Volume 18, No. 2, 2020 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… Read More
Articles
Using Machine Learning to Predict Realized Variance
Volume 18, No. 2, 2020 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… Read More
Dynamic Goals-Based Wealth Management Using Reinforcement Learning
Volume 18, No. 2, 2020 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… Read More
Can Machines “Learn” Finance?
Volume 18, No. 2, 2020 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… Read More
On the Stability of Machine Learning Models: Measuring Model and Outcome Variance
Volume 18, No. 2, 2020 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… Read More
Time-Series Variation in Factor Premia: The Influence of the Business Cycle
Volume 18, No. 1, 2020 Christopher Polk, Mo Haghbin and Alessio de Longis Factor cyclicality can be understood in the context of factor sensitivity to aggregate cash-flow news. Factors exhibit different sensitivities to macroeconomic risk, and this heterogeneity can be exploited to motivate dynamic rotation strategies among established factors: size, value, quality, low volatility and momentum… Read More
Trends Everywhere
Volume 18, No. 1, 2020 Abhilash Babu, Ari Levine, Yao Hua Ooi, Lasse Heje Pedersen and Erik Stamelos We provide new out-of-sample evidence on trend-following investing by studying its performance for 82 securities not previously examined and 16 long–short equity factors. Specifically, we study the performance of time series momentum for emerging market equity index futures… Read More
Timing is not Everything—Assessing Manager Skill in Factor Timing
Volume 18, No. 1, 2020 Andrew Chin and Piyush Gupta We introduce an innovative framework to assess the contribution and persistence of factor timing within US large-cap equity funds. After decomposing active returns into three components—strategic factor contribution, tactical factor contribution and security selection—we find that they are all significant but security selection is the dominant contributor… Read More
Do High-Frequency Traders Improve Your Implementation Shortfall?
Volume 18, No. 1, 2020 Robert A. Korajczyk and Dermot Murphy We take advantage of a regulatory change that effectively imposed a “tax” on HFT order activity on Canadian equity venues to study the resulting effect on the execution costs of large institutional trades.We find that bid–ask spreads increase and price impact decreases for these trades… Read More
The Fully-Anticipated P/E Promise and Its Realization
Volume 18, No. 1, 2020 Martin L. Leibowitz, Stanley Kogelman, and Anthony Bova In this paper, time paths of P/Es are projected, by applying a theoretical model in which the totality of “fully anticipated” future “franchise” investments serve as the source of higher P/Es. At the outset, the P/E path slowly ascends until the first… Read More