Scientific Advisory Board Conference, San Diego

September 1, 2016

Robert A. Gillam, CFA Chief Investment Officer McKinley Capital Management, LLC
Gregory S. Samorajski, CFA Director of Investments McKinley Capital Management, LLC
John B. Guerard Jr., Ph.D. Director of Quantitative Research McKinley Capital Management, LLC

McKinley Capital Management, LLC (“McKinley Capital”) is a disciplined, systematic, global growth equity manager. Our internal Quantitative Research Team works daily to refine our proprietary investment model. This team is headed by Dr. John Guerard1. However, specific technical expertise can be supplemented and amplified with independent experts and advisors. To that end, McKinley Capital established a Scientific Advisory Board. Members of the advisory board work with McKinley Capital’s CIO, Rob Gillam, Dr. John Guerard, and our Quantitative Research Team on ideas designed to explore mitigating the downside risk of portfolio returns without sacrificing upside potential.

Executive Summary

On September 29th, 2016, at the University of California San Diego, McKinley Capital convened a meeting of its Scientific Advisory Board. The conference was opened by Rob Gillam and Dr. John Guerard. They introduced the four featured presenters and their research topics. Dr. Ian Domowitz, of Investment Technology Group, Inc. (“ITG”), discussed quantitative procedures which can be used to integrate fundamentally selected core holdings into a security count constrained quantitatively formed portfolio. Rochester Cahan, of Empirical Research Partners, LLC, addressed the use of text recognition protocols to analyze earnings call transcripts. Dr. José Menchero, of Bloomberg, LP, presented a framework which can be used to handle a large number of optimization variables in a multi-asset class context. Dr. Harry Markowitz presented research on the persistence of the “small cap” effect. Brief summaries of each presentation are provided below. Your account representative can provide you with additional detailed information upon request.

Doughnuts: A Picture of Optimization Applied to Smart Alpha
Ian Domowitz, Ameya Moghe
Investment Technology Group, Inc. (“ITG”)

Dr. Domowitz asks us to imagine a world of fundamental portfolio management. In this world, fundamental managers develop a limited number (30 for example) of “good” stock ideas. The manager subjectively weights those stocks into a portfolio; in a way which best express the ideas of the manager. Dr. Domowitz supposes that fundamental managers resist subjecting their picks to an optimization system out of a belief that their fundamental opinions might be distorted with optimization. Yet, these managers also understand that such a concentrated portfolio might have an unacceptably high level of tracking error. Dr. Domowitz proposes a doughnut methodology to address both concerns. A portion of the portfolio (50% to 100%) is devoted to the manager specified core picks and weights. This portion is the core, center, or the “hole” of the doughnut. The balance of the portfolio, called the doughnut, is selected using mathematical optimization to offset some of the systematic exposures of the fundamental core.

To illustrate his approach, Dr. Domowitz forms a sample of 24 hypothetical U.S. stock fundamental core portfolios and measures returns from 2005 to 2015. The portfolios are formed in a variety of ways, but each contains 30 stocks. The core portfolios have realized annualized returns that range from 1.5% to 15% – in an era where the annualized return of the Russell 1000 Growth Index is approximately 8%. For each portfolio, he analyzes core weights of 100%, 75%, 67%, and 50% with the balance allocated to the optimized doughnut. The optimizer is calibrated to minimize a combination of tracking error and transactions costs, with the greater weight on tracking error. There is a limit of 75 stocks for the composite portfolios.

Dr. Domowitz finds that in almost every scenario, transaction costs are significantly reduced – due to the focus on transaction costs in the doughnut portion. In almost every scenario, the composite portfolio has less modeled total risk than the corresponding stand-alone core portfolio. On average, the composite portfolios have higher Sharpe Ratios than the stand-alone core portfolios. The increase in Sharpe Ratio is dramatic for those core portfolios with realized returns lower than the benchmark. In those cases, adding the doughnut both increases return and reduces total risk. Even for those core portfolios with realized returns in excess of the benchmark, the reduction in Sharpe Ratio is not significant. In those cases, the drag on return is often offset by a reduction in risk. Usually, all of these effects are magnified as the amount allocated to the doughnut increases. Dr. Domowitz concludes that the doughnut approach to portfolio construction is something that might benefit a concentrated fundamental manager who is concerned with excess risk.

