Suggestion of recommender system of table menu using Bayesian network

DOI IR Web Site Open Access

Bibliographic Information

Other Title
  • ベイジアンネットワークを用いた食事メニュー推奨システムの提案
  • ベイジアン ネットワーク オ モチイタ ショクジ メニュー スイショウ システム ノ テイアン
  • ベイジアンネットワークを用いた食事メニュー推薦システムの提案

Search this article

Description

In this paper, we propose a framework of recommender system that recommends menus in daily table for customer. We use the data called Shoku-MAP data, which recorded the situation of daily table. First of all, we define classification criteria of the customers to use the data. As the result, the customers are classified eight types. Then, we define the defferent models that recommends the menu for each type of customers. We use a Bayesian network as the method determines which menu is recommended. The Bayesian network is the one of the probability models that represents causal relationship of event. It is feature of this model that the model sequentially improves the output of model by accumulation of the data. Therefore, the system is expected to output more appropriate results, by inputting the customer's mood and policy of menu on the day. In addition, we calculate the accuracy of the model by using cross validation .

Journal

  • 文化情報学

    文化情報学 6 (1), 1-10, 2011-03-10

    同志社大学文化情報学会

Keywords

Details 詳細情報について

Report a problem

Back to top