Presentation information

Oral presentation

General Session » [General Session] 13. AI Application

[2J2] [General Session] 13. AI Application

Wed. Jun 6, 2018 1:20 PM - 2:40 PM Room J (2F Royal Garden B)

座長:水田 孝信( スパークス・アセット・マネジメント株式会社)

2:00 PM - 2:20 PM

[2J2-03] Classification by Time-Series Gradient Boosting Tree

Application to Financial Time-Series Prediciton

〇Kei Nakagawa1,2, Mitsuyoshi Imamura1,3, Kenichi Yoshida2 (1. Nomura Asset Management Co.,Ltd., 2. University of Tsukuba Graduate School of Business Sciences, 3. University of Tsukuba Graduate School of Systems and Information Engineering)

Keywords: Time-Series Decision Tree, Gradient Boosting Tree, Time-Series Gradient Boosting Tree, Stock Price Prediction

We propose a time-series gradient boosting decision tree for a data set with time-series and cross-sectional attributes.
Our time-series gradient boosting tree has weak learners with time-series and cross-sectional attribute in its internal node, and split examples based on dissimilarity between a pair of time-series or impurity between cross-sectional attributes.
Dissimilarity between a pair of time-series is defined by dynamic time warping method or in financial time-seires by indexing dynamic time warping method.
Experimental results with stock price prediction confirm that our method constructs interpretable and accurate decision trees.