Back to Community
Factor preprocessing

I am developing an algo following the contest guideline with constraints and optimization in place. When producing a factor, do I have to worry about outliers adjustment, factor standardization and common factor (market & sector) neutralization other than a simple preprocessing as follows ?

def preprocess(a):  
    a = a.astype(np.float64)  
    a[np.isinf(a)] = np.nan  
    a = np.nan_to_num(a - np.nanmean(a))  
    return preprocessing.scale(a)