Alternative-ingredient Recommendation Based on Co-occurrence Relation on Recipe Database

Abstract

This paper proposes a recommendation method of alternative-ingredients based on co-occurrence relation on recipe database. Currently, dishes are often cooked with reference to recipes on Website. Convenience to access so many and varied recipes encourages beginners to cook. Recipe on Website list ingredients used for a dish. However, for some reason, some of the listed ingredients cannot be used for the cooking; this paper defines such ingredient as “exchange-ingredient.” To cook a dish, it should alternate exchange-ingredient and another one (i.e., alternative-ingredient). This paper proposes two algorithms to recommend alternative-ingredient. Through the cooking and tasting experiments, it was confirmed that the each of the proposed methods were effective for each intended purpose.