Quant Macro Investing

Risk Taking Disciplined

AI That Picks Stocks Better Than the Pros

(Technology MIT Review, June 10 2010) The ability to predict the stock market is, as any Wall Street quantitative trader (or quant) will tell you, a license to print money. So it should be of no small interest to anyone who likes money that a new system that works in a radically different way than previous automated trading schemes appears to be able to beat Wall Street’s best quantitative mutual funds at their own game.

It’s called the Arizona Financial Text system, or AZFinText, and it works by ingesting large quantities of financial news stories (in initial tests, from Yahoo Finance) along with minute-by-minute stock price data, and then using the former to figure out how to predict the latter. Then it buys, or shorts, every stock it believes will move more than 1% of its current price in the next 20 minutes – and it never holds a stock for longer.

The system was developed by Robert P. Schumaker of Iona College in New Rochelle and and Hsinchun Chen of the University of Arizona, and was first described in a paper published early this year. Both researchers continue to experiment with and enhance the system – more on that below.

Using data from five non-consecutive weeks in 2005, a period chosen for its lack of unusual stock market activity, here’s how AZFinText performed versus funds that traded in the same securities (which were all chosen from the S&P 500):

And here’s how it performed compared to the top 10 quantitative mutual funds in the world, all of which draw from a much larger basket of securities, except of course for the included S&P 500 itself:

Software that analyzes textual financial information – quarterly reports, press releases, news articles – is nothing new. Researchers have been publishing on the subject since at least the mid-1990’s.

However, previous approaches to this technique were hampered by either poor performance (averaging little better than chance) and / or requirements for unreasonable amounts of computational horsepower. Schumaker and Chen get around these issues by first radically shrinking the amount of text their system has to parse by boiling down all the financial articles the system ingests into words falling into specific categories of information.

Interestingly, these techniques and categories derive from classification schemes described at the 7th Message Understanding Conference, held in 1997, which was a Defense Advanced Research Projects Agency project to create new and better ways to extract information and meaning from texts. (At the time, they were concentrating on terrorist activities in Latin America, airplane crashes, rocket and missile launches and other things relevant to national security.)

Schumaker and Chen’s system concentrates on Proper Nouns – people and companies – and combines information about their frequency with stock prices at the moment a news article is released. Using a machine learning algorithm on historical data, they look for correlations that can be used to predict future stock prices.


Further work with the AZFinText system has revealed oddities that may or may not remain relevant as researchers continue to apply it to other bodies of historical stock market and financial news data. For example, in a paper described on June 6 at the Computational Linguistics in a World of Social Media workshop, Schumaker went fishing for the Verbs most likely to cause a stock to move up or down in the next 20 minutes, and came up with a list of 211 terms that had some power to move stock prices. (In his work, ‘verb’ is a technical term, and does not exactly correspond with the conventional definition of the word.)

According to Schumaker:

The five verbs with highest negative impact on stock price are hereto, comparable, charge, summit and green. If the verb hereto were to appear in a financial article, AZFinText would discount the price by $0.0029. While this movement may not appear to be much, the continued usage of negative verbs is additive.

The five verbs with the highest positive impact on stock prices are planted, announcing, front, smaller and crude.

Schumaker did not attempt to determine why these particular terms move stock prices, but it’s interesting to note that the stock market does not appear to like the marketing buzzword “green,” but is quite happy to hear any news at all about the term “crude,” as in oil.

Editing Assistant: Frances Wu

June 14, 2010 Posted by | Indicator setup | Leave a comment

Up and Down and Round and Round

(Bespoke, June 3, 2010) From February 8th to April 23rd, the S&P 500 climbed 15.9%. From April 23rd through yesterday, the index was down about 10% on a closing basis. As shown in the candle chart below, the mountain has been a lot steeper on the way down than it was on the way up. On the way up, the market basically inched a little bit higher each day in a very tight range, averaging a daily hi-lo spread of 0.99%. On the way down, investors have been thrown off a cliff, with huge moves and an average daily hi-lo spread of 2.47%. After making a steep ascent and then basically falling down, markets now sit right where they did in early February. This is one case where slow and steady did not win the race.

Editing Assistant: Frances Wu

June 7, 2010 Posted by | Indicator setup | Leave a comment

Volatility Concentration Are Bearish?

(Advisor Group, June 4, 2010) A reader commented and asked:

“The article ‘Volatility is a Bear Market Signal’ by David Schwartz measures volatility not in terms simply of big percentage days, but a cluster of such days within a specified time period (movements in excess of 1% on FTSE on at least 20 of 40 consecutive trading days). The prediction made in 2007 looks to have been well founded, giving the strategy an apparent success rate of 8 out of 9 hits if the author’s data can be trusted. What do you think?”

