Abstract: Disclosed is a computer implemented method of providing automated advice including receiving factors for use in providing automated advice, each factor including a defined respective set of categories, and each factor and each category including a respective initial weighting; receiving a rule for generating a recommendation and using the respective weightings of the factors and categories, the rule including a set of possible recommendations such that a generated recommendation is one of the set of possible recommendations; receiving training cases, each training case including inputs relating to each factor, and to the categories, and including a respective validated recommendation; processing the training cases, to derive a respective optimized weighting for each factor and for each category, to satisfy or to match the respective validated recommendations optimally, using the rule, and storing the derived respective optimized weightings for the factors and for each category.