The four categories of investment models offered in their entirety this past year to subscribers are detailed below. Each category represents very different models formed into consistent samples of portfolios both weekly and monthly for two reasons: (1) To test that the financial research and algorithms that each is based upon can actually perform as advertised, and (2) To give investors frequent opportunities to join a portfolio at regular formation intervals or select from among several portfolios at anytime within each category that they think will outperform.
The four different types of momentum and value investment models run this year included:
The Momentum Breakout Portfolio is a weekly replenishment model for increasing the frequency of obtaining short-term high volatility stock returns. This methodology is based on my doctoral research published in 2016 that showed through multiple discriminant analysis that the frequency of selecting 10%+ price gains could be increased by more than 4 times expected market rates. A summary of that study is available here.
The Forensic (Negative/Positive) Portfolios are monthly generated, buy/hold, experimental value portfolios based on two top bankruptcy models and one earnings manipulation model from the field of financial forensics. The combination of all three algorithms employs 22 different fundamental ratios, valuations, and variables that the researchers used to asses the solvency and stability of a firm.
The Piotroski Enhanced Value Portfolios are monthly generated, buy/hold, annually tracked portfolios based on documented abnormal returns in financial literature. Since its publication in 2000 by Joseph Piotroski, the value model has remained the premier value model in financial literature despite regular retests and challenges by financial scholars with new models. One of the most recent evaluations, by Amor-Tapia & Tasc贸n (2016), again confirmed the model significantly outperformed three other value contenders.
The Russell 3000 Anomaly Stock Portfolio is an experimental portfolio based on documented abnormal returns from the annual reconstitution of the Russell 3000 stock index. This model tests the documented momentum phenomenon of the top stocks selected for addition to the Russell Index in the annual June reconstitution period. Another test will be run in 2018.
Financial Returns for All Portfolios at Year End 2017
|Model (Value / Breakout)||Returns YTD||Number of Periods|
|1. Weekly Momentum Breakouts||40.98%*||40 Weeks|
|2. Forensic Negative Selections|
|July (-) Forensic Portfolio||70.50%*||5 Months+|
|Aug (-) Forensic Portfolio||40.71%*||4 Months+|
|Sep (-) Forensic Portfolio||21.50%*||3 Months+|
|Oct (-) Forensic Portfolio||-8.52%||2 Months+|
|Nov (-) Forensic Portfolio||0.04%||1 Month+|
|Dec (-) Forensic Portfolio||3.01%*||2 Weeks|
|Forensic Positive Selections|
|July (+) Forensic Portfolio||13.46%*||5 Months+|
|Aug (+) Forensic Portfolio||11.25%*||4 Months+|
|Sep (+) Forensic Portfolio||5.98%||3 Months+|
|Oct (+) Forensic Portfolio||0.98%||2 Months+|
|Nov (+) Forensic Portfolio||-2.43%||1 Month+|
|Dec (+) Forensic Portfolio||-1.35%||2 Weeks|
|3. Piotroski Enhanced Value|
|August Portfolio||7.91%||4 Months+|
|September Portfolio||9.76%*||3 Months+|
|October Portfolio||5.68%||2 Months+|
|November Portfolio||-0.29%||1 Month+|
|December Portfolio||1.61%*||2 Weeks|
|4. Russell 3000 Anomaly Portfolio||45.11%*||5 Months+|
* All portfolios with returns that outperformed the S&P 500 in their respective time periods.
Investment Cautions to Live By
First, I’ve included a few foundational investing principles worth reading that are applicable to the stock selection models I offer. As a finance PhD and certified fraud examiner I have seen a lot of BS in the financial markets. A central guiding principle is that if anything looks too good to be true, it probably is. But if you still want to try it, only risk what won’t disturb a good night’s sleep. Here are some investment cautions that may benefit you:
“All Models Are Wrong, Some Are Useful.” Applying models in the most appropriate way is the key to judging utility. Excellent article to manage your expectations when deciding to trust someone else’s trading system or explanation of how something may (or may not) work.
“Lies, damned lies… and back tests” (.pdf) If you’re following a system with “proven success” based exclusively on back-testing, you’re wasting your time and probably your money too. Dozens of very important hazards are documented here that show why forward testing remains the best way to assess reliability and utility. You also have my permission to slap me if I ever annualize future returns in any of my marketing to project out imaginary 700% gains based on some artificial performance baseline. Watch out for this kind of financial shenanigans.
