The goal of this thesis is to provide an effective tool for screening a stock portfolio, with socially responsible investment (SRI) in mind, using efficient frontier models. Data envelopment analysis (DEA) has been used previously to build SRI portfolios, but this thesis shows that free disposal hull (FDH), a similar model which does not assume the convexity of the decision-making units, yields superior results when applied to a stock universe of 253 Korean companies. Over a four-year time span from 2006 to 2009, portfolios selected using the FDH method consistently outperform those selected using DEA with both variable returns to scale and constant returns to scale assumptions.