Yesterday I wrote an early version of financial software to help users improve their investing portfolios.  This software has the ability to solve financial problems in a very different way than taught in graduate-level finance classes.   Rather than relying solely on a type of mathematics called statistic analysis, Sigma1 software uses techniques from computer science called artificial intelligence or AI.  (I prefer the term machine intelligence because there is nothing artificial about the intelligence results produced by a solid AI algorithm.  If you doubt this, I challenge you to beat Chessmaster 11 running on your PC… on max difficulty.)

My idea has been to develop a sophisticated program that would allow institutional investors such as fund managers to  ”plug in” their proprietary valuation models and come up with solid portfolios in minutes or hours, rather than days or weeks using brute-force techniques.    As I was working, I realized that smaller “normal” investors could also benefit from a simplified version of Sigma1 software.

Rather than sell this lite version of portfolio-opt software I may provide a free version on a website.  The free version would have limitations on both the number of securities and the “depth” of analysis and reporting.  For example the user may only be able to enter a maximum of 20 securities in their current (or proposed) starting portfolio.  The free web version would quickly suggest an asset-allocation mix of those securities that is (potentially) safer with the same expected return or (potentially) equally safe with a higher expected return.

If the free web version is popular enough, Sigma1 may introduce a paid web subscription service that allows a larger portfolio, a wider selection of securities, more detailed reports and even sample portfolios to “blend” with the investor’s favorite tickers.

Even after the free web version is released, I plan to refine the advanced institutional version of the software.  I plan to use it to improve the composition of the Sigma1 proprietary trading fund.  I also intend to develop a world-class product that institutional investors will want to have access to… for a very reasonable price.

At this time I have zero interest in sharing the source code or specific concepts underlying the current and future Sigma1 software.  Many of these ideas stem from work in my undergrad engineering and computer science studies.  They have developed in my graduate work in finance and engineering.   The realization that the techniques I have developed for engineering, game-theory, poker and number theory apply most directly to portfolio construction and optimization hints at the possibility that I have hit upon one of those rare ideas that strike gold.  Not academic gold; real “gold” with real financial value.

I love academic research and open-source software.  I don’t intend to keep the concepts and code that Sigma1 is developing locked up forever.  If the Sigma1 financial software is financially successful enough, I hope to release pieces of it to the open-source community over time.  (Conversely, if the software does  not ultimately find a lucrative market, I will eventually release it too )

Portfolio Optimization Software: Tech Speak

Yesterday I wrote the key pieces of an evolutionary algorithm to build and optimize securities portfolios, namely mutation and crossover.   The remaining pieces: heuristics and selection should be relatively easy to code.   The coding and testing was very quick  1) because I’ve written GA’s (EA’s) many times before, 2) because I had 2 days to think about it as I was driving and 3) because I wrote it in Ruby.

Based on previous experience (and depending on the complexity of the heuristics), run-times should be swift for populations of 200 and portfolios of 500 securities or less.  In previous research I’ve been able to use distributed computing when the heuristics/analysis dominated run-time.  Generally the GA has not been the limiting factor for speed.

I plan to start with relatively simple heuristics to test the portfolio-optimization software.  Likely the first test will merely compute the (near-optimal) efficient frontier for a basket of securities, plotting 3-year standard deviation of various portfolios on the frontier versus expected return.  If I wish I may even compare the results to efficient frontiers constructed with classic methods using covariance matrices.

Once I create a Ruby prototype I plan to re-code the software in C/C++, both for execution speed and for the relative IP-protection provided by releasing only compiled binary executables.

{EAV:7c9500fb17420345}

I started Sigma1 with $35,000 in seed capital, a Linux workstation and a domain name I acquired in auction for $760.  The original plan was to create a revolutionary hedge fund with accredited investors as clients.  I started studying for the Series 65 exam and all went well until I started reading about securities laws and various legal case studies.  I gradually realized two things:

1. U.S. Securities Law is very restrictive, even for “lightly regulated” hedge funds
2. The legal start-up costs for a hedge fund were much higher than I anticipated

The first realization was the most devastating to my plans.  The innovative fee structure I wished to use was likely to face serious legal challenges to implement. Without a revolutionary fee structure, more favorable to clients, the Sigma1 Fund would be hard to differentiate from the hundreds of other funds already available.

The second objective of Sigma1 has been to develop proprietary financial software.  Until now the Sigma1 Proprietary Trading Fund has been constructed based on research, pencil-and-paper securities analysis and some rudimentary Excel simulations.  Some quantitative analysis has been applied, but without the mathematical rigor I prefer.   That is about to change.

I recently devised a way to apply techniques developed while studying Electrical Engineering and Finance in grad school.  In a nutshell, I will apply genetic algorithms to optimize portfolio construction.  The same fundamental techniques my electrical engineering colleagues and I used to explore and optimize around the random perturbations inherent in fabricated silicon circuits can be used to optimize portfolios by efficiently exploiting conventional (linear) and unconventional (non-linear) correlations between diverse assets.

