(866)-482-2177

sales@alphatheory.com

REQUEST A DEMO

SYSTEM REQUIREMENTS


Please note the following System Requirements. Further, please limit the number of open applications (particularly price streaming applications) while logged in to Alpha Theory™.


Recommended System Specifications
Processor: Dual Core or Quad-Core 2.4GHz or faster
RAM: 4GB+
Browser: Google Chrome 30+
Screen Resolution: 1280 x 1024 or greater
Internet Access: Business Class High-Speed


Minimum System Requirements
Processor: Intel Pentium-M 2.0Ghz or equivalent
RAM: 2GB+
Browser: Google Chrome, Mozilla Firefox, Internet Explorer 9+ (without Compatibility View), Safari
Screen Resolution: 1024 x 768 or greater
Internet Access: High-Speed

Subscribe to Alpha Theory content

Alpha Theory Blog - News and Insights

48 posts categorized "Portfolio Optimization"

July 18, 2016

Superforecasting – Alpha Theory Book Club

Alpha Theory hosted its first ever book club on July 12th with over 40 portfolio managers, analysts, and allocators coming together to discuss “Superforecasting” by Phil Tetlock. We were lucky enough to have two Superforecasters, Warren Hatch and Steve Roth, moderate and perform forecasting exercises with the group. We spent 2 ½ hours together and only scratched the surface on applying Superforecasting to investing.

Here are a few key takeaways:

1. RAW TALENT: On average, our group had the attributes of Superforecasters with high Active Open-Mindedness (3.99 out of 5) and high Fluid Intelligence (8 out of 10 – this is the highest score that the Good Judgement folks have seen).

Active Open Mindedness

 

 1

Fluid Intelligence

2

2. IDENTIFYING TALENT: There are identifiable attributes that can be used in hiring and have a profound impact on forecasting skill (40% - see chart below).

Screen Shot 2016-07-18 at 4.02.10 PM

3. DEVIL’S ADVOCATE: Firms should appoint a Devil’s Advocate for each investment to expand critical thinking (someone to ask the question, “I see your downside is $40. How is that if the 52-Week Low is $22 and the trough multiple would put it at $25?”)

4. OUTSIDE VIEW: Firms should require an Outside View for every investment idea (“While everyone I’ve spoken to says this deal will close, only 20% of deals with one party under SEC investigation close.”)

5. REFINEMENT: New information should always be incorporated in forecast (think Bayesian).

6. POSTMORTEM: An Accuracy Score should be calculated for every investment and should frame the conversation of “what did we do well?” and “what did we do poorly?”.

7. TEAMS MAKE BETTER FORECASTS: Team dialog generally improves forecasting accuracy.

8. FORECAST CULTURE: Firms should embrace “forecast” as part of their vernacular and conversations should revolve around how information impacts the forecast.

9. MEASURE TO BE BETTER: We all forecast, but we rarely measure. That fact needs to change if we really want to improve.

10. BOOK CLUBS ARE COOL!!!

The October Alpha Theory Book Club topic will be “Success Equation: Untangling Skill and Luck” by Michael Mauboussin. Mr. Mauboussin will moderate and highlight the book’s application to investing. Contact your Alpha Theory representative if interested in attending.

 

June 21, 2016

How Good Are My Analysts? Building a Better Hedge Fund Through Moneyball & Superforecasting

Traditionally, measuring hedge fund analyst skill has been an opaque process mired in ambiguity and subjectivity.  It is often misconstrued and tainted by portfolio manager influence in the form of sizing decisions, liquidity constraints and other non-analyst determinants.  But, in the same way Moneyball revolutionized evaluating baseball player value by prioritizing on-base percentage over batting average, Alpha Theory has distilled the key indicator for predictive aptitude. Alpha Theory invented the Alpha Theory Accuracy Score to introduce radical transparency into the rating of forecasting skill for hedge fund analysts.

P&L is Yesterday’s Batting Average

Using the Moneyball analogy, quantitative disruption of baseball player evaluation changed the way players are paid by isolating the player skill that contributes most to team wins. Using that data, managers now pay athletes in proportion to the amount of that winning skill they individually possess.  As such, the key metric for baseball player value evolved from batting average, to the more predictive on-base percentage, or OBP. 

