Stock selection using a multi-factor model - empirical evidence from the French stock market

Using a Barra-type factor model, we have attempted to determine whether it is possible to beat the benchmark by taking advantage of anomalies established in the financial empirical literature. More specifically we have built an equity premium model based on three sets of factors (accounting variables, stock market characteristics and sector indicators) using a Bayesian method corrected for heteroscedasticity to estimate risk premiums, a technique that takes agents' learning into account. The results are encouraging: first, the factors that carried most weight on the equity premiums corroborated the results of empirical studies described in the financial literature, secondly, the portfolios constructed from our methodology and simulated outside our sample, returned higher performance than the benchmark and rewarded the supplement of volatility.