I have sequestered myself in a beautiful, tranquil location while on a well-earned sabbatical from work.  While genetic algorithms (also called evolutionary algorithms) will be a significant part of the software suite I will develop, I also intend to incorporate heuristics and machine-learning techniques as well.  Similarly I intend to use techniques from CAPM such as efficient-frontiers, but only as a first-order guide.  Many of the limitations of CAPM (and Fama-French enhancements thereof) consist on their intrinsic reliance on Gaussian or “normal-distribution” statistical models.  Such models do not properly model long-tail events, nor asymmetrical distributions, nor even log-normal distributions.  Classic CAPM models even struggle with geometric-mean of expected or passed returns and generally use arithmetic means to preserve the use of linear systems analysis.  Genetic algorithms and other AI techniques need not use such assumptions as a mathematical crutch.   The software I intend to develop should be able to find near-optimal solutions to financial problems that classic statistical methods “solve” only by making grossly inaccurate assumptions about probability distributions.

My intention is to develop one or more software products for fund managers that will aid in portfolio analysis, construction and refinement.

1. Diversify with non-traditional and non-Wall Street investments.  For example real real estate.
2. Lower your ETF (and mutual fund) expense ratios.  The ETF revolution is constantly competing for your money with an expense-ratio war.  For instance, consider VEA vs EFA.
3. Consider employing a buy-write strategy, either on your own, or via an ETF such as PBP as a modest part of your investing strategy.
4. Improve your investment tax savvy. Know your ETF and mutual fund distribution dates, and consider selling before them (if you are going to sell any way).  Use option-strategies to lock in short-term gains until they become long-term capital gains.  Use tax-deferred accounts for high-tax investments (like junk bonds).
5. Re-balance and re-align with your long-term investment allocation strategy.

• 50 shares EFA
• 100 shares SCHB
• 100 shares VEA
• 100 shares JNK
• 200 shares PBP
• 100 shares VTI
• 100 shares SPY

NAV: 36,604.55 USD.

Even though I have been emulate the CBOE S&P 500 BuyWrite Index (BXM) for somewhat less than PBP’s 0.75% expense ratio, I decided eat some crow and just buy some PBP. This saves me the hassle of trading options every month.

The fund is now has no short positions, other than cash, which currently costs over 1.6% to borrow. Current closing NAV of the Sigma1 Proprietary Trading Fund is $36,571.

If you had to invest $1,000,000 for a client, and your had only two choices, which would you choose?   (A) “Invest” the whole $1,000,000 on red or black at the roulette wheel.  (B) “Invest” on red or black $1000 at a time, one thousand times.

My friend said he knew the right answer, to that question and most of the others.  I believe he was offered this particular job, but declined it in lieu of better offers elsewhere.  Anyhow, he asked what my answer would be.

I said (B).  If single zero roulette, the client can expect to lose on 1/37 (about 2.7%);  if double zero, 2/38 or about 5.3%.   My friend said, sorry, wrong answer.  If you lose money for a high-net-worth client, even 2.7%, they are likely to be disappointed and take their business elsewhere.  If you double their money, a roughly 50/50 proposition, you will have an ecstatic client who will stick their $2,000,000 with you for years.  If you lose their whole $1,000,000 they will be disappointed and walk away, but “them’s the breaks.”

This story resonates with me to this day.  This is an absurd question from a financial standpoint, but it is a powerful question on ethics.  The business rationale behind answer (A) is valid.  However, I chose to work for a company where the correct answer is (B).

On a separate note I’ve been bogging up a storm at my other other investing blog at Balhiser Investing.  There, I try to keep the topics less technical and more accessible to a wider investing audience.

* Sigma1 is a proprietary trading group fund, and is not currently available to outside investment.  It is currently structured as a long-short macro-centric hedge fund with long positions in equities (domestic and foreign) and junk bonds, and short positions in international bond ETFs.

So, what is my opinion on US equities?   Neutral to mildly bullish.

The fact of the matter is that US equities are leading economic indicators.  Unless you believe in momentum investing, which I don’t (see disclaimer), past market moments do not predict similar future market movements.  To the contrary, from a value investing standpoint, sharp upward market fluctuations simply presage undesirable valuations.  Or in plain English,  when the stock market skyrockets, be cautious.  That is why I’m not a fan of “plain English”;  it is too untextured, abstract,  and strangely foreign to my financial ear.

My opinion has very little to do with my asset allocation.  In painfully plain speak, “I pretty much stay the course with my investment choices, no matter how I feel at the time.”  In other words, I stick to a purposely pseudo-static asset allocation strategy with the empirically grounded assumption that impromptu reallocations increase standard deviations without increasing alpha.

I apologize for the last two sentences.

My opinion, for what it worth, is that I’m less certain about my bullish equity positions.  Simultaneously, I’m quite bearish on US debt securities… like US Treasuries (or as the WSJ writes it, Treasurys.)

All said, I am have not significantly changed the holdings of Sigma1.  Not yet.

Disclaimer:  Momentum investing is, in my opinion, only viable on a scale of seconds or microseconds in terms of algorithmic or “high frequency” trading.  In general it is a guise for other investment bets, some of which pay off and some of which do not.