Even if something works, if it doesn’t help you, don’t use it. I’m not making the case that any of these financial models presented here are invaluable or even applicable to your investing goals. You need to carefully and independently evaluate that for yourself. Details on the Weekly Momentum Breakouts
This model is what brought me to the Seeking Alpha platform at the start of 2017 — with a desire to publicly establish a forward testing track record. The breakout forecast was created from my doctoral dissertation building on the methods of Altman (1964) and Taffler (1984) who applied predictive discriminant analysis to classify firms at risk of bankruptcy. I extended their approach by initially evaluating 24 variables simultaneously from behavioral, fundamental, and technical theories to classify different conditions of stock price momentum. I have since greatly expanded the original study to more than 40 variables over significantly longer historical periods time, but nothing beats the raw application of actual forward selection. My selections and results are all documented herein. As with all these financial models, they are works in progress to frame a better understanding of ways to benefit from an uncertain market.
** This next section is intended to answer many of the frequently asked questions I receive about the breakout forecast selections. You can skip down to the other portfolio results below **
What is this Breakout method trying to accomplish?
These Breakout selections are focused on a very small population of stocks in the market capable of +/- 10% daily and weekly moves. For example, on a typical day fewer than 40 stocks out of more than 4,300 stocks (non-OTC, ex-funds, share price > $2) gain more than 10% in a day. That represents a segment of less than 1% of the stocks on the NYSE, NYSE Mkt, and NASDAQ. This method is trying to improve that frequency of occurrence using the strongest variables that emerged from the multiple discriminant analysis in my ongoing research.
While variables were selected and parameters calculated for each of seven different momentum conditions both daily and weekly in the original study, the Breakout Model offered here is primarily focused on Segment 6 (Positive Momentum Acceleration) as shown in the graph below.
Additionally, as I run the selection screens I try to limit selections to stocks with prices greater than $2/share and preferably greater than $5/share. I understand that this higher share price range is more attractive to most investors and avoids penny-stock speculation and higher risk and volatility.
However, reducing risk and volatility with a $2/share price limit also greatly reduces the available sample of stocks capable of producing greater than 10% short term returns. For example, when a $2/share limit is applied the number of 10%+ gainers is reduced by 44% on a typical day. At a $5/share cut-off as much as 68% the 10%+ gainers are no longer available for selection. Because I don’t want to make this a penny-stock chasing model, this is the challenging trade-off that occurs in this segment. As challenging as the effort is to find positive +10% moves in a week, the sample of available stocks with -10% moves in a week is even smaller on average. Keep that in mind as you leverage the selections.
Breakout Frequency Table
The objective of the Momentum Breakout model is to increase the frequency, i.e. the rate over time, for selecting stocks that make greater than 10% moves. I’ve talked a bit about the increased rates of 5%+, 10%+ and 15%+ etc. moves compared to expected market rates and developed a chart below to illustrate the resulting difference between the model and the broader market.
The frequency of occurrence in the breakout model of 10%+, 15%+, 20%+ and 30%+ compared to the broader stock market of all the same type of stocks (ex-funds, non-OTC, share price > $2) continues to produce rates with statistically significant differences well above 3 times the equivalent population of stocks in the broader market:
One SA author explains that if you can capture fifty consecutive 10% gains you can turn $10k into $1,000,000. The odds are quite long, but so far I’ve collected a smattering of 79 stock moves greater than 10% in 40 weekly portfolios (24.7% of the stocks). So please just avoid any downturns and let me know if that strategy to $1,000,000 ever works out for you!
The other important component in this model is time. The time horizon in this initial 2017 study has been arbitrarily set to one week for a variety of reasons related to the initial publication and towards generating a high frequency dataset to more easily validate significance. We know from Jegadeesh & Titman (1993) as well as Fama & French (2008) that price momentum is based on the observed phenomenon,
where stocks with low returns over the last year tend to have low returns for the next few months and stocks with high past returns tend to have high future returns (Fama & French, 2008, p. 1653)
The question that still lingers is what is the optimal period of time to derive the best momentum results? 1 year? 1 month? 1 week? Some people have looked to use the Breakout Forecast for buy/sell points or to produce a pass/fail percentage of picks that were missed each week to assign a score to the model that way. That is not the way a frequency model is best measured. I will however introduce a new portfolio in 2018 with buy/sell decisions that can be appropriately measured in that way.
