Abstract
In the present paper, we investigate the Gompertz function, which is commonly used, mostly as diffusion model, in economics and management. Our approach is based on indicating in a given time series, presumably with a Gompertz trend, some characteristic points corresponding to zeroes of successive derivatives of this function. This allows us to predict the saturation level of a phenomenon under investigation, by using only the early values of the time series. We also give an example of applications of this method.