Stock Selection in Korea Beyond Efficient Frontier Capital Management Onthida Boonpiamsak Pab Jotikasthira Jeongsik Lee Neal Triplett Jaekeun Yoon
Agenda Sorting method and attributes for screening Diagnostics Factor/portfolio selection Optimization Conclusion
Sorting Method Attributes for Screening We used sorting method in stock selection: Univariate Attributes Dividend yield Earning growth Projected Earnings Growth Projected P/E ROE Reinvestment Rate Momentum (1mo., 1yr.) Cash Flow to Price Earnings to Price Book to Price Revenue Growth Bivariate Attributes BV/P and MCAP Dividend yield and Earning growth Dividend yield and Projected EY
Diagnostics Performance Measurement Consistency Measurement Average return and excess returns over market and risk-free % Periods > Market % Periods with positive return Average ranking score Consistency Measurement Standard deviations of returns and excess returns Year by year ranking score
Factor /Portfolio Selection Significant Attributes CF/P E/P PPE ROE RIR BV/P and MCAP DY and PPE
Korean Stock Market (6/93-5/98)
Factor/Portfolio Selection Cash Flow/Price
Factor/Portfolio Selection Earning/Price
Factor/Portfolio Selection Prospective Price/Earning
Factor/Portfolio Selection Return On Equity
Factor/Portfolio Selection RIR
Factor/Portfolio Selection Low Book Value/price Sorted by MCAP
Factor/Portfolio Selection Low Dividend Yield Sorted by Projected P/E
Optimization Match market volatility and maximize return: Weight Weight (Top) (Bottom) BV/P and DY -0.20 0.32 CF/P 0.37 -0.20 E/P -0.02 0.00 PPE 0.43 0.07 ROE 0.38 0.11 RIR -0.20 -0.06
Optimization In-sample performance: Beat market by 0.96% per month on average. Beat market 68.75% of the time. Out-of-sample test on 11-month data: Beat market by 2.83% per month on average. Beat market 72.73% of the time.
Conclusion Significant attributes in selecting stocks include CF/P, E/P, PPE, ROE, RIR, and BV/P and dividend yield together. In Korea, stock selection (by sorting method) can help improve performance. One important finding is that top fractiles tend to have high correlations with one another; hence, we may need to use bottom fractiles to reduce volatility.