Evaluating Momentum Holding Periods and Buy/Hold Strategy
Since I still don’t know what period of time is the optimum holding period for the highest frequency of greater than 10% gains, I considered another perspective. I know that when using the arbitrary period of 1 week (4 or 5 trading days) this model is consistently outperforming the market at more than 4 times the expected market frequency. So what if I take a look at longer momentum survivors? Can we see a consistent decay in performance among the top stock selections? Can I further optimize a buy/hold approach knowing we would all agree to the dump the worst stocks as early as possible?
Perhaps the best application of these volatile breakout selections is to set percentage gain targets over weekly (or longer) periods keeping past probabilities in mind and see if there is a more optimal profitable return period than one week. Determining what the optimum holding period should be for these stocks will definitely be a profitable undertaking for a future study, limited only by time and resources.
Indexing the Breakout Momentum Returns
Lastly, I continue to advance the breakout model as originally designed in my published research, as a system that generates more than 4 to 5 times the expected market frequency of weekly breakout returns. However, most people don’t think in terms of frequencies and really prefer to assess the selection risk with a visual form of indexing against a benchmark like the S&P 500. Which leads to accommodating another form of measurement:
So after I piece together the end-of-week results for each of the momentum breakout selection weeks while eliminating all the intervening gaps and recording the appropriate S&P 500 returns for each week, I get the resulting performance chart above. The average weekly return of all 8 stocks is 1.02% with a cumulative return of +40.98% with the following sample standard deviation and variance:
It does not take into account any transaction costs of over 300 trades (In order to improve testing of the methodology I deliberately select eight different stocks every week), entry/exit slippage, taxes, fees and other factors. Nor does it permit any dumping of obvious intraweek losers, nor allow the cashing out of any large gainers before the end of the week — but it does give a view of performance against the S&P 500 that some significant profitability may be achievable from week to week. If you would like more wonky details with a link to my dissertation it is available here.
Some of the best stocks (80%+ YTD) selected this year using the Breakout Forecast include: Sangamo Therapeutics, Inc. (SGMO) +271.59%, RLJ Entertainment (RLJE) +99.48%, KEMET Corporation (KEM) +100.77%, XOMA Corporation (XOMA) +426.94%, Fusion Telecommunications International (FSNN) +120.48%, ION Geophysical (IO) +157.69%, 22nd Century Group (XXII) +157.28%, Abeona Therapeutics, Inc (ABEO) +175.00%, QuinStreet, Inc (QNST) +86.85%, Vital Therapies (VTL) +81.97%, Dicerna Pharmaceuticals (DRNA) +94.25%, Town Sports International Holdings (CLUB) +88.52%, Limelight Networks (LLNW) +89.47%, NL Industries (NL) +83.70%.
The Forensic Portfolio Selections
The next set of models I offer are the Forensic Model value selections. The positive and negative scoring forensic models arose out of curiosity about whether the combined application of two top bankruptcy models and one earnings manipulation model could produce abnormal returns in short-term forward testing. According to research conducted by Beneish, Lee, & Nichols (2013),
“[The evidence] indicates that [the Beneish] M-score has significant ability to predict one-year-ahead cross-sectional returns. Our results show that this predictive power does not come from its correlation with value, momentum, size, accruals, or short interest” (p. 65).
The adverse scoring forensic portfolios with the most adverse scores across all three of the academic forensic models continue to significantly outperform both the market as well as the portfolios with the highest positive forensic scores. In particular, the adverse forensic portfolios for July, August and September saw strong gains this year and are significantly outperforming the S&P 500 since their respective formation dates.
The selections for both the positive and adverse scores are updated every month using the highest and lowing scoring stocks across all three forensic models (Altman Z-score, Ohlson O-score, and the Beneish M-score). Unlike the Breakout Model, the Forensic Model allows for continuation of the same qualifying stocks from one period to the next out to a full year. Also I have set the number of test portfolios for each of the adverse and positive scoring methods at six portfolios per year. A new set of portfolios will replace these 2017 portfolios in each corresponding month in 2018. In this way we can see if the Beneish M-score and other forensic algorithms may contribute to excess annual returns.
