ICA-DEODA: An independent feature extraction model for stock index forecasting

Conference proceedings article

ผู้เขียน/บรรณาธิการ

กลุ่มสาขาการวิจัยเชิงกลยุทธ์

ไม่พบข้อมูลที่เกี่ยวข้อง

รายละเอียดสำหรับงานพิมพ์

รายชื่อผู้แต่ง: Wijitcharoen A., Watanapa B., Padungweang P., Anantasabkit W.

ผู้เผยแพร่: Hindawi

ปีที่เผยแพร่ (ค.ศ.): 2017

ISBN: 9781509044207

นอก: 0146-9428

eISSN: 1745-4557

URL: https://www.scopus.com/inward/record.uri?eid=2-s2.0-85016189922&doi=10.1109%2fICSEC.2016.7859924&partnerID=40&md5=5b53244ae7a9be81a66f18c513c5b658

ภาษา: English-Great Britain (EN-GB)

ดูบนเว็บไซต์ของสำนักพิมพ์

บทคัดย่อ

In this paper, an integration of the independent component analysis (ICA) and an unsupervised feature selection scheme is proposed as a data engineering approach, called ICADEODA. The proposed feature extraction model enables beyond second order analysis which can powerfully underlie knowledge discovery methods. When applying the model for stock forecasting, firstly, independent components (ICs) are extracted from a set of influential factors of Security Exchange of Thailand (SET) using ICA. DEODA is then applied to select a number of highly informative independent components for being inputs of the forecasting model. Experimentally, the support vector regression (SVR) was taken for predicting movement of the Stock Exchange of Thailand (SET) using quarterly data. The results demonstrated that the proposed model outperforms the traditional PCA-SVR, SVR and also PCA-DEODA-SVR model. ฉ 2016 IEEE.

คำสำคัญ

Set index, Stock movement forecasting, Support vector regressio