Specifically, OBP has a 92 percent correlation with runs scored compared to batting’s 81 percent, making it more predictive.  Also, OBP’s 44 percent correlation year-to-year is more persistent than the 32 percent correlation of batting.  The predictive reliability and performance consistency make OBP a superior metric to forecast wins for baseball teams.  OBP’s disruption of batting average is an apt metaphor for the way Alpha Theory’s Accuracy Score will transform analyst ranking and assessment today.      

In 2016, analysts are still primarily rated by the profits and losses their investments generate for the fund, or P&L.  But making money on an investment is a misleading measure of analyst skill.  Beyond its tendency to be distorted by portfolio manager discretion, P&L performance, both good and bad, often masks the integrity and quality of investment processes.  Thus, P&L often misleads portfolio managers into thinking lucky analysts are actually skilled and vice versa.

For example, take these two analysts:

How good is my

Looking at the table above and using P&L to measure skill, Analyst #1 would be exceptional and Analyst #2 would be sub-par.  But Analyst #1 and #2 had the same forecasts, so their forecasting skill is actually identical.  P&L does not translate into forecast skill because analysts do not have ultimate control over position sizing; the portfolio manager does!

More Science, Less Art                                                                                                                         

Inspired by the ideas presented in the groundbreaking book, Superforecasting: The Art and Science of Prediction, Alpha Theory’s Accuracy Score delivers quantitative insight into a qualitative blind spot for portfolio managers.  Authored by Wharton Professor Phillip Tetlock and Dan Gardner in 2015, Superforecasting applies a Brier Score-inspired approach to quantifying predictive skill.  The Brier Score was created by meteorological statistician, Glenn Brier, in 1950 and measures the accuracy of probabilistic outcomes.  Superforecasting applies Brier’s methodology to only binary, or yes/no, outcomes.  

The New Standard

Alpha Theory’s Accuracy Score is an algorithmic solution that measures analysts’ predictive skill over a 0 - 100 percent range, where 100 is the best.  Scores are calculated on a per-forecast basis and then averaged per analyst.  The Accuracy Score algorithm transforms point estimate price targets and probability forecasts into an implied probability distribution, enabling each forecast to be independently scored.  By distributing multi-faceted outcomes across a range of probabilities, the Accuracy Score can measure forecasting skill for any price along the distribution.

The distribution of scores across our Alpha Theory clients is shown below.  The results follow a normal distribution, which further validates the Accuracy Score’s efficacy in rating analysts’ ability to forecast future price movements.

Screen Shot 2016-06-21 at 9.41.12 AM

Good forecasts are the most essential component of fund success and critical when portfolio managers are sizing positions.  Using a data-driven approach to determine which analysts make the best forecasts allows managers to apply those forecasts with greater confidence, leading to better position sizing and superior performance.

The Good Judgement Project

In 2011, the Intelligence Advanced Research Projects Activity, a U.S. government research organization, sponsored a geopolitical forecasting tournament that would span 4 years. The IARPA tournament enlisted tens of thousands of forecasters and solicited more than 1 million forecasts across nearly 500 questions related to U.S. national security.

A group called the Good Judgement Project entered the competition, engaged tens of thousands of ordinary people to make predictions, and the won the tournament. The GJP’s forecast accuracy was so persistent that IARPA closed the tournament early to focus exclusively on them. In fact, GJP was able to find a select group of “Superforecasters” that generated forecasts that were "30 percent better than intelligence officers with access to actual classified information.” 

Ways to Improve Forecasting Skill

The main findings of the GJP and the book that followed are especially relevant to investors. The research in Superforecasting indicates that predictive accuracy doesn’t require sophisticated algorithms or artificial intelligence.  Instead, forecast reliability is the result of process-oriented discipline.  

This process entails collecting evidence from a wide variety of sources, thinking probabilistically, working collaboratively, keeping score and being flexible in the face of error. According to the book, the 10 traits that most Superforecasters possess are: 

