Abstract

A cosine similarity matching method for a binary measurement scale was proposed and applied to a recommender system in our previous study for retrieving interior design drawings. However, for mixed types of intervals, nominal, ordinal, or ratio scales, this matching method fails, as the cosine similarity measure function is not defined for ordinal and nominal values. Compared to our previous study, this paper proposes a new fuzzy similarity matching method for mixed measurement scales and applies the matching method to a recommender system. A numerical case study was carried out to demonstrate the effectiveness and capabilities of the proposed similarity matching method for handling interior design drawing recommendation problems.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call