龙马奋进 · 校庆70周年学术系列讲座
精算论坛讲座 第156期—蔡宁(4月19日)
教育部人文社科重点研究基地中央财经大学中国精算研究院学术活动
精算论坛讲座 第156期—蔡宁
(2019年4月19日)
报告人：Ning Cai（蔡宁）
蔡宁是香港科技大学工业工程及决策分析学系的副教授。他是香港科技大学金融科技硕士项目（由工学院，理学院和商学院联合主办）的首任Academic Director，同时担任工业工程及决策分析学系金融工程及金融科技实验室的Director。蔡宁于2008年在哥伦比亚大学获得运筹学博士学位，并分别于2000年和2003年在北京大学数学科学学院获得概率统计学士和硕士学位。蔡宁的研究方向主要包括金融工程，金融科技，数据科学，应用概率以及金融和经济中的随机建模。蔡宁现在担任Operations Research, Operations Research Letters, Digital Finance 和 IMA Journal of Management Mathematics的associateeditor以及Probability in the Engineering andInformational Sciences的editorial board member.
报告时间：2019年4月19日（周五）下午14:00—16:00
报告题目：FinTech, Data Analysis, and Privacy Preservation
报告摘要: Many data aresensitive in areas such as finance, economics, political science, and lifescience. How to protect individual privacy when collecting and analyzing datahas become even more significant and has raised growing public concerns in theage of big data because a huge amount of personal data are being generated andused almost freely every day. We propose an ER (encryption and recovery)algorithm that allows a central administration to do statistical inferencebased on the encrypted data, while still preserving each party's privacy evenfor a colluding majority in the presence of cyber attack. Theoretically, weessentially establish a general framework for privacy-preserving statisticalinference, which can be viewed as the sensitive data based counterpart oftraditional statistical inference assuming availability of the data. Wedemonstrate the applications of our algorithm to linear regression, logisticregression, maximum likelihood estimation, estimation of empiricaldistributions, and estimation of quantiles. Moreover, our algorithm can help toaddress another practically significant issue -- privacy preservation fordistributed statistical inference when data are allocated to different partieswho are unwilling to share their own data with others. Our algorithm is apromising “technology” that can be applied to overcomethe difficulties of data analysis with privacy preservation not only infinancial industry but also in other areas concerning people's privacy rightsin the era of big data.
报告地点：中央财经大学学术会堂南楼506（精算院会议室）
欢迎各位老师和同学积极参加！
