When managing their growing service portfolio, many manufacturers in B2B markets face two
significant problems: They fail to communicate the value of their service offerings to their customers,
and they lack the capabilities to generate profits with value-added services. To tackle these two issues,
we design and evaluate a collaborative filtering recommender system which (a) makes individualized
recommendations of potentially interesting value-added services when customers express interest in a
particular physical product and also (b) obtains estimations of a customer’s willingness-to-pay to
allow for a dynamic, value-based pricing of those services. The recommender system is based on an
adapted conjoint analysis method combined with a stepwise componential segmentation algorithm to
collect preference and willingness-to-pay data for value-added services. Compared to other conjointbased
recommendation approaches, our system requires significantly less customer input before
making a recommendation and at the same time does not suffer from the usual cold-start problem of
recommender systems. And, as is shown in an empirical evaluation with a representative sample of
428 customers in the machine tool market, our approach does not diminish the predictive accuracy of
the recommendations offered.