TURN IT UP!

The Joe SixPacks of the investment world have been re-entering the market since March 9th.  This was after they initiated a pretty sizable outflow of mutual funds during January and February.   However, the Joes may be slowing their rate of equity inflow for some reason.

The charts below provide this year’s data.  The data source (e.g., http://www.ici.org/ ) lags by about a week, thus, we have to wait to confirm some possible developing trends.

Figure 1 above shows the weekly closing prices of VTI, the total market ETF.  This is the pattern we are all familiar with in terms of equity price increase from March 9th.

Figure 2 above shows inflow/outflow to domestic and foreign equity mutual funds.  Note the outflow from January to late February, and the resulting increase in inflow from early March to present.  Note also that in terms of cumulative balance for 2009 the equity funds are still “underwater”, that is, they need to exceed the “breakeven” line to begin a positive balance in the funds for 2009.

Is there are correlation between VTI data and mutual fund inflow/outflow?  Yes.   However, I don’t want to spend time mulling over those statistics because (1) correlations cannot be used to infer causality, and (2) the charts are presented only to visualize a potential trend in the direction of money flow.

What I want to outline in this post is the fact that the slope of  Joes’ inflow has changed, and it is decreasing (Fig 2).  This is interesting when we look at the pattern of inflows and outflows from money market mutual funds.  Basically, we see that while money has continued to move out of money markets at a fairly steady rate, something has happened to the rate of inflow into equity funds (cf. Fig 2).

I’ll be watching this possible trending action closely in the next few and post any new  developments that might present themselves.  The inflection in equity prices during mid-2003 was marked by many events, one of which was a transition in money flow from money market funds to  equity mutual funds .  We hear a lot about so-called “side-lined money” from the media (no, I will not mention DK in this post), and  mutual funds account for at least one source of the side-lined money.  Thus, if there is a change in the direction of mutual fund flow it most likely will have significance for the broader equity market.

They were showing said movie on Showtime tonight…seen it before but watched it anyway, and I’m still impressed with how good it was.  IMO, a much underrated noir thriller, with a nice twist or two at the end.  Even Dane Cook is bearable in it, while Kevin Costner gives possibly his best performance ever.  If y’all haven’t seen it, I highly recommend it…

“<i>Finding someone you think would be fun to kill is a bit like, well it’s a bit like falling in love. You meet a lot of candidates, and you like some of them, and they’re nice. But they’re not right. And that special one comes along, and your heart beats faster, and you know that’s the one.</i>”

And speaking of thrilling…that’s what the put/call ratio has been the last few days.  After sitting dormant for many weeks, it has now given 2 signals in the last 3 days.  Today, it fell back down to 0.87, which is once again close enough to give a contrarian entry:

The trade from Monday’s signal was closed today (via the trailing stop) for essentially no gain (i.e. just enough profit to cover commissions).  Could’ve had some profit had I held to the end of the day…but I was following the rules I had set forth for myself (especially with this being the first ‘for reals’ trade in the system), so I’m happy with the result.  The updated spreadsheet for the put/call ratio trades is below (5W, 2L):

Interestingly enough, cuervoslaugh’s Deucey-SPY system has also fired, and bought some SPY Jul’09 90. calls at today’s close.

Due to this dichotomy (and the upcoming holiday weekend), I’m playing along just virtually in both systems right now.  So essentially I’m sitting on a (virtual) 90/94 SPY strangle heading into the weekend – this would need some serious volatility to become truly profitable.

Unfortunately, we will also forgo the usual individual items column as I have not done any research whatsoever on it.  I’ve been busy most of the night preparing for (and getting all required IDs/etc ready for) tomorrow’s citizenship exam.  I’d hate to be the idiot who fails to pass this most basic exam.

My favorite question, bar none (from the 100 potential ones), is “What did the Declaration of Independence do?”…ummm…bound us in eternal servitude to King George??  LOL.  (For those interested, the full list of 100 questions can be found at the USCIS website.  You should _easily_ pass these.  Afterall, you (most of you, anyway) are already “part of the club”.)

Hola senors y senoras!

I have set aside 42 of the best pictures out of 457 from my trip to Spain. If you are oblivious, I am finally home.  Hope you enjoy the pictures, and don’t forget to click to enlarge!!

While technically it’s past midnight here on the West Coast and thus I can officially begin my birthday celebrations (which had already started in Vegas) this here is a look back to Tuesday’s options action.

