising: with 5bp transaction cost, the Sharpe ratio = 1.5 in addition to average annual render = 11%. The next figure is the daily P&L of the strategy based on $1 per stock position

 Cumulative P&L of momentum Strategy with I/B/E/S

We tried the same momentum strategy using Estimize information over 2012-2013, in addition to it generated negative returns this time. This is non surprising since nosotros establish before that the hateful reversion strategy using Estimize information generated positive returns.

We proceeded to backtest this momentum strategy over the S&P100 using out-of-sample I/B/E/S information betwixt 2010 in addition to 2012, in addition to unfortunately the strategy failed in that place too. The next figure is the daily P&L of the strategy from 2010-2014.

Cumulative P&L of momentum Strategy with I/B/E/S 

So how would Deltix’s mean-reversion strategy with Estimize information run over this out-of-sample period? Unfortunately, nosotros won’t know because Estimize didn't laid out collecting information until the halt of 2011. The next tabular array is a summary on the annual returns comparison unlike strategies using unlike information sets in addition to periods.

Strategies	Mean-Reversion	Momentum
Estimize (2012.01-2013.12)	6%	-9%
I/B/E/S (2012.01-2013.12)	-17%	11%
I/B/E/S (2010.01-2011.12)	1.8%	-6.4%

As a result, nosotros cannot conclude that Estimize information is consistently meliorate than I/B/E/S information inwards terms of generating alpha: it depends on the strategy deployed. We also cannot create upward one's hear which strategy – mean-reversion or momentum – is consistently better: it depends on the fourth dimension menses in addition to the information used. The solely decision nosotros tin sack achieve is that the brusk duration of the Estimize information coupled with our lack of proper toll information inwards 2014 agency that nosotros cannot bring a statistically pregnant backtest. This Earth of inconclusiveness volition of course of teaching live cured inwards time.

_________

Yang Gao, Ph.D., is a inquiry intern at QTS Capital Management, LLC.

===

Industry Update

(No endorsement of companies or products is implied past times our mention.)

• There is a practiced word comparison Quantconnect to Quantopian here.
• For FX traders, Rizm offers a comparable service every bit Quantconnect in addition to Quantopian every bit it is straight connected to FXCM.
• Quantopian straightaway offers gratuitous cardinal information from MorningStar. Also, cheque out their Quantopian Managers Program where yous tin sack compete to deal existent money.

===

Workshop Update

Our adjacent online workshop volition be Millisecond Frequency Trading on March 25-26. It is for traders who are interested inwards intraday trading (even if non at millisecond frequency) in addition to who desire to defend against certain HFT tactics.

===

Managed Account Program Update

Our FX Managed Account program had a rigid complete inwards 2014, with annual internet render of 69.86%.

===

Follow me on Twitter: @chanep

An Open-Source Genetic Algorithm Software (Guest Post)

By Lukasz Wojtow

Mechanical traders never halt researching for the side yesteryear side marketplace seat edge. Not exclusively to acquire meliorate results but equally good to receive got to a greater extent than than 1 system. The best trading results tin give notice live achieved amongst multiple non-correlated systems traded simultaneously. Unfortunately, most traders purpose similar marketplace seat inefficiency: roughly traders specialize inward tendency following, roughly inward hateful reversion as well as and so on. That's because learning to exploit 1 form of border is difficult enough, mastering all of them – impossible. It would live beneficial to receive got a software that creates many non-related systems.

Recently I released Genotick - an opened upward rootage software that tin give notice create as well as create create a grouping of trading systems. At the Genotick's centre lies an epiphany: if it's possible to create whatever software amongst but a handful of assembler instructions, it should live possible to create whatever trading systems amongst a handful of similarly elementary instructions. These elementary as well as meaningless-on-its-own instructions boot the bucket extremely powerful when combined together. Right instructions inward the right fellowship tin give notice create whatever type of mechanical system: tendency following, hateful reverting or fifty-fifty based on primal data.

The driving engine behind Genotick's mightiness is a genetic algorithm. Current implementation is quite basic, but amongst roughly extra quirks. For example, if whatever of the systems is genuinely bad – it stays inward the population but its predictions are reversed. Another play a joke on is used to assistance recognize biased trading systems: a organization tin give notice live removed if it doesn't give mirrored prediction on mirrored data. So for example, seat on GBP/USD must live opposite to the 1 on USD/GBP. Genotick equally good supports optional elitism (where the best systems e'er remain inward the population, spell others are retired due to onetime age), protection for novel systems (to avoid removing systems that didn't yet receive got a peril to bear witness themselves) as well as inheriting initial system's weight from parents. These options give users plenty of room for experimentation.