The adaptation of this doughnut research – taking a small handful of benchmark weights and surrounding them with an optimized McKinley Capital portfolio – may prove to be better than an equal active risk weighting.

Getting Sentimental: Conference Call Sentiment and Stock Returns
Rochester H. Cahan
Empirical Research Partners, LLC

Mr. Cahan sets the groundwork for his study by computing long-term top minus bottom decile ICs for 41 standard factors, including components and subcomponents of McKinley Capital’s momentum and earnings based model. He finds that on a raw and on a risk adjusted basis, the McKinley Capital factors rank among the best, particularly the forecasted earnings acceleration factor. Mr. Cahan also finds that the AdaBoost machine learning approach performs well when applied to all 41 factors.

Mr. Cahan is a leader in the application of text recognition protocols as a way to measure the sentiment level (positive to negative) of a news story about a company. McKinley Capital incorporates news sentiment as a penalty function in the computation of its momentum scores. Large negative changes in sentiment are often associated with deteriorating momentum. In this study, Mr. Cahan seeks to apply these techniques to the analysis of company conference call transcripts – typically earnings calls. While the study is global, most of the conference call data is concentrated in U.S., U.K., and Canadian companies. From 2010 to 2015, he measured sentiment separately for management comments and Q&A comments. In testing the efficacy of these sentiment indicators, Rochester discovers that Q&A sentiment is more powerful. In fact, on a stand-alone basis, Q&A sentiment is one of the top five factors. On a risk-adjusted basis, this indicator ranks 13th of the 41 tested factors. None of the tested factors represent pure factor returns – the factors are not understood to be independent. It is possible that Q&A sentiment proxies for some of the other tested factors.2 Mr. Cahan concludes, however, that the inclusion of Q&A sentiment as one component of other larger models has the potential to enhance performance.

Based on the results of Q&A sentiment as a potentially efficacious source of alpha, McKinley Capital will study whether the incorporation of Q&A sentiment can potentially enhance our firm’s specific investment model.

Multi-Asset Class Risk Models
Overcoming the Curse of Dimensionality
José Menchero
Bloomberg, LP

In his highly technical paper, Dr. Menchero discusses the problems associated with multi-asset class portfolio risk measurement and optimization. For example, a portfolio might be composed of equities, fixed income, and commodities. Each of these major asset classes is composed of a number of local markets – U.S., Canada, U.K., Japan, Europe, etc. Finally, returns in each of these local markets are modeled by a large number of factors. José shows that, as a practical matter, it is not possible to calculate all of the sample estimates required to compute a full factor covariance matrix. There are simply more parameters to estimate than data available. Dr. Menchero refers to this problem as the curse of dimensionality. The problem is particularly acute for portfolios formed through optimizers, since optimizers rely heavily on robust covariance matrices. Dr. Menchero finds that the realized risk of most optimized portfolios significantly exceeds model risk, and that neither ex-post nor out-of-sample performance is well-predicted by ex-ante forecasts. Dr. Menchero concludes that the acid test of any procedure used to specify a correlation matrix is how it performs in a portfolio optimization environment.

Because it is difficult, if not impossible, to specify covariance matrices using sample statistics alone, a simplified method must be used. In his presentation, Dr. Menchero compares several methods that are often used to address the specification issue within the equity asset class. While a description of each method is beyond the scope of this summary, we note that José compares the efficacy of the following techniques: principal components analysis, random matrix theory, time series approaches, Eigen-adjusted methods, and a new proprietary Bloomberg technique (MAC2). The Bloomberg technique blends limited amount sample correlation calculations with empirically estimated principal components to “fill in the gaps”. Dr. Menchero tested the alternatives from January 2001 through August 2014, and finds that the new Bloomberg blended methodology compares favorably with the other approaches. In particular, Dr. Menchero finds that the new Bloomberg MAC2 model significantly outperforms its original MAC1 model.