    1.  Intelligence - above average, but genius isn’t required

    2.  Quantitative - not only understand math but apply it to everyday life

    3.  Foxes, not hedgehogs - speak in terms of possibilities, not absolutes

    4.  Humility - understand the limits of their knowledge

    5.  System 2 Driven - use the logic-driven instead of instinct-driven portion of their brain

    6.  Refute fatalism - life is not preordained

    7.  Make frequent and small updates to their forecast based on new information

    8.  Believe that history is one of many possible paths that could have occurred

    9.  Incorporate internal and external views

    10. CONSTANTLY SEARCH FOR WAYS TO IMPROVE THEIR FORECASTING PROCESS

Accountability = Profitability

Organizations cannot improve without systematic and data-driven assessments of their personnel.  Take Bridgewater Associates, for example.  One of the primary factors driving the persistent outperformance of Ray Dalio’s storied fund has been the institutional commitment to radical transparency and accountability.  Similarly, Alpha Theory’s Accuracy Score illuminates blind spots and holds analysts accountable through the precise measurement of predictive skill. For funds that lack the time, inclination or internal resources to create their own probabilistic forecast-grading models, Alpha Theory’s Accuracy Score fills the void.

To this end, Alpha Theory is exploring areas of collaboration with the leadership of Good Judgment Inc. (a spin-off from the Good Judgement Project in “Superforecasting”).  As the competitive landscape for investment capital tightens, discretionary managers must leverage probabilistic data to survive.  Alpha Theory’s Accuracy Score is a mission-critical asset that can help funds compete in the current investment landscape, improving operating inefficiencies and better aligning analyst pay with their intrinsic value to the firm.

October 12, 2015

Do Price Targets Matter in Volatile Markets? (And, Why Alpha Theory Should Be a Starting Point Even in Turbulent Times)

This blog was co-authored with Alpha Theory's Customer Relations Manager, Dana Lambert.

    “Stock prices will continue to fluctuate – sometimes sharply – and the economy will have its ups and downs.  Over time, however, we believe it is highly probable that the sort of businesses we own will continue to increase in value at a satisfactory rate.” – Warren Buffett, famed investor

    “While many have portrayed the current environment as a highly risky time to invest, these individuals are likely confusing risk with volatility.  We believe risk should be determined based on the probability that an investor will incur a permanent loss of capital.  As market values have declined substantially, this risk has actually diminished rather than increased. “– Bill Ackman, Pershing Square 3Q08 Investor Letter

The recent market environment has proven challenging for many funds, including Alpha Theory clients. The market has been volatile, but the real challenge is directionality.  As of September 28, the S&P was down 11% over the prior 49 trading days, with 30 of the 49 days being down.  Alpha Theory clients generally benefit from pure volatility (large ups and downs without a direction) because they are buying on dips and selling on rises (mean-reversion).  The problem with a uniformly down directional market is that clients are continually getting indications to add to their longs and trim their shorts – the proverbial “catching the falling knife”.  Although Alpha Theory can not overcome persistent negative correlation between scenario estimates and outcomes – in other words inaccurate research – it does offer three options to help clients deal with these circumstances.

OPTION #1 - RAISE PREFERRED RETURN. When the price of an asset falls, its probability-weighted return (PWR) rises.  When the PWR rises, the normal action is to increase your position size.  But when all asset prices fall, all PWRs rise and thus the longs become more attractive and the shorts less so.  This suggested increase in long exposure may not be tenable and there may be a general skepticism regarding the price targets. In this situation, a manager can raise the preferred return for longs and thus raise the ‘hurdle rate’ required to be a full position in his or her fund (i.e., before you required only a 40% PWR to be a full position, but in this market environment you require 60%).  This will immediately lower long exposure and only suggest adding to the best ideas.  In the extreme example of February 2009, clients raised their hurdle rates to 70% or 80% and were able to see quickly numerous compelling ideas and how to shift capital appropriately.

OPTION #2 - RELATIVE INDEX ADJUSTMENT. As the market falls, the “market multiple” decreases – which has ripple effects through the price targets in Alpha Theory.  For those who cannot re-underwrite all of their targets for the new market paradigm, the application offers an easy-to-use feature called ‘Relative Index Adjustment’.  This basically adds back the move of the market to an asset’s expected return, and the following would be an illustrative example.  If the market is down 11%, then most assets’ prices will also be down and their suggested position sizes will increase.  Now let’s turn on the Relative Index Adjustment.  If every asset is down 11%, commensurate with the market move, then Alpha Theory will adjust the prices so that there is no change (-11% Stock Move minus -11% Market Move = 0% change) and thus no suggested change in position size.  The beauty of this system is that you can turn it on and off and the Market Move is calculated since the last price target update.  So if an analyst updates a price target, the Market Move gets set back to zero because the analyst would take into account the new “market multiple.”

