Abstract
本演講介紹台指選擇權資料處理與量化交易策略建構的過程。選擇權因為其特殊結構與波動特性,資料處理相對複雜,然而也因為這些特性,選擇權特別適合做量化交易策略的分析。本研究基於資金管理概念,提出具固定停損或停利機制的選擇權賣方與價差交易策略,藉由停損機制對最大獲利及損失進行量化,降低產生超額虧損的風險。我們透過傳統統計方法及隨機森林演算法對勝率進行估計,採用熱點圖對預測結果進行視覺化,同時考量勝率門檻及穩固性擷取有利可圖的交易區間,並以混淆矩陣、Accuracy 及 Precision 等指標評估模型效能。實驗結果顯示,本研究建構之隨機森林預測模型對所提出交易策略擁有相當優秀的預測能力(Precision 最高達 0.9),能夠有效達成資金管理及風險管理之目標。
Bio
Mu-En Wu is an Associate Professor at Department of Information and Finance Management at National Taipei University of Technology, Taiwan. Dr. Wu received his Ph.D. degree with major in computer science from National Tsing Hua University, Taiwan, in 2009. After that, he joined Institute of Information Science, Academia Sinica at Taipei City, Taiwan as a postdoctoral fellow during 2009~2014. During February 2014 to July 2017, he served as an assistant professor of Department of Mathematics at Soochow University. He has a wide variety of research interests covering cryptography, information theory, prediction market, money management, and financial data analysis. He has published more than 70 research papers in referred journals and international conferences. He is also a blogger on “Bituzi” with pen name “牧清華”.