讲座题目：Emerging risk management and data techniques in insurance（保险业的新兴风险管理与数据技术）

主讲人：金卓 教授 澳大利亚麦考瑞大学(Macquarie University)商学院

讲座地点：bv韦德B224

讲座时间：2023年7月14日9:30-11:30

讲座内容摘要：

For cyber risk management, a cluster-based method is developed to investigate the risk of cyber-attacks in the continental United States. The proposed analysis considers geographical information on cyber incidents for clustering. By clustering state-based observations, the frequency and severity of cyber losses demonstrate a simplified structure: independent structure between inter-arrival time and size of cyber breaches. The independence between frequency and severity is significant at the state level instead of the national level. It is shown that the cluster-based models have a better fitting and are more robust than the aggregate model, where all incidents are considered together. To detect fraud insurance claims, we propose a new variable importance methodology incorporated with two prominent unsupervised deep learning models, namely, the autoencoder and the variational autoencoder. Each model's dynamics are discussed to inform the reader on how models can be adapted for fraud detection and how results can be perceived appropriately with a greater emphasis placed on qualitative evaluation.

对于网络安全风险管理，本文开发了一种基于聚类的方法来研究美国网络攻击风险。模型分析中考虑了网络事件的地理信息以进行聚类。通过对基于状态的观察进行聚类，网络损失的频率和严重程度展示了一个简化的结构：到达间隔时间和网络漏洞规模之间的独立结构。频率和严重程度之间的独立性在州一级而不是国家一级具有重要意义。结果表明，基于聚类的模型比聚合模型具有更好的拟合性，并且更稳健，聚合模型将所有事件一起考虑。为了检测保险欺诈索赔，我们提出了一种新的可变重要性方法，该方法结合了两个突出的无监督深度学习模型，即自动编码器和变分自动编码器。讨论了每个模型的动态，以告知读者如何调整模型以进行欺诈检测，以及如何适当地感知结果，并更加强调定性评估。

主讲人学术简介：

金卓，澳大利亚麦考瑞大学(Macquarie University)商学院教授，研究方向包括最优控制论在精算中的应用，数理金融，金融科技，机器学习与金融交叉。在Insurance Mathematics and Economics, European Journal of Operational Research, Journal of Risk and Insurance, SIAM Journal on Control and Optimization, Automatica等顶级期刊发表论文60余篇。他还是包括Society of Actuaries在内的多个重要学术组织的成员。