When Genotick is run for the outset fourth dimension - at that spot are no systems. They are created at the start using randomly chosen instructions. Then, a genetic algorithm takes over: each organization is executed to cheque its prediction on historical data. Systems that predicted correctly gain weight for hereafter predictions, systems that predicted incorrectly – lose weight. Gradually, 24-hour interval afterwards day, population of systems grows. Bad systems are removed as well as expert systems breed. Prediction for each 24-hour interval is calculated yesteryear adding predictions of all systems available at the time. Genotick doesn't iterate over the same historical information to a greater extent than than 1 time – preparation procedure looks precisely equally if it was executed inward existent life: 1 24-hour interval at a time. In fact, at that spot is no carve upward “training” phase, programme learns a footling fleck equally each 24-hour interval passes by.

Interestingly, Genotick doesn't cheque for rationale behind created systems. As each organization is created out of random instructions, it's possible (and genuinely really likely) that roughly systems purpose ridiculous logic. For example, it's possible that a organization volition give a “Buy” betoken if Volume was positive 42 days ago. Another organization may desire to boot the bucket brusk each fourth dimension the 3rd digit inward yesterday's High is the same equally 2nd digit inward today's Open. Of course, such systems would never move inward existent footing as well as equally good they wouldn't move for long inward Genotick's population. Because each system's initial weight is zero, they never gain whatever important weight as well as so don't spoil cumulative prediction given yesteryear the program. It may seem a footling giddy to permit such systems inward the outset place, but it enables Genotick to attempt out algorithms that are gratis from traders' believes, misguided opinions as well as personal limitations. The pitiable fact is, the marketplace seat doesn't aid most what organization yous purpose as well as how much effort as well as tears yous set into it. Market is going to create what it wants to create – no questions asked, non taking prisoners. Market doesn't fifty-fifty aid if yous purpose whatever sort of intelligence, artificial or not. And so, the exclusively rationale behind every trading organization should live really simple: “Does it work?”. Nothing more, nada less. This is the exclusively metric Genotick uses to approximate systems.

Each program's run volition live a footling fleck different. Equity nautical chart below shows 1 possible performance. Years shown are 2007 until 2015 amongst actual preparation starting inward 2000. There is nada exceptional most twelvemonth 2007, cry back – Genotick learns equally it goes along. However, I felt it's of import to await how it performed during fiscal crisis. Markets traded were:

USD/CHF, USD/JPY, 10 Year U.S. Bond Yield, SPX, EUR/USD, GBP/USD as well as Gold.

(In roughly cases, I tested the organization on a marketplace seat index such equally SPX instead of an musical instrument that tracks the index such equally SPY, but the divergence should live minor.)  All markets were mirrored to permit removing biased systems. Some vital numbers:

CAGR: 9.88%
Maxim drawdown: -21.6%
Longest drawdown: 287 trading days
Profitable days: 53.3 %
CALMAR ratio: 0.644
Sharpe ratio: 1.06
Mean annual gain: 24.1%
Losing year: 2013 (-12%)

(Click the cumulative returns inward % nautical chart below to enlarge.)

Cumulative Returns (%) since 2007

These numbers correspond exclusively “directional edge” offered yesteryear the software. There were no stop-losses, no leverage as well as no seat sizing, which could greatly improve existent life results. The functioning assumes that at the cease of each day, the positions are rebalanced as well as so that each musical instrument starts amongst equal dollar value. (I.e. this is a constant rebalanced portfolio.)

Artificial Intelligence is a hot topic. Self driving cars that drive meliorate than an average human as well as chess algorithms that crunch an average histrion are facts. The divergence is that using AI for trading is perfectly legal as well as opponents may never know. Unlike chess as well as driving, at that spot is a lot of randomness inward fiscal markets as well as it may accept us longer to discovery when AI starts winning. Best hedge funds tin give notice live yet run yesteryear humans but if whatever trading method is genuinely superior, AI volition figure it out equally well.

At the 2nd Genotick is to a greater extent than of a proof-of-concept rather than production-ready.

It is really express inward usability, it doesn't forgive mistakes as well as it's best to inquire earlier using it for existent trading. You volition demand Java vii to run it. It's tested on both Linux as well as Windows 10. Example historical information is included. Any questions or comments are welcomed.

Genotick website: http://genotick.com

Source code: http://github.com/alphatica/genotick

Forum: https://groups.google.com/forum/#!forum/genotick

For a full general reference on genetic algorithms, come across "How to Solve It: Modern Heuristics". 

===

My Upcoming Workshop

Oct 28-29: Quantitative Momentum Strategies. 

Momentum strategies receive got performed superbly inward the recent marketplace seat turmoil, since they are long volatility. This course of written report volition embrace momentum strategies on a diversity of property classes as well as amongst a gain of trading horizons.

====

Follow me on Twitter: @chanep