OPTION #3 - REUNDERWRITE CONSERVATIVE PRICE TARGETS.  Fundamental investors recognize that there is no absolute intrinsic value for each asset because their assumptions are subjective.  There is, however, a range of assumptions that span from aggressive to conservative.  Down markets imply that pushing your assumptions to the conservative end of the spectrum may be appropriate.  After doing this, you can see which assets are still suggested buys and which are not.  The confidence imbued by using the most conservative assumptions allows you to be aggressive with add and trim decisions. 

A few views to help isolate where to start the re-underwriting process are: 

  • Performance view: shows those assets that have suffered the most on an absolute and relative basis
  • Group by Risk/Reward within 10%: groups the assets that are within 10% of Reward and 10% of Risk targets

  Do Px Targets Matter 1

                        Do Px Targets Matter 2

 

While consideration of the aforementioned steps certainly is appropriate as you develop conviction about downward directionality for the market, it is also worth noting that volatile markets can often be followed by periods of relative calm and distinct upwardly-biased directionality – and of course this has been the pattern for the past several years now.  So where in one week an analyst or PM sees a 1-year target as likely to be unachievable, the next week suddenly the expected return gap narrows considerably.  In short, just when you may be losing faith in your targets, they can quickly fall back into an attainable range.

Directional markets that move quickly are challenging for many reasons.  It is easy to throw up your hands and rationalize that “price targets don’t matter” or “our research is wrong”.  It is hard to restrain those emotions and redouble your efforts to find the value that has been exposed in the quick, volatile relocation of asset prices. To do so requires a rigorous, disciplined process that begins with retesting assumptions (i.e., raising return hurdles, adjusting for the market move, and setting more conservative targets).  If, after re-underwriting price targets and portfolio inputs, Alpha Theory is still recommending upsizings, then you can feel confident in your actions … even in a volatile, directional market.

August 24, 2015

Impact of Minimum and Preferred Return Settings on Optimal Position Size

We welcome our very own Customer Relations Manager, Dana Lambert, for this guest post:

During the on-boarding phase and in meetings with clients, we often like to point out how minimum and preferred return settings influence optimal position size (OPS), as well as the right framework to think about these settings.

As a starting point, Alpha Theory was designed to derive OPS using a set of linear relationships between OPS and risk-adjusted return (RAR) and – if used – liquidity, beta and other thresholds.  The way to think about this is straightforward enough, starting with the RAR bounds.  If the parameters are set to 0% and 10% for minimum and maximum position sizes, respectively, and 0% and 50% for minimum and preferred returns, then the following will be the case.

(1)    For a stock with a 50% or greater risk-adjusted return, all else equal, Alpha Theory will recommend a 10% position size.

(2)    For shares with a 0% return, all else equal, the application will suggest a 0% position size.

(3)    At a 25% return, the midpoint of the risk-adjusted return range, Alpha Theory will show a 5% position recommendation, the midpoint of the position size range.

Following is a graphical depiction of the linear relationship with OPS on the y axis and RAR on the x axis:

The ‘all else equal’ implies that no other portfolio-level constraints or Checklist items are in use.  In short, Alpha Theory employs a linear scale to determine the optimal position weighting as well as for liquidity thresholds, beta, and confidence. 

(For example, assuming the same minimum and maximum position size thresholds, and $10m and $20m average daily volume bounds for minimum and preferred liquidity: any stock with below $10m in liquidity will see a 0% position recommendation, a $20m or greater liquidity name will see no cut to OPS from the liquidity parameters, and a stock with $15m in ADV will see a 5% position suggestion – assuming the 50% or greater return threshold is already met.  Further, stocks with a beta of 2.0 will see half the optimal position size recommendation versus stocks with a beta of 1.0 while betas of 0.5 will result in a doubling of OPS.  Finally, for each 10% degradation in confidence, OPS will also fall 10%.)

What this implies is that by establishing a range for both RAR and position size, we’re establishing the degree of sensitivity for this linear relationship, or the slope of the line in our diagram above.  In the example above, each 10% increment in RAR leads to a 2% jump in OPS.  Of course, the next logical question is how one goes about determining minimum and preferred RAR, which involves more consideration for most versus setting the minimum and maximum position size (which most portfolio managers have long ago determined without substantial deliberation).