McKinley Capital is a leader in the comparative study of quantitative risk and optimization models in conjunction with McKinley Capital’s alpha models. The new Bloomberg model is a cross-country, cross-asset, and cross-correlation methodology that could be used to value publicly traded assets. The firm looks forward to continuing to test these kinds of models in future studies.

The Impermanence of the Small Cap Premium
Wynce Lam, CFA, Harry M. Markowitz, Sheldon P. McFarland

In 1981, Rolf W. Banz published a seminal study, showing that U.S. small capitalization (“cap”) stocks outperformed large cap stocks on a risk-adjusted basis.3 Since that study, academics have come to different conclusions about the persistence of the small cap premium. Dr. Markowitz uses a Bayesian model and monthly index returns from 1926 to 2012 to study the persistence of the small cap effect. The researchers look at the market for U.S. stocks separately for growth and value stocks. The pre-Banz time period is defined as 1926 through the end of 1981. The post-Banz time period is defined as the beginning of 1982 through the end of 2012. The presenters conclude that in the value universe, the pre-Banz small cap premium most likely persisted into the post-Banz period at a somewhat lower level of volatility. However, in the growth universe, the pre-Banz small cap premium most likely disappeared and possibly transformed into a large cap premium.

This research confirms McKinley Capital’s decision to offer all cap, large cap, and small cap portfolio management options —all without a planned relative size bias.

Conclusion

McKinley Capital’s Scientific Advisory Board performs an important role – research and discussion with members of our Scientific Advisory Board enhances McKinley Capital’s proprietary model and helps optimize up/down capture. Working with thought leaders in the industry allows McKinley Capital to harness their insight and apply the research in a McKinley Capital specific way.

¹A list of select journal articles published by Dr. Guerard and the Scientific Advisory Board members is included in the references.
There does not appear to be a high correlation between Q&A sentiment and the McKinley Capital earnings acceleration variable. Mr. Cahan measured it at 0.06.
3 Using a single-period capital asset pricing model (“CAPM”) framework.
4 As a firm, McKinley Capital does not express an opinion on the question of the possible existence of a small cap premium; whether in the growth, value, U.S., or non-U.S. markets. Any portfolio exposure to size (relative to the appropriate benchmark) is opportunistic, dynamic, and bottom-up based on the firm’s investment process.

References

  • Banz, Rolf W., “The Relationship Between Return and Market Value of Common Stocks.” Journal of Financial Economics, 9 (1981), 3-18.
  • Beheshti, B. “A Note on the Integration of the Alpha Alignment Factor and Earnings Forecasting Models in Producing More Efficient Markowitz Frontiers.” International Journal of Forecasting. 31, Issue 2 (2015), 582-584.
  • Brown, L.D., Zhou, L. “Interactions between Analysts’ and Managers Earnings Forecasts.” International Journal of Forecasting. 31, Issue 2 (2015), 501-514.
  • Gillam, R.A., Guerard, J.B., Jr. and R. Cahan. “News Volume Information: Beyond Earnings Forecasting in a Global Stock selection Model.” International Journal of Forecasting 31 Issue 2 (2015), 575-581.
  • Guerard, J., Lahari, K. “International Financial Forecasting: Global Economic Linkages and Corporate Earnings.” International Journal of Forecasting. 31, Issue 2 (2015), 392-298.
  • Guerard, J.B., Jr., H. M. Markowitz, and G. Xu. “Global Stock Selection Modeling and Efficient Portfolio Construction and Management”, Journal of Investing 22 (2013), 121 -128.
  • Guerard, J.B., Jr., H. M. Markowitz, and G. Xu. “Earnings Forecasting in a Global Stock Selection Model and Efficient Portfolio Construction and Management” International Journal of Forecasting 31 Issue 2 (2015), 550-560.
  • Guerard, J.B., Jr., H. M. Markowitz, and G. Xu. “The Role of Effective Corporate Decisions in the Creation of Efficient Portfolios.” IBM Journal of Research and Development, 58 (July / August 2014), 6.1 – 6.11.
  • Guerard, Jr. B., Jr., Xu, Ganlin, Gültekin, Mustafa. “Investing with Momentum: The Past, Present, and Future.” Journal of Investing 21 (2012), 68-80.
  • Guerard, J., Ye, H., Ashley, R. “Comparing the effectiveness of traditional vs. Mechanical Identification Methods in Post-Sample Forecasting for a Macroeconomic Granger-Causality Analysis”, International Journal of Forecasting, 31, Issue 2 2015, 488 – 500.
  • Markowitz, M. Harry. “Topics in Applied Investing Management: From a Bayesian Viewpoint.” The Journal of Investing. 21, (2012), 7-13.
  • Saxena, Anureet, Stubbs, Robert A. An Empirical Case Study of Factor Alignment Problems Using the USER Model. The Journal of Investing. 21 (2012), 25-43.
  • Shao, Barret Pengyuan. “Mean-ETL Optimization of a Global Portfolio.” The Journal of Investing. 22 (2013), 115-120.