To check this signal independently, we measure returns at intervals of 5, 10, 21, 63, 126 and 252 trading days after onset of concentrations of days with close-to-close volatility greater than 1% for the S&P 500 Index. Using daily closes of the index for January 1950 through May 2010, we find that:
The following chart shows the number of trading days with lagged concentrations of S&P 500 Index daily volatility over the entire sample period. For example, there are 885 instances of intervals of 40 trading days during which at least 20 days have S&P 500 Index movement (up or down) of at least 1%. However, these intervals cluster/overlap, such that a trader tracking this condition and exiting the market upon encountering it would not be able to act on most of the 885 signals.

There are no intervals of 40 trading days with 36 high-volatility days.

What are the future returns after tradable signals?

Assumptions for measuring tradable future returns are:

■Exit is at the close with a signal (the trader must slightly anticipate the daily close that reaches the threshold condition).
■For future return intervals of 63 trading days or less, signals must be at least three months apart (frequent traders could relax this assumption for short-term trading).
■For future return intervals of 126 (252) trading days, signals must be at least six months (one year) apart.
■Ignore trading frictions (there are not many trades) and dividends.
The next chart summarizes S&P 500 Index average future returns at various horizons after onset of clustered daily volatilities of at least 1% (winnowed as described) for cluster thresholds of 20, 25 and 30 trading days out of 40 over the entire sample period. Sample sizes are small, with no more than 28, 10 and 4 trades over 60+ years for thresholds of 20, 25 and 30 trading days out of 40, respectively.

Average future returns for all days in the sample provide a benchmark for abnormal behavior.

Results do not confirm a belief that tradable volatility clusters reliably signal poor future returns.

More generally, arguments and charts such as presented in the cited article often explicitly or implicitly assume perfect foresight with regard to exit signal threshold and signal economic value. A real investor has access only to past data and may infer different (or no) thresholds based on these data. Said differently, seeing “patterns” retrospectively is not the same as setting rules that make money in real time. Even if a investor knew what threshold to use in the past, the loss avoidance implied in the article unrealistically assumes getting back into the market at bear market lows.

Also, the number of volatility rule/count/threshold combinations the author tried before settling on >20 out of the last 40 over 1% is unknown. The more combinations considered, the more likely the chosen one impounds data snooping bias (luck). The smaller the sample is, the stronger the bias.

In summary, evidence from simple tests does not support a belief that clusters of daily volatility reliably signal poor future returns.

Editing Assistant: Frances Wu

June 7, 2010 Posted by | Indicator setup | Leave a comment

Highest Intraday VIX Readings

(VIX and More, June 4, 2010) With stocks suffering a minor meltdown as I type this (DJIA 9997), I thought I might use the ongoing European sovereign debt crisis and recent May 21st VIX spike to 48.20 to put the recent VIX spike in the context of the all-time highest intraday VIX readings.

The graphic below captures the six crises which have resulted in VIX spikes above the 40.00 level since 1990. Notably, the 2008 financial crisis stands well above the crowed with an intraday high of 89.53. The other five crises have all seen intraday VIX spikes that have topped out in the 48-50 range, with last month’s spike to 48.20 making the European sovereign debt crisis the 6th highest threat – at least as far as an implied volatility proxy is concerned – in the past 20 years.

If one were to use reconstructed data going back to 1987, the best estimate is that the VIX (actually the VXO) would have hit about 170.

Editing Assistant: Frances Wu

June 7, 2010 Posted by | Indicator setup | Leave a comment

January 21, 2010 – Stock Returns and Changes in Implied Volatility

http://www.cxoadvisory.com/blog/external/blog1-21-10/

Are there reliable and exploitable predictive relationships between stock returns and changes inimplied volatility? In the January 2010 version of their paper entitled “The Joint Cross Section of Stocks and Options”, Andrew Ang, Turan Bali and Nusret Cakici investigate the relationship between changes in implied volatility and stock returns for individual stocks. Using monthly implied volatilities and associated stock prices and firm fundamentals for a broad sample of U.S. stocks over the period January 1996 through September 2008 (153 months), they conclude that:

  • Stocks with large increases in call-implied (put-implied) volatilities tend to rise (fall) over the following month.
  • The spread in average next-month returns and three/four-factor alphas between the highest and lowest quintile portfolios formed monthly by ranking the entire sample on changes in call-implied volatilities is about 1% per month. A double ranking first on changes in put-implied volatility for the entire sample and then on changes in call-implied volatilities within the lowest put-ranked quintile enhances this spread. (See the chart below.)
  • Options for stocks with high returns over the past month tend to have increases in call-implied volatility over the next month, with an abnormal stock return of 1% implying an increase in call-implied volatility of about 3%.
  • The predictive power of changes in implied volatilities for stock returns stems from idiosyncratic, not systematic, volatility components. In other words, the predictive relationship derives from information about the stock and not information about the market.
  • Results are consistent with the presence of informed traders in both the equity and options markets, with slow inter-market information diffusion.