Much ado was made about end-of-quarter last minute fuckery, but compared to previous WTF patterns, the close was rather tame…

The put/call ratio was quite active on the other hand and nearly spiked back the other way from the previous day’s spike down.  Looks like the big move down in the morning had investors running to the safety of protective puts:

As planned yesterday, I bought some SPY Jul’09 94. puts at the open…the first ‘real’ trade based off the index put/call ratio.  It is currently showing ~15% profit and thus has become the proud owner of a trailing stop, set at just above breakeven.  Futures are semi-bullish right now, so the only concern here is the possibility of a major gap up, which could potentially push the put price under the limit set along with the trailing stop and leave the sell order unfilled…

Quick Look at Some Individual Items:

• Latest biotech lottery number: SPPI.  FDA decision coming up on the 2nd.  The stock has been on an insane run and may be a good candidate for a straddle/strangle.  Might want to go with Aug’09 options though, which are only a tiny bit more expensive than the Jul’09 ones (due to vast difference in volatility) but will be less adversely affected by the upcoming volatility crush…
• Data also expected ’soon’ in RIGL…volatility there is a bit more even amongst the months however…
• Lots of action seen in WYE, with all Oct’09 ATM calls very active on the day…bull call spreads galore!
• Couple of the highest volume equity options on the day were EXC calls, thanks to what seems to be a giant calendar spread with Jul/Aug’09 55. calls.  50k each; going long the Aug’09 while selling the Jul’09 to reduce risk and cost.

And that’s about it for today…DPeezy Birthday Special picks for tomorrow (assuming the semi-bullish futures hold up):  RIMM (above $72.50) | CHK (above $20.25).

If this is true:

Then this might be an industry wide policy that should put you here:

Really you should just:

But then who would be left to manipulate ?

I feel better now

Happy July 4th kids !

The Case Shiller housing index was released today.  It was down over last month but there were a few signs of hope for the optimistic.  Here is my chart with my 18 month ARIMA forecast for housing prices (click for a bigger/better view):

So my forecast model has home prices as measured by the 10-city Case Shiller being about flat for the next few months but that is due to the strong seasonal effect this time of year.  My forecast has a year from now being down about 11% from here.  Still too early to tell if the bottom in housing is here although there are some signs that at least the rate of decrease is slowing. 

The MacroMarkets Case-Shiller ETF’s UMM and DMM begin trading today.  These trade 3x the cumulative change in the Case Shiller Index up (UMM) and inverse (DMM).  You can see some of my blog posts on these for more info but some key points to keep in mind:

• These are tied to the cumulative change in the case shiller housing index.  Not a daily change so they should not be subject to the value erosion problems some of the leveraged ETF’s have.
• The settlement date is Nov 2014 so technically what matters is the price of the housing index then.  However based on assumed value UMM and DMM should track the changes in the case shiller between now and then.
• These provide a very unique opportunity to invest directly in the U.S. housing market in a way not possible before this.
• These could be used to hedge your personal housing risk although I doubt  many will do so.

I plan to watch these closely as I have alot of interest in these especially because I feel good about my case shiller forecasting model.  But I want to let them trade for  a bit to see how they get valued in the market. 

I will surely do some followup posts in the future.

Do you like unordered lists?  Here’s a few of them.  Before reading, you may want to hit play on the video below to provide some famous house beats from our featured band:

So I spent the last 3 days in Las Vegas and have made the following observations…

OMG, we’re (still) in a fucking recession…now PANIC and FREAK OUT!

• I could get a (fountain-view) room at the Bellagio for $100 or a strip-view room at the Wynn (2 weeks out) for $175 (with $75 resort credit).
• Half the cabanas at the Bellagio pool went unsold on Saturday ($300/day).
• Could only count 2 occupied cabanas (out of ~100) at the Wynn on Sunday.
• I could actually walk down the strip without having to rub shoulders with every other person I came across.
• There was no outrageous rush-hour (Friday eveneing/Sunday afternoon) clusterfuck at the airport.  No feelings of claustrophobia whatsoever!
• Several cabbies tried to pull the $10-minimum shit.
• I could get a center spot at the railing for the Bellagio fountain show without any problems at all hours of the day (granted, I obviously wasn’t there for every single show, just a fairly random sampling in the afternoon, evening, and midnight).
• I could get into the lounge at Joe’s (@ Caesar’s) at 8pm (party of 2) without a wait.
• Literally EVERY single store was having a sale, regardless of location.  From the standard mall stores of the Miracle Mile through the upscale shops at The Forum Shops to Manolo Blahnik/LV/Cartier/Chanel/Ferrari at the Wynn.  And these weren’t just your usual “3 items on 1 rack are 10% off”…these were 30-50% off the entire store!
• Only about half the population of Mexico was out snapping their whore-cards at you.  They used to bring over everybody in years past.  Hell, I think I even saw a couple whities proudly displaying their ‘Girls direct to you’ shirts…

Nah…Vegas is (still) recession proof!