Returns of the adverse scoring forensic portfolios:
The working assumption is that the negatively scoring forensic stock portfolios will have a correspondingly adverse stock return over a medium to long term investment period. However, results so far in this informal forensic study show significantly better returns among the adverse scoring portfolios than using the most positive scoring stocks across the Beneish M-score, Altman Z-score and the Olson O-score as shown in the portfolio chart below:
The Piotroski Enhanced Value Portfolio
The next set of models I regularly offer are the Piotroski Enhanced Value Portfolio selections with a one-year investment target. This Piotroski F-score model has emerged from the financial literature as one of the better value stock selections tested by financial scholars over the past 17 years. I have added a few minor enhancements to avoid penny-stocks and some adverse financial outliers. Running multiple one-year portfolios from a new Piotroski selection each month may also provide a reasonable forward testing approach of the effectiveness of this standout value algorithm.
The early results confirm the potential for a solid low risk annualized returns. So far only two of the Piotroski portfolios are outperforming the S&P 500 in their respective periods. There is also some slight overlap in the month to month stock selections and that may add to the credibility of the F-score selection process on an annual basis.
The Russell 3000 Anomaly Stock Portfolio
The final model I currently track on a regular basis is the Russell 3000 Anomaly Stock portfolio. This is another well documented anomaly that generates abnormal returns. I decided to take a sample of the top 10 best performing stocks added to the Russell 3000 index in their annual reconstitution process every June on the basis that these might be among the best momentum performers throughout 2017.
Measurable price effects of the Russell 3000 annual index reconstitution have been documented for both stock additions and deletions (Chang, Hong, & Liskovich, 2013).
Similarly, positive S&P 500 Index effects have been measured at around 5% to 7% in the month following the addition announcement with a large fraction of the gains remaining permanent.
Stock additions to the Russell 3000 index leads to a “dramatic increase” in trading volume ratio in the month of June (Chang et al., 2013).
Historical returns of the Russell 3000 reconstitution stocks have been tracked closely since 2000 and are summarized in my initial study here. I plan to track this anomaly for a full year and then create a new Russell 3000 portfolio for 2018. So far the strong results of +45.11% demonstrate some promising excess returns YTD. As the chart for 2017 shows, the initial momentum from the reconstitution date is very strong and then by October has peaked. It will be interesting to see if these stocks remain some of the top performers in the Russell 3000 by the next index reconstitution date in June 2018.
I am as interested in finding alpha as the next investor or financial researcher. I continue to invest considerable time, resources, and energy in searching through different anomalies, models, and financial literature on the latest market discoveries. All of my systems are applied in my own private equity fund trading and I have realized substantially better results from what I have learned over the years. Behavioral, technical, and fundamental analysis are all of great interest to me as I am certain they each comprise critical pieces of the puzzle to answer the question, “what really matters in assessing the best potential return on investment of any asset?”
My forward testing projects have now merged into a subscription based Marketplace offering here on Seeking Alpha. The detailed composition of each of these portfolios is available to subscribers. I’m still running financial experiments and thoroughly enjoy finding good ways to add value, especially for those of you willing to purchase a subscription membership and try to get every advantage in your market trading. I would be glad to have you join me as I continue this journey wherever it leads — and for as long as I decide to keep publishing!
Many thanks to the dozens of subscribers who joined me this year even long before any meaningful results were realized. Thank you, and I wish you all many blessing — especially the riches of time with your friends and family in the coming New Year!
Disclosure: I am/we are long XXII.
I wrote this article myself, and it expresses my own opinions. I am not receiving compensation for it (other than from Seeking Alpha). I have no business relationship with any company whose stock is mentioned in this article.
Editor’s Note: This article covers one or more stocks trading at less than $1 per share and/or with less than a $100 million market cap. Please be aware of the risks associated with these stocks.
About this article:ExpandAuthor payment: $35 + $0.01/page view. Authors of PRO articles receive a minimum guaranteed payment of $150-500.Tagged: Investing Ideas, Quick Picks & ListsWant to share your opinion on this article? Add a comment.Disagree with this article? Submit your own.To report a factual error in this article, click here