However, this method has several drawbacks. On the first hand,
it requires that animals must be weighted just before the slaughter
in order to achieve accurate results; in practice this is not feasible.
On the other hand, the main disadvantage of the percentages is
that they do not consider any individual morphological feature;
in fact not all double (or single) muscled animals are equal.
The approach presented here is based on Machine Learning procedures
that aim to learn a function to map carcass weights from a
collection of morphological measures of the animals and the number
of days until the slaughter. In this way, individual peculiarities
of the animals are involved in weight estimation.