Disclosure

McKinley Capital Management, LLC (“McKinley Capital”) is a registered investment adviser under the U.S. Investment Advisers Act of 1940. McKinley Capital is not registered with, approved by, regulated by, or associated with the Financial Conduct Authority (“FCA”), the Prudential Regulation Authority (“PRA”), the Securities & Futures Commission of Hong Kong or the China Securities Regulatory Commission. Additionally, none of the authorities or commissions listed in the previous sentence has commented on the firm, the content of any marketing material or any individual suitability assessments.

Returns are absolute, were generated using McKinley Capital’s proprietary growth investment methodology as described in McKinley Capital’s Form ADV Part 2A, are unaudited, and may not replicate actual returns for any client. McKinley Capital’s investment methodology has not materially changed since its inception but it has undergone various enhancements. No securities mentioned herein may be considered as an offer to purchase or sell a firm product or security. Any comment regarding an individual security is presented at the client’s request, may only be used for client reference, and may not be reflective of composite or individual portfolio ownership. McKinley Capital may not currently hold a specific security. In addition, any positive comments regarding specific securities may no longer be applicable and should not be relied upon for investment purposes. No security is profitable all of the time and there is always the possibility of selling it at a loss. With any investment, there is the potential for loss. Investments are subject to immediate change without notice. Comments and general market related perspectives are for informational purposes only; were based on data available at the time of writing; are subject to change without notice; and may not be relied upon for individual investing purposes. Past performance is no guarantee of future results.

Trade date based performance shown reflects the reinvestment of realized gains, dividends, interest and other earnings calculated using McKinley Capital’s growth investment methodology. Portfolio performance is shown gross and/or net of management fees or asset based broker fees as indicated in the text of the presentation. Clients should realize that net returns would be lower and must be considered when determining absolute returns. Detailed account inclusion/exclusion policies are available upon request. Returns are based on fully discretionary accounts and do not take individual investor tax categories into consideration. Returns reported for the periods prior to January 1, 2001 were initially calculated using McKinley Capital’s quarterly reporting methodology. Monthly returns for the period were retroactively calculated and are considered supplemental information. Returns from January 1, 2001 to current date utilize a monthly reporting methodology. No guarantee can be made that the composite performance reflects a statistically accurate representation of the performance of any specific account. Charts, graphs and other visual presentations and text information are derived from internal, proprietary, and/or service vendor technology sources and/or may have been extracted from other firm data bases. As a result, the tabulation of certain reports may not precisely match other published data. Specific results from calculations and formulas may be rounded up. Future investments may be made under different economic conditions, in different securities and using different investment strategies.

