报告题目：Portfolio Selection with Deep Learning
报 告 人：赖永增教授
加拿大劳瑞尔大学 (Wilfrid Laurier University)
时 间：2019年5月15日（周三）下午 14：30
地 点：管理学院第二会议室
【赖永增教授简介】
赖永增，加拿大Wilfrid Laurier University教授，2000年获美国Claremont Graduate University博士学位，之后在加拿大University of Waterloo做博士后。主要研究领域包括金融衍生品定价及风险管理、计算金融、投资组合优化、Monte Carlo模拟方法及应用等。在Automatica、Journal of Computational Finance、Insurance Mathematics and Economics、Economic Modeling等重要国际学术期刊及会议上发表论文40余篇。主持加拿大国家自然科学基金多项，获教育部科研优秀成果三等奖及广东省社科优秀成果一等奖。
【报告内容摘要】
A two-stage framework to construct portfolios based on deep learning algorithms will be introduced. In stage 1, we used principal component analysis (PCA), auto-encoder(AE) and restricted Boltmann machine (RBM) as data representation methods to reconstruct the stock prices, and select outstanding stocks to enter the portfolio according to the characteristics of data reconstruction. In stage 2, taking stock index as target, using rectified linear unit (Relu) activation function to train networks to construct investment portfolios. Our results show that (1) there is no significant difference in the performance of different data representation methods; (2) the contribution of communal information to the optimal portfolio descended with the number of selected stocks; (3) the characteristics of different markets obtained by deep learning are different; (4) this model achieves good results for different frequency data.
欢迎有兴趣的教师、博士生、硕士生参加。
管理学院科研管理办公室
2019年5月14日