In setting the minimum RAR, we consider it best practice to use the 0% bound.  The reason is simple, in that as long as there is some positive return available in a stock, we do not want Alpha Theory to suggest a zero weighting in that name.  The reality is that as expected return approaches zero (say, 3% then 2% then 1% return left), the OPS will be suggesting some nominal position anyway, so risk will be minimized.

In establishing the preferred RAR level, one place to begin is to look across all of one’s stock-by-stock expected returns and note what the average or even just predominant trend is in RAR levels.  If one’s entire book shows itself to offer no single stock with greater than say, a 20% probability-weighted return, then a 50% preferred return threshold is almost certainly too high.  Another way to think about preferred return is to determine the 95% confidence interval of the RAR range.  Find a preferred return that is close to but not ultimately the highest RAR in the book.

On the other hand, too low a preferred RAR may indeed make position size recommendations too sensitive to changes in expected return.  So if one has the original 0% and 10% position limits from our first example, but RAR bounds are changed to 0% and 20% (rather than 0% and 50%), then only a 4% change in expected return will be required to change the position recommendation by 2%, a much higher ratio than the original 10% RAR change needed (2%/10% or 1:5 in the original example versus 2%/4% in the current example or 1:2).  Clearly a 4% change in expected returns occurs much more frequently and easily than a 10% change, so the swing in OPS will be much more pronounced when a lower return delta exists.  For this reason, we find ourselves recommending to many clients who have too low a preferred return threshold – and as a result who are seeing major and/or unsettling OPS changes – that they widen their RAR range, and in effect lessen the optimal position size sensitivity.

We always want to allow for personal preference and one’s own intuition to dictate the ‘business rules’ in Alpha Theory, and indeed there is not a ‘perfect’ level for most portfolio constraints.  But we also want users to understand fully the implications of their choices, especially for critical fund-level parameters that influence the OPS framework.  The relationship between RAR and position size is the starting point and key construct for the optimal position size calculation, and this post should serve to highlight how to consider one’s choices for these thresholds.

May 26, 2015

Eight of the 50 Top Performing Hedge Funds are Alpha Theory Clients

This is a continuation/republish of our March blog, “20% of Top 15 Hedge Funds are Alpha Theory Clients” where we highlighted that three of the Top 15 Hedge Funds over the past three years are Alpha Theory clients.

Our friends at Novus, who put out great research, released their first quarterly analysis of hedge fund performance. In their Q1 2015 report, eight Alpha Theory clients are in the Top 50 hedge funds. Based on the size of our client base, we would have expected less than one* Alpha Theory client to be on the list but our clients actually make up 16% of the Top 50 (8/50). While we recognize that one quarter does not a trend make, we have seen empirical and anecdotal evidence of our clients’ outperformance due to their focus on value, process, discipline, and unemotional decision making.  

There are two benefits reinforced by Alpha Theory which may explain why our clients are so prevalent on this list. The first is better position sizing. Performance results are a function of Stock Selection + Position Sizing. Position Sizing is often an instinctual assessment (“best guess”) of amalgamated information processed in a portfolio manager’s head. Making it even more complicated, pricing and information is constantly in flux.  Genius or not, the task of sizing positions through mental (instinctual) calculation is subject to error and bias. Position Sizing is less than optimal for funds using instinct based decision processes because their Transfer Coefficient (the correlation between the fund’s assessed idea quality and the position size) is much less than 1. For Alpha Theory clients, the Transfer Coefficient is much closer to 1 which maximizes the alpha tied to position sizes.

The second reason why Alpha Theory customers are outperforming their peers is process. Each of our customers develop a custom process that automatically highlights when positions are mis-sized, forces conversations when price objectives are breached, or creates a framework for discussing ideas based on their probabilistic outcomes. It is difficult to create discipline without process and our clients are able to do both and outperform because of it.

We’ve measured the performance improvements that come with better position sizing and they’re real. We’ve seen it from real-world analysis of our clients where performance improvements averaged over 7%. We’ve run Monte Carlo simulations which suggest that tightly coupling idea quality and position size can add 2-6% of additional alpha (this even assumes that price targets and probabilities can be off by up to 50%).