For GIPS® compliant presentations, all information is supplemental to the GIPS® compliant composites and a copy of the applicable GIPS® composite(s) is included with the presentation. Composite returns and individual client returns may materially differ from the stated benchmark(s). Deviations may include, but are not limited to, factors such as the purchase of higher risk securities, over/under weighting specific sectors and countries, limitations in market capitalization, company revenue sources, McKinley Capital’s investment process and/or client restrictions. Global market investing, (including developed, emerging and frontier markets), also carries additional risks and/or costs including but not limited to: political, economic, financial market, currency exchange, liquidity, accounting, and trading capability risks. Derivatives trading and short selling may materially increase investment risk and potential returns. These risks may include, but are not limited to, margin/mark-to-market cash calls, currency exchange, liquidity, unlimited asset exposure, and counter-party risk. Foreign accounting principles may also differ from standard U.S. GAAP standards.

Fees are billed monthly or quarterly, which produces a compounding effect on the total rate of return net of management fees. As an example, the quarterly effect of investment management fees on the total value of a client’s portfolio assuming (a) $1,000,000 investment, (b) portfolio return of 5% a year, and (c) 1.00% annual investment advisory fee would be $10,038 in the first year, and cumulative effects of $51,210 over five years and $110,503 over ten years. Actual client fees vary. A fee schedule, available upon request, is described in the firm’s Form ADV part 2A.

Composite returns include only those accounts holding common stocks, preferred stocks, ADRs, ordinary shares, money market instruments and/or cash equivalents – and for non-U.S. and global composites foreign currencies and stocks. For the period prior to April 1, 2001, composites contain both wrap and non-wrap accounts. For this period, net returns for non-wrap accounts were not reduced by wrap sponsor fees, and gross returns for non-wrap accounts were reduced by transactional costs. The performance results prior to March 11, 1991 reflects the investment performance of discretionary brokerage accounts managed by Robert B. Gillam, Chief Investment Officer at FAS Alaska, Inc. (prior to the formation of McKinley Capital) with a growth investment philosophy and methodology similar to that described in McKinley Capital’s brochure.

Data may have originated from various sources including, but not limited to, Bloomberg, FactSet, MSCI, Axioma, Russell Indices, FTSE, TQA, APT, Zephyr and/or other systems and programs. With regards to any material, if any, accredited to FTSE International Limited (“FTSE”) ©FTSE [2016]: FTSE™ is a trade mark of London Stock Exchange Plc and The Financial Times Limited and is used by FTSE International Limited under license. All rights in the FTSE Indices vest in FTSE and/or its licensors. Neither FTSE nor its licensors accept any liability for any errors or omissions in the FTSE Indices or underlying data. With regards to any materials, if any, accredited to MSCI: Neither MSCI nor any other party involved in or related to compiling, computing or creating the MSCI data makes any express or implied warranties or representations with respect to such data (or the results to be obtained by the use thereof), and all such parties hereby expressly disclaim all warranties of originality, accuracy, completeness, merchantability or fitness for a particular purpose with respect to any of such data. Without limiting any of the foregoing, in no event shall MSCI, any of its affiliates or any third party involved in or related to compiling, computing or creating the data have any liability for any direct, indirect, special, punitive, consequential or any other damages (including lost profits) even if notified of the possibility of such damages. No further distribution or dissemination of the MSCI data is permitted without MSCI’s express written consent. Please refer to the specific service provider’s web site for complete details on all indices. McKinley Capital makes no representation or endorsement concerning the accuracy or propriety of information received from any third party. All information is believed to be correct but accuracy cannot be guaranteed. Clients should rely on their custodial statements for the official investment activity records. Clients should contact their custodian with any questions regarding monthly/quarterly receipt of those statements.

To receive a copy of the firm’s ADV, a complete list and description of McKinley Capital’s composites and/or a presentation that adheres to the GIPS® standards, please contact McKinley Capital at 1.907.563.4488 or visit the firm’s website, www.mckinleycapital.com.