Premiums and Discounts. The model fitting process makes average premium or discount very close to 0%. An important characteristic of the model is the distribution of these premiums or discounts (technically the model views these as errors or components of price it can't explain with the fundamental variables.) By examining the percentile of a company's premium or discount, one can find out how many stocks in the database had comparable, or higher, levels of premium.
Statisticians Note. This month the model has about a 64.5% R-Square (in continuously compounded premium/discount space). I will make it a practice to report the model's fit each month using the the same universe of stocks and the same basic architecture of model (e.g. same inputs and number of hidden neurons, etc.) Perhaps the increase in R-Square over last month indicates a stronger "value" theme in the market after July's correction.