Application of partial least squares (PLS) regression to predict the ripening time of Manchego cheese

Partial least squares (PLS) regression was used to predict the ripening time of Manchego cheese, based on some physicochemical parameters and secondary proteolysis indices of 63 standard Manchego cheeses manufactured in different seasons (autumn, winter and spring). PLS regression demonstrated that the variables that most contributed to predict the ripening time of the cheeses were water activity (aw), pH and dry matter (DM). The prediction model obtained yielded good results for the prediction of the ripening times of commercial Manchego cheeses manufactured in the same factory as the standard cheeses, since the root mean square error of prediction was 11.9 days. The model was also good for the prediction of the ripening times of commercial Manchego cheeses manufactured in different factories.