Everyone recognizes that position sizing is important and a growing number of hedge funds are starting to do something about it. Imagine two hypothetical hedge funds that have both performed the exact same research. The firm that has a better process to translate that research into a portfolio is going to win every time (assuming the research is reasonably accurate). Process and discipline will be the hallmark of many of the future hedge fund superstars. If you don’t have a structured process now, it is important to start soon. The move towards a more logic-driven decision process has already begun and the winners are starting to show up in the data.

* Assuming that there are approximately 10,000 hedge funds worldwide according to HFR.com.

March 25, 2015

20% of the Top Performing Hedge Funds are Alpha Theory Clients

A recent Wall Street Journal article measured the three year performance of hedge funds and three of the top fifteen are clients of Alpha Theory. That means that 20% of the top 15 performing hedge funds are Alpha Theory clients. There are approximately 10,000 hedge funds worldwide (according to HFR.com) so approximately 5% of our clients are in the top 15 versus the expected percentage of less than 1%. Two of our clients are in the top 10, or 3% versus the <1% expected percentage.

There are two benefits reinforced by Alpha Theory which may explain why our clients are so prevalent on this list. The first is better position sizing. Performance results are a function of Stock Selection + Position Sizing. Position Sizing is often an instinctual assessment (“best guess”) of amalgamated information processed in a portfolio manager’s head. Making it even more complicated, pricing and information is constantly in flux.  Genius or not, the task of sizing positions through mental (instinctual) calculation is subject to error and bias. Position Sizing is less than optimal for funds using instinct based decision processes because their Transfer Coefficient (the correlation between the fund’s assessed idea quality and the position size) is much less than 1. For Alpha Theory clients, the Transfer Coefficient is much closer to 1 which maximizes the alpha tied to position sizes.

The second reason why Alpha Theory customers are outperforming their peers is process. Each of our customers develop a custom process that automatically highlights when positions are mis-sized, forces conversations when price objectives are breached, or creates a framework for discussing ideas based on their probabilistic outcomes. It is difficult to create discipline without process and our clients are able to do both and outperform because of it.

We’ve measured the performance improvements that come with better position sizing and they’re real. We’ve seen it from real-world analysis of our clients where performance improvements averaged over 7%. We’ve run monte-carlo simulations which suggest that tightly coupling idea quality and position size can add 2-6% of additional alpha (this even assumes that price targets and probabilities can be off by up to 50%).

Everyone recognizes that position sizing is important and a growing number of hedge funds are starting to do something about it. Imagine two hypothetical hedge funds that have both performed the exact same research. The firm that has a better process to translate that research into a portfolio is going to win every time (assuming the research is reasonably accurate). Process and discipline will be the hallmark of many of the future hedge fund superstars. If you don’t have a structured process now, it is important to start soon, as the move towards a more logic-driven decision process has already begun and the winners are starting to show up in the data.

February 27, 2015

Capitalizing on the Random Walk (Part 2)

I wrote a blog post 3 ½ years ago about the topic of trading around positions. See part #1 of Capitalizing on the Random Walk

 

        “Our trading models tend to buy stocks that are recently out of favor and sell those recently in favor. Thus, to some extent, our actions have the effect of dampening extreme moves in either direction, and, as a result, reducing volatility in those stocks.” - James Simons, Legendary Investor of Renaissance Technology

        “I made my money by selling too soon.” – Bernard Baruch, Legendary Businessman

        When asked how he had become so rich?  He replied, “I sold too early.” - JP Morgan, Famous Financier

 

A smart client of ours asked the question, “how often should we trade to maximize the benefit of trading around positions?” In an ideal world, you would buy at the nadir and sell at the apex of any straight-line price increase.

    Example of a stock that trades from $40 up to $50 down to $30 then back to $40. The net profit for not trading is 0%. The maximum profit is a trading gap that times a sell at the apex of the trading range ($50). The fund is assumed to have a maximum position size of 10% and the starting position size at $40 is 6.6%.