• The Bank (@ Bellagio) still had the balls to charge you $20/drink, $7/bottled water, and $1000 for bottle service at their shitty-ass VIP “booth”.
• Carnival Court (@ Harrah’s) was actually charging a cover!
• I think I saw a few construction workers at the still-in-progress City Center.
• Ummm…yeah, that’s about it.

So there ya have it…take it for what’s it worth…but Vegas, as I mentioned above, has always been billed in my mind as ‘recession proof’.  Apparently…just maybe…not so much.

And taking a quick/cursory look at options activity…the index put/call ratio has fallen to its lowest level since the 5th of May!

While this reading may seem bullish at face value, we’re working with the theory that the put/call ratio is a contrarian indicator at its extremes.  Thus, I will be buying some SPY puts at tomorrow’s open (while all my trades with this ’system’ have been virtual so far, I may yet do this for real…depends on how I feel in the morning).  Performance so far:

As many others, I have been watching Natural Gas (UNG) lately.  I have done a number of posts on my blog analyzing natural gas price and other data.  Most recently I looked at the price ratio of natural gas and crude and developed an ARIMA model looking at the time behavior of that ratio and based on that model I think this is a good time for a pair trade of shorting crude and going long natural gas.

Here is a quick summary of the background, if you want more details you can see my blog post.  To start, here is a chart of the price ratio of natural gas to crude.  This is monthly data going back to 1992.

(I think you can click on the picture for a better view, I downsized it so it won’t get cut off while the image downsizer gets fixed.)  It is on a log scale which is important for all price data but also for a price ratio.  But you will see this price ratio has trended through the years up until about 2002 and then since it has trended down.  But the shorter term swings are more what I am interested in and so I fit an ARIMA model to that dynamic shorter term behavior.  I won’t show the details of the ARIMA model but the next step is to look at the residual error from the ARIMA model.  This basically shows you when the ARIMA model is not fitting the short term behavior well.  That is an indication of the price ratio getting too high or low on a short term basis (kinda like an oversold or overbought reading but it is based on a statistical model and statistics).  Here is what that residual looks like with a Moving Average control chart:

When the residual plots over the upper control limit it is a sell signal and when it plots below the lower control limit it is a buy signal.  So I tried a basic trading system where you buy when the ARIMA residual MA plotted above goes below the lower control limit and then you sell when the MA goes back above the center line.  And vice versa on the top side.  Here is what it looks like trading natural gas since 1992:

(again hopefully you can click the image to see a larger and clearer view).  But as you can see, this really produces some amazing results.  It is just a backtested result so it may be overly optimistic and no slippage of course included.  But since this is a statistics based system with little to no over-optimization, I am still pretty impressed by it.

Taking us to now, this system issued a buy on natural gas in March.  That buy is still open.  This analysis is a monthly price analysis so in reality when I would see a buy or sell on this system, I would then watch the daily charts more closely for a purchase.  Technically this analysis is on the Ratio of natural gas and crude so if it issues a buy you would buy NG and short crude.

Taking a quick look at the UNG and USO charts, I like the idea of being long UNG and short USO:

Trade Execution/Strategy: I will probably do this via DTO, the 2x Crude inverse ETF which would allow me to only use 1/2 the capital and not outright short.  And then buy UNG.  So I would for example buy $10k in UNG and buy $5k in DTO. 

Disclosure: I have not done this yet but probably will.

Jump Off

For the better part of the last year, I have been writing about the usage of Information Theory as a means of quantifying equity movement. Usually it’s been in the application of spreadsheet based mechanical systems for the purpose of illustrating the efficacy of this analytical process but, also to show readers how fairly straight forward it is to apply this little known tool to something as nonsensical as Mother Market herself.

Finding myself between gigs and wanting to keep my skillset sharp, I decided to take what was out there and find a more straightforward way to use the ID3 algorithm. Additionally, I wanted to learn how to build a GUI app with my second favourite programming language, Ruby.

What follows is the presentation part of a technical demo that I gave last week of this very simple application to the president of our provincal professional association.

On with the show.

ID3A

ID3A, is a windowed app which facilitates the use of the ID3 algorithm as implemented by Sergio Fierens in his Rubygem ai4r.

To wit, it provides an interface which is more consistent with the average computer user as opposed to being an application that requires cryptic commands typed in a terminal session.

