Innovative Applications of O.R. Enhancement of equity portfolio performance using data envelopment analysis Eero Pätäri a,⇑ , Timo Leivo b , Samuli Honkapuro b a School of Business, Lappeenranta University of Technology, Finland b LUT Energy, Lappeenranta University of Technology, Finland article info Article history: Received 22 December 2010 Accepted 6 February 2012 Available online 25 February 2012 Keywords: Data envelopment analysis (DEA) Investment analysis Portfolio performance Value investing Momentum investing Performance measurement abstract This paper examines the applicability of data envelopment analysis (DEA) as a basis of selection criteria for equity portfolios. It is the first DEA application for constructing a combined equity investment strat- egy that aims to integrate the benefits of both value investing and momentum investing. The 3-quantile portfolios are composed of a comprehensive sample of Finnish non-financial stocks based on their DEA efficiency scores that are calculated using three variants of DEA models (the constant returns-to-scale, the super-efficiency, and the cross-efficiency models). The performance of portfolios is evaluated on the basis of the average return and several risk-adjusted performance metrics throughout the 1994– 2010 sample period. The results show the capability of the DEA approach to add value to equity portfolio selection. The out- performance of the top 3-quantile DEA portfolios in contrast to both the comparable bottom portfolio and the stock market average is statistically significant on the basis of all performance measures employed. The outperformance is slightly more significant when the stock price momentum is included in the DEA variables. The methodology employed offers an interesting alternative for detecting the outperforming stocks of the future by capturing both the price momentum and several dimensions of relative value simultaneously. DEA is particularly useful as a multicriteria methodology in cases in which the number of stocks in the sample is large. It therefore also has useful implications to practical portfolio management. Ó 2012 Elsevier B.V. All rights reserved. 1. Introduction Considerable evidence against the efficient stock market hypothesis has been documented over the past three decades. On the one hand, numerous studies have identified the existence of price momentum on stock returns (e.g., see Jegadeesh and Titman, 1993, 2001; Chan et al., 1996, 2000; Rouwenhorst, 1998; Grundy and Martin, 2001; Lewellen, 2002; Korajczyk and Sadka, 2004; Gutierrez and Kelley, 2008; Billio et al., 2011), which refers to the tendency of recent winner stocks to generate abnormal returns also in the near future. On the other hand, there is plenty of inter- national evidence of a value premium (e.g., see Fama and French, 2006; Brown et al., 2008; Barbee et al., 2008), which refers to the tendency of value stocks to outperform glamour stocks for most of the time. Momentum investing has been documented to per- form best in the short term (e.g., see Jegadeesh and Titman, 2001; Cooper et al., 2004; Lam et al., 2010), whereas value invest- ing performs better when using longer holding periods (see e.g., Bird and Whitaker, 2003; Rousseau and van Rensburg, 2004; Bird and Casavecchia, 2007a). Since the price of value stocks may remain low for an extended period of time, some scholars have started to examine whether value portfolio selection could be com- plemented with a timing indicator that shows when to purchase undervalued stocks. Bird and Whitaker (2004) report that the added value attributable to each value and momentum strategy is basically uncorrelated, which enables performance improve- ment by combining these two strategies. Recently, further evi- dence of added-value of combining value and momentum strategies has been documented (e.g., see Bird and Casavecchia, 2007a; Bettman et al., 2009; Leivo and Pätäri, 2011). However, the major problem with such a research design is how to combine the value indicator and the momentum indicator into a single selection criterion. In this paper, we test whether data envelop- ment analysis (DEA) is applicable to resolve this dilemma. To contribute to the scant literature on DEA applications in the context of equity portfolio selection, this paper examines the effi- ciency of DEA as a formation criterion for equity portfolios in a case in which input and output factors are derived from indicators of rel- ative valuation of stocks and from the price momentum indicator. Thus applied, the DEA approach can be considered as an alternative for constructing a combined investment strategy that aims to inte- grate the benefits of both value investing and momentum investing. To our knowledge, this is the first time when the DEA approach is employed for combining value and momentum indicators. As far 0377-2217/$ - see front matter Ó 2012 Elsevier B.V. All rights reserved. doi:10.1016/j.ejor.2012.02.006 ⇑ Corresponding author. Address: School of Business, Lappeenranta University of Technology, P.O. Box 20, FIN-53851 Lappeenranta, Finland. Tel.: +3584 0833 6907; fax: +3585 6217 299. E-mail addresses: eero.patari@lut.fi, eero.patari@gmail.com (E. Pätäri). European Journal of Operational Research 220 (2012) 786–797 Contents lists available at SciVerse ScienceDirect European Journal of Operational Research journal homepage: www.elsevier.com/locate/ejor