                       

What this example illustrates is that if the price goes down (time is irrelevant because this would apply for 1 tick, 1 day, 3 days, etc.) you would want your position to be at 0% and when it rises, you would want to be at a full position. Clearly that is not realistic, but to understand the mechanics of the system it is important to understand the extremes. The counter-extreme is to not trade at all and return 0% which is the worst outcome in a mean-reversion trading pattern. So somewhere in between lies the hybrid of ideal and practical. The exact point is different for different managers, but I would say that you should set Trade Triggers (colored highlight rules if you are an Alpha Theory user) that alert you when gaps are greater than 1% or 1.5% or 2%, whatever allows for maximum profit capture per unit of acceptable inefficiency. Basically, you need to create a heuristic like “we trade when assets are 1% away from optimal and the difference is at least 50%.” Here’s an example:

Alert if:

1)      OPS = 0%

2)      If %FromOptimal > 1% and Max(%fromOptimal/CPS, %fromOptimal/OPS) > 50%

 

ASSET #1:

% from Optimal = 2%

CPS = 1%

OPS = 3%

Max(2%/1%,3%/2%)=100%. This asset would be highlighted.

 

ASSET #2:

% from Optimal = 3%

CPS = 7%

OPS = 10%

Max(3%/7%,3%/10%)=43%. This asset would NOT be highlighted.

 

It is important to remember that while this method is sub-optimal if the stock ever trades above the selling price it is vastly superior to No Trades.

Finally, for those with tax considerations there is a different constraint. Basically, I think it ends up being a different heuristic. Let’s say we come up with a 6/1 rule of thumb. If you’re 6 months away you’ll trade 1% differences, 5 months = 2%, 4 months = 3%, 3 months = 4%, 2 months = 5%, and 1 month = 6%. I’m not sure that is perfect, but there is DEFINITELY a huge value in waiting for Long Term treatment if the fund is tax sensitive.

July 18, 2014

Probability Inflation: The Risk of Ignoring Batting Average – Part 2

In my last post, I discussed how the probability of success in investing is grossly overestimated compared to historical batting average (funds assume 75% of success vs. their batting average of 55%). This causes miscalculations in portfolio allocation. In this post, I will discuss how Alpha Theory has been partially controlling for this phenomenon through our proprietary risk-adjusted return calculation (Alpha Theory Risk-Adjusted Return). Our method basically averages the arithmetic and geometric probability weighted returns. Note the difference between the Arithmetic and Geometric returns below.

Geometric return more heavily weights the downside node and reduces the risk-adjusted return for assets with high probabilities of extreme loss (see “Which Way is Up?” for further explanation). Not only does the geometric adjustment highlight the same gradation of the lower probabilities between the 75% and 55% arrays, it also is more intuitive to a portfolio manager. When surveyed, we found that portfolio managers would not size the top three positions equally when only shown the arithmetic return. There is an inherent heuristic that portfolio managers employ to control for this phenomenon. The problem is that heuristics are easily miscalculated and inconsistently applied.

Alpha Theory uses a hybrid Arithmetic/Geometric return to calculate the Alpha Theory Risk-Adjusted Return. This allows managers to properly account for portfolio impact and avoid heuristics. Downside is more impactful than upside in a compounding vehicle like a portfolio, so overemphasis of downside is practical. To properly allocate capital, it is critical for funds to first, make explicit forecasts of price targets and probability and then second, properly account for the asymmetry of upside and downside. This is difficult (impossible really) to accomplish without a systematic approach and we encourage every fund to capture and calculate risk-adjusted return for every investment in their portfolio.

In portfolio management, preventing loss is paramount. Using realistic probabilities, more closely in line with the fund’s historical batting average, and Alpha Theory Risk-Adjusted Return, will properly skew the portfolio towards those assets that have large asymmetry and little downside. In a compounding vehicle, like a portfolio, avoiding these “bad bets” will generate higher long-term geometric expected return, the ultimate goal of portfolio management.

June 17, 2014

Probability Inflation: The Risk of Ignoring Batting Average – Part 1

My company, Alpha Theory, started performing historical analysis of clients’ data about six months ago. We’ve only finished work on a dozen or so clients but one trend seems to be consistent, probability inflation. Let me explain what that means. Our clients use Alpha Theory to estimate the risk-adjusted return of each investment and use that information to properly allocate capital across their portfolio. Part of estimating risk-adjusted return is assigning probabilities to various potential outcomes. What we find is that clients generally have probabilities of success (scenarios where they make money) that fall in the 70-80% range. The issue is that their historical batting averages are more in the 50-60% range (batting average is how often they ACTUALLY make money on their bets).

