Presentation information

Oral presentation

General Session » [General Session] 3. Data Mining

[3L1] [General Session] 3. Data Mining

Thu. Jun 7, 2018 1:50 PM - 3:30 PM Room L (3F Sapphire Hall Asuka)

座長:大澤 昇平(東京大学)

3:10 PM - 3:30 PM

[3L1-05] Embedding special-day effects for demand prediction

〇Takuji Tahara1, Yiou Wang1, Keiichi Nemoto1 (1. Fuji Xerox Co., Ltd.)

Keywords:demand prdiction, embedding, special day

Special days such as public holidays have significant impact on time-varying customer’s demand. In this paper, we propose a new method to handle the special days' effects by embedding techniques using neural network. We evaluate the usefulness of our method in the real call center data set and demonstrate that embedded features generated by our method provide substantial performance gains in call arrival prediction. In addition, we visualize the embedding features of special day and its neighborhood and further understand their relationship.