报告题目：Scalable Frequent Sequence Mining with Subsequence Constraints
主 讲 人：Alexander Renz-Wieland
时 间 ：2019-4-2 10：00-11:00
地 点 ：华东师范大学中北校区地理馆201
主办单位：华东师范大学数据科学与工程学院
报告摘要
Frequent sequence mining is a data mining task that finds frequent subsequences in a sequence database. FSM is ubiquitous in applications, including natural language processing, information extraction, web usage mining, market-basket analysis, and computational biology. Some of the existing algorithms for frequent sequence mining can handle very large datasets with hundreds of millions of sequences. These scalable algorithms are inflexible, however, in that they cannot be tailored to a particular application. They often produce a multitude of frequent subsequences, among only few may be interesting to applications. This talk will give an overview of frequent sequence mining as well as its applications and introduce two novel algorithms that are both flexible and scalable.
报告人简介
Alexander Renz-Wieland is a Research Associate and a PhD candidate in the Database Systems and Information Management (DIMA) group at Technische Universität Berlin, supervised by Volker Markl and Rainer Gemulla. He researches methods for scalable machine learning and data mining. Prior to that, he completed a M. Sc. Business Informatics with a specialization in Data and Web Science at Universität Mannheim and Vrije Unviersiteit Amsterdam. He obtained a B. Sc. in a dual program at DHBW Mannheim and Universidad Carlos III de Madrid, while working for Hewlett-Packard in Germany and the U.S.
