The most important feature of a successful multi factor stock selection model is its ability to differentiate potential factor winners and losers. Here I developed a tool algorithm to help us choose the most effective factors. 

At the begining of each month I get the factor value of stocks after coarse selection and rank those stocks by factor value. Then I divide them into 5 portfolios and calculate the monthly returns. Monthly returns are converted to an annual return for analysis.  

There are three metrics to judge the significance of different fundamental factors:

a. The correlation between ranked portfolio series and their annual returns (A significant factor should have higher corrlation coefficient)

b. The probability that win portfolio outperforms the benchmark and the probability that loss portfolio underperforms the benchmark

(A significant factor should have high value of these two probability)

c. The excess return of the win and loss portfolios

(For significant factors, portfolios should have much higher excess returns than loss factor)

The algorithm is an example of PERatio.