価格変動パターンを用いた市場予測k-Medoids Clustering with Indexing Dynamic Time Warpingの株式市場への適用

カテゴリ: 論文誌(論文単位)

グループ名: 【C】電子・情報・システム部門

発行日: 2018/08/01

タイトル(英語): Stock Price Prediction using k-Medoids Clustering with Indexing Dynamic Time Warping

著者名: 中川　慧（野村アセットマネジメント(株)），今村　光良（野村アセットマネジメント(株)），吉田　健一（筑波大学大学院ビジネス科学研究科）

著者名(英語): Kei Nakagawa (Nomura Asset Management Co., Ltd.), Mitsuyoshi Imamura (Nomura Asset Management Co., Ltd.), Kenichi Yoshida (Graduate School of Business Sciences, University of Tsukuba)

キーワード: k-medoids clustering，indexing dynamic time warping，株価予測，価格変動パターン，モメンタム，リバーサル_x000D_　　k-medoids clustering，indexing dynamic time warping，stock price prediction，price fluctuation pattern，momentum，reversal

要約(英語): Various methods to predict stock prices have been studied. In the field of empirical finance, feature values for prediction include “value” and “momentum”. In this research, we use the pattern of stock price fluctuations which has not been fully utilized in the financial market as the input feature of prediction. We extract the representative price fluctuation patterns with k-Medoids Clustering with Indexing Dynamic Time Warping method. This method is k-medoids clustering on dissimilarity matrix using IDTW which measures DTW distance between indexed time-series. We can visualize and grasp a price fluctuation pattern effective for prediction with the proposed method. To demonstrate the advantages of the proposed method, we analyze its performance using TOPIX. Experimental results show that the proposed method is effective for predicting monthly stock price changes.

本誌: 電気学会論文誌C（電子・情報・システム部門誌） Vol.138 No.8 （2018） 特集：人間と情報を繋ぐ情報システム

本誌掲載ページ: 986-991 p

原稿種別: 論文／日本語

電子版へのリンク: https://www.jstage.jst.go.jp/article/ieejeiss/138/8/138_986/_article/-char/ja/