Volume 18, No. 2, Second Quarter 2020

Machine Learning in Capital Markets

• Article

  On the Stability of Machine Learning Models: Measuring Model and Outcome Variance

  by: Vasant Dhar and Haoyuan Yu

  How do you know how much you should trust a model that is learned from data? We propose that a central criterion in measuring trust is the decision-making variance of a model. We call this “model variance.” Conceptually, it refers to the inherent instability machine learning models experience in their decision-making in response to variations in the training data. We report the results from a controlled study that measures model variance as a function of (1) the inherent predictability of a problem and (2) the frequency of the occurrence of the class of interest. The results provide important guidelines for what we should expect from machine learning methods for the range of problems that vary across different levels of predictability and base rates, thereby making the results of general scientific interest.

• Article

  Can Machines “Learn” Finance?

  by: Ronen Israel, Bryan Kelly and Tobias Moskowitz

  Machine learning for asset management faces a unique set of challenges that differ markedly from other domains where machine learning has excelled. Understanding these differences is critical for developing impactful approaches and realistic expectations for machine learning in asset management. We discuss a variety of beneficial use cases and potential pitfalls, and emphasize the importance of economic theory and human expertise for achieving success through financial machine learning.

• Article

  Dynamic Goals-Based Wealth Management Using Reinforcement Learning

  by: Sanjiv R. Das and Subir Varma

  We present a reinforcement learning (RL) algorithm to solve for a dynamically optimal goal-based portfolio. The solution converges to that obtained from dynamic programming. Our approach is model-free and generates a solution that is based on forward simulation, whereas dynamic programming depends on backward recursion. This paper presents a brief overview of the various types of RL. Our example application illustrates how RL may be applied to problems with path-dependency and very large state spaces, which are often encountered in finance.

• Article

  Using Machine Learning to Predict Realized Variance

  by: Peter Carr, Liuren Wu and Zhibai Zhang

  Volatility index is a portfolio of options and represents market expectation of the underlying security’s future realized volatility/variance. Traditionally the index weighting is based on a variance swap pricing formula. In this paper we propose a new method for building volatility index by formulating a variance prediction problem using machine learning.We test algorithms including Ridge regression, Feed forward Neural Networks and Random Forest on S&P 500 Index option data. By conducting a time series validation we show that the new weighting method can achieve higher predictability to future return variance and require fewer options. It is also shown that the weighting method combining the traditional and the machine learning approaches performs the best.

• Book Review

  Smart(er) Investing – How Academic Insights Propel the Savvy Investor

  by: Elisabetta Basilico and Tommi Johnsen • reviewed by: Zachary Simon

  “Book Reviews” identifies important, and often popular, new books from a wide range of investment topics. Beyond providing a summary and review of the content and style of the books, “Book Reviews” seeks to contribute to a conscious, critical, and informed approach to investment literature.

• Case Study

  Collective Defined Contribution Plans

  by: Seoyoung Kim

  “Case Studies” presents a case pertinent to contemporary issues and events in investment management. Insightful and provocative questions are posed at the end of each case to challenge the reader. Each case is an invitation to the critical thinking and pragmatic problem solving that are so fundamental to the practice of investment management.

• Practitioner's Digest

  Practitioner’s Digest • Vol. 18, No. 2

  The “Practitioners Digest” emphasizes the practical significance of manuscripts featured in the “Insights” and “Articles” sections of the journal. Readers who are interested in extracting the practical value of an article, or who are simply looking for a summary, may look to this section.

• Insight

  Introduction to the Special Issue on Machine Learning

  by: Charles Elkan

  “Insights” features the thoughts and views of the top authorities from academia and the profession. This section offers unique perspectives from the leading minds in investment management.

• Article

  Local, Global, and International CAPM: For Which Countries Does Model Choice Matter?

  by: Demissew Ejara, Alain Krapl, Thomas J. O’Brien and Santiago Ruiz de Vargas

  For individual stocks of 46 countries, this study investigates empirical differences in discount rate estimates between three risk–return models of interest to practitioners who perform discounted cash-flow valuation analysis: (1) the traditional (local) CAPM; (2) the global CAPM (GCAPM), where the only risk factor is the global market index; and (3) an international CAPM (ICAPM) with two risk factors, the global market index and a wealth-weighted foreign currency index. The study finds that model choice makes a substantial difference for many, but not all, countries.