The following figure, constructed from data in the paper, shows the average next-month gross returns for two sets of equally weighted quintile portfolios formed monthly over the entire sample period. One set derives from ranking the entire sample on the monthly change in call-implied volatility. The other derives from ranking first on the monthly change in put-implied volatility and then ranking the lowest resulting quintile on the monthly change in call-implied volatility. Results indicate that: (1) the larger the change in call-implied volatility, the larger the expected stock return; and, (2) combining the information in changes in put-implied and call-implied volatilities may enhance power to predict stock returns.

It is not obvious that this predictive power is exploitable at the net level (after trading frictions), especially for individual investors.

In summary, evidence suggests that investors may be able to gain an edge from the power of changes in implied volatilities to predict returns for individual stocks, and the power of stock returns to predict future changes in implied volatilities.

For related research, see Blog Synthesis: Volatility Effects.

January 22, 2010 Posted by | Case Study, Indicator setup | Leave a comment

Even Better Than the Real Thing – 700% this decade

Even Better Than the Real Thing – 700% this decade

December 7th, 2009 by Mebane Faber

One of the best real time examples of using AlphaClone is comparing a clone to the underlying manager this year (which is real time and out of sample). In this case we take a look at the returns for David Tepper’s Appaloosa fund via Dealbreaker.  Year to date the fund is up a whopping 119.7% gross and 84.62% net (those pesky 2% and 20% fees!!).

How about following Tepper on AlphaClone?  Taking his top 10 picks, equally weighted and rebalanced quarterly, would be up 126% through the end of November.  That not only beats Tepper’s gross returns, but also goes  to show how nicely it replicates the fund’s performance.  You’d certainly be bank heavy with some of his positions like BAC, C, FITB, VCI, and BC.

So to my readers who are institutions, family offices, endowments, and money managers – doesn’t this sound a lot better than dealing with all the lockups, headaches, K-1’s, tax inefficiency, career risk, fraud, and transparency risk of allocating to these funds?

And check out the returns since 2000 – beats the market by a mile.  While the S&P had negative returns over this period, following Tepper resulted in a 7 bagger.

December 9, 2009 Posted by | Indicator setup | Leave a comment

QDII基金轉投內需產品

Today HKEJ (p.11)

I wonder what info we can get on QDII investment (their top stock holdings?).  How frequent would the info be available (monthly?).

摩根士丹利昨天的中國策略報告指出,九隻合格境內機構投資者(QDII)基金,已經調整了其投資重點,更多的轉向內需、保險、互聯網和媒體、能源投資等,大摩相信,此舉預示這些基金未來將有更好的增長。

九家QDII基金目前百分之六十九的資金投資在香港市場,百分之九在美國市場。今年第三季度這些基金淨資產增加了百分之十點四,高於MSCI中國和A股市場。

在增加經濟增長類股的同時,這些基金也降低了銀行/房地產和資源類產品的投資比重,這些行業更容易受退市政策影響。大摩表示,認同上述投資策略■

November 10, 2009 Posted by | Indicator setup | 2 Comments

Market Folly portfolio ranked No.1 in …

I wonder what the others are doing (rank No.2, 3, 4, etc).

Full text

http://www.marketfolly.com/2009/11/market-folly-custom-portfolio-ranked-1.html

 

We have some fantastic news to report in that our very own Market Folly custom ‘hedgefundesque’ portfolio is ranked #1 on Alphaclone’s leaderboard for all fund strategies! Upon checking out their leaderboard, we discovered that if you select the ‘max’ date-range and search for 50% hedged strategies, our clone is ranked #1 out of all the various funds they track with a total return of 878.3%, an annualized return of 26.1%, and Alpha of 23.4 all since January of 2000. This of course is the portfolio we post updates on each month. The portfolio takes positions from 3 handpicked hedge funds we’ve selected and combines them into a cohesive hedgefundesque clone by taking the top 3 holdings of each fund, equal weighting them, and then employing a 50% market hedge.

Read more: http://www.marketfolly.com/2009/11/market-folly-custom-portfolio-ranked-1.html#ixzz0Vtg7L4UQ

November 4, 2009 Posted by | Indicator setup | Leave a comment

Soc Gen’s Albert Edwards on market turning points

Lead indicators to identify turning points – here for more info.

October 31, 2009 Posted by | Indicator setup | 1 Comment

Wall Street recommendation

Such data available from Bloomberg – quite handy isn’t it?  I wonder if similar data available in Asia, and if this indicator helps to identify turning points for market.

 

(Pragmatic Capitalist) … the reason why 95% of all investment banks and advisors maintained at least a high level of buy and hold ratings all last year.  They want to keep you in the game.  See the chart below and notice the consistent 5% sell ratings by analysts.  Do you mean to tell me that during one of the greatest collapses in economic history the level of stocks rated “sell” never moved above 5%?  That is an utter embarrassment for the entire Wall Street community.  In my own business I rarely have more than 5% of the entire stock market on my BUY list.

analystratings

October 31, 2009 Posted by | Indicator setup | 5 Comments