The additional benefits of this machine learning paradigm are it’s speed and the transparency of the rulesets that are developed with ID3.

The ID3 algorithm was introduced in 1975 by Australian Ross Quinlan and published in the first issue of Machine Learning and has been taught in AI courses ever since. Tried and true, it is often a “beginner’s introductory tool” to the field and subsequently passed on during studies. It is for this probable reason that the wikipedia entry shows a robust variety of implementations however, none of them are aimed at an end user who is not already extremely comfortable with computers.

The Demonstration – Batch Querying

The most recent addition to the application is the means of querying a csv file of data in a batch manner so that one is not forced to deal with a dialog for each query.

Step 1: Download the csv file output from the Dow Jones Industrial Average (^dji on Yahoo!) from October 1, 1928 to June 23, 2009

Step 2: In the columns following the “Adjusted Price” begin adding these headers: Above 5 Days Ago?, Above 10 Days Ago?, Above 20 Days Ago?, Above 10 DMA?, Above 20 DMA?, Above 50 DMA?, Above 75 DMA?, Above 100 DMA?, Higher 100 Days from today?

Step 3: Next create formulae that answer the above questions in columns H to U with each cell giving a “Y” or “N” to the column’s header question.

You will now find that your data set has been reduced slightly to a range of Feb 26, 1929 to Jan 29, 2009.

Step 4: Copy and past only the answers into a separate spreadsheet.

Step 5: Split the data into an 80/20 split which will give 16, 157 examples to train on and 4,017 examples to test against.

Step 6: Now that you have split the data, take the spreadsheet with the 80% training set and save it as “dji_train.csv”.

Step 7: Save the testing set as “dji_test_master.csv”.

Next you will need to create the sample set for the batch query, the only difference is that the last column “Higher 100 Days from Now?” column will be blank beneath the header. Save this file as “dji_test.csv”

Step 8: Download the v.02 version of ID3A from it’s location on github (http://github.com/cuervoslaugh/ID3A/tree/v.02) and unzip it on your desktop

Step 9: In the /bin folder you will find ID3A.exe and it launches with a double click

Step 10: Under the File menu, select “Load CSV” and select the “dji_train.csv” that was created in Step 6

Step 11: Under the Analyse menu, select “Generate Rules” and after about 10 seconds you will find that a ruleset has been created from the 16,157 examples (speed will vary with CPU – on my duo core, it’s about 10 seconds)

Step 12: Under File, select “Save Rules” and give the ruleset a name

Step 13: Close ID3A and restart it

Step 14: Under Analyse menu, select “Batch Query” and it will ask you to pick first which ruleset you want to use (select the one you saved in step 12) and the batch samples to load (select “dji_test.csv”)

Step 15: Open the report that was generated in the /reports folder and copy the last column into the last column of the dji_test_master.csv file.

The Results

At this point, you will have noticed that 90% of your time has been spent building the spreadsheets to feed into ID3A, the application itself is able to chew through an immense amount of data fairly quickly. (While I have not pushed it to it’s limits, I was able to generate rulesets for 10,000 examples of 1,000 columns in under 30 seconds and process a similar batch query in the same amout of time.)

System Results

As you may have surmised from above, the system is a very slow motion 100 day trading system that buys a share of the Dow Jones and holds for 100 days.

For the period from Feb 23, 1993 to March 3, 2009 the system gave these results:

• Number of trades: 40
• Average Trade: $135.43
• Average Win: $563.24
• Average Loss: $1,115.56
• Win Percent: 70%
• Expectancy $59.60
• Annualised Returns: $158.94

For those that care, the Two-tailed P Score is 0.0114 which is considered “statistically significant”.

Closing comments:

ID3A is an open source piece of software. I could not in good faith, create an application based on open source software and attempt to monetise the actual application itself. As for any consulting services relating to developing and using machine learning techniques – I’m open to discussions. My contact information is on github.

I’d like to thank the beta-testers who took the time to thrash it around and see if it broke. The fast and furious emails in the hours after it went in closed beta release helped keep last weekend interesting.

Special thanks go out to DPeezy who figured out how to get it to run on a Mac and to Woodsheddar who kept a steady stream of feedback and to Jeremy who didn’t use the internet laser beam on my FEMA trailer.

I’m about to pack up our belongings and relocate the fam back to Toronto this summer so I don’t know how often I’ll be posting in the near future but, I’d like to thank The Fly for his series on how he dealt with his first brokerage job and his ultimate win in the year that followed.

Theme Song

Filed under Uncategorized · Tagged with

« Older posts