"Of the almost 100 U.K. and U.S. fund managers in Investment Intelligence’s database, Chaban says, the best hit rate he’s seen is 64 percent; the median is just over 50 percent. " - Taras Chaban, chief executive officer of Investment Intelligence Ltd. (Bloomberg article)

Inflated probability of success causes two issues. One, the risk-adjusted return is inflated. Two, the probability of loss is too low which results in an underestimation of risk. The net effect is overly optimistic assumptions and bets on assets that are too risky.

Here’s an example. Below we have three potential investments with equal 75% probabilities of success. As you can see, the return and risk characteristics vary dramatically for each asset but the risk-adjusted return is a constant 30%. Imagine a portfolio manager deciding between this set of investment options with inflated probabilities and determining to weight all three positions equally.

                       

Now imagine a portfolio manager, presented with the same investment choices, but with more realistic probabilities of success (55% instead of 75%). There is no way that these would be equally sized. In fact, #3 wouldn’t even be considered.

 

The return reduction for investment #1 is 8%, which is meaningful, but nothing like that for #3, which falls from 30% to -5%! Assuming a 55% probability of success creates an entirely different (and more realistic) set of investment possibilities for the portfolio manager to choose between. The complexion of the portfolio changes to lower probability of downside bets. I strongly encourage funds to use more realistic probabilities (average closer to historical batting average). If not, they will almost certainly suffer from overexposure to the #3s of the investment world.

Be on the lookout for next month’s post discussing Alpha Theory’s novel approach to calculating return and its relevance to the issue of Probability Inflation.

 

December 31, 2013

Missing Message of Moneyball

“It’s about getting things down to one number. Using the stats the way we read them, we’ll find value in players that no one else can see. People are overlooked for a variety of biased reasons and perceived flaws. Age, appearance, personality…mathematics cut[s] straight through that. Billy, of the 20,000 notable players for us to consider, I believe that there is a championship team of 25 people that we can afford, because everyone else in baseball undervalues them.” - Peter Brand (played by Jonah Hill) tells his boss Billy Beane (played by Brad Pitt) in the movie “Moneyball”

I was reading an article in Institutional Investor about Moneyball’s applicability for hedge funds by Daniel Nadler. In the article, Mr. Nadler makes the cogent case that big data adoption in sports is a prelude to big data adoption in investing. His article crystalized a view for me that there is a dichotomy in the message of Moneyball. The two sides are that Moneyball makes decisions simple and Moneyball makes decisions complex. The complex interpretation of Moneyball looks at the advancement of quantitative analytics in sports and points to Billy Beane as the spark that lit the fire. Most professional teams have an on staff stat PhD and use complex camera systems to measure new statistical variables. Basketball has expanded from field goal percentage to field goal percentage per spot on the floor. Baseball has evolved from a batting average to a batting average per pitch location. There are even ways to score defensive position based on cameras measuring distance from opposing players. While I completely agree with the premise that, without Billy Beane, sports would not be as stat driven as they are today, I also believe that Moneyball’s lasting impact is that it focus on making decisions simple.

The simple message of Moneyball is that Billy Beane distilled the decision process into basic elements and made better decisions. A decision maker must determine their objective, then determine the variables that most directly impact the objective, and create a process using the variables to make decisions. In baseball, the objective is to win games. Billy Beane learned that On-Base Percentage (OBP) was the variable that most directly impacted winning percentage and he created a repeatable process using OBP to price baseball players so that he could make better draft and player management decisions. I believe, without question, this is the most important impact of Moneyball (for more on why a simple model is so important, check out my previous post: The Beauty of Robyn Dawes).

Is there a metric like On Base Percentage for investing? Let’s start by determining the objective. In baseball, it is maximizing winning percentage. In investing, it is maximizing risk-adjusted return. Next step, who are the players on the investing baseball team? It is the stocks, bonds, real estate, commodities, etc. that we invest in. What is the variable for each investment that has the greatest bearing on my portfolio’s objective of maximizing risk-adjusted return? It is the Expected Return (i.e. how much I'm going to make if I'm right vs. how much I'll lose if I'm wrong). Of course there are other factors, but this is the one with the greatest influence. So step one in applying Moneyball to hedge funds is to calculate an Expected Return for every investment in your portfolio (upside * probability of upside + downside * probability of downside). This gives the firm the "one number" upon which all the rest of the investment process can build. Over time, factoring in the other variables that influence your objectives will make the decision process better and more repeatable. Like the natural evolution of Moneyball from simple to complex.