CHAPTER 11
Factor-Based Equity Portfolio Construction and Analysis
Deputy Director of the Mathematics in Finance Masters Program and Clinical Associate Professor, Courant Institute of Mathematical Sciences, New York University
Joseph A. Cerniglia
Visiting Researcher, Courant Institute of Mathematical Sciences, New York University
Frank J. Fabozzi, Ph.D., CFA, CPA
Professor of Finance, EDHEC Business School
Common stock investment strategies can be broadly classified into the following categories: (1) factor-based trading strategies (also called stock selection or alpha models), (2) statistical arbitrage, (3) high-frequency strategies, and (4) event studies. Factors and factor-based models form the core of a major part of today's quantitative trading strategies. The focus of this and the companion chapter that follows is on developing trading strategies based on factors constructed from common (cross-sectional) characteristics of stocks. For this purpose, first we provide a definition of factors. We then examine the major sources of risk associated with trading strategies, and demonstrate how factors are constructed from company characteristics and market data. The quality of the data used in this process is critical. We examine several data cleaning and adjustment techniques to account for problems occurring with backfilling and restatements of data, missing data, inconsistently reported data, as well as survivorship and look-ahead biases. In the last section of this chapter, we discuss the analysis of the statistical properties of factors. In the companion chapter, we extend this analysis to include multiple factors and cover techniques used to implement multifactor trading strategies.
In a series of examples throughout both chapters, we show the individual steps for developing a basic trading strategy. The purpose of these examples is not to provide yet another profitable trading strategy, but rather to illustrate the process an analyst may follow when performing research. In fact, the factors that we use for this purpose are well known and have for years been exploited by industry practitioners. We think that the value added of these examples is in the concrete illustration of the research and development process of a factor-based trading model.