BERNHARD MITSCHANG (Stuttgart University, Germany)
Data Science in the Manufacturing Domain
The manufacturing domain is known for its high automation level that is achieved by means of a number of cooperating systems in all areas covering the product lifecycle: product design, product engineering, enterprise resource planning, supply chain management, manufacturing execution, service and support, recycling, etc. This suite of systems is known to produce high volumes of data in all engineering and production areas. In order to exploit these volumes of data for optimization purposes, many data science projects are set up to analyze the available data and to come up with optimization proposals. In this talk, I will first give an overview of the manufacturing domain and then dive into some data science topics, especially into data management and data analysis issues. Finally, I will come up with lessons learned and a set of challenges for future work.
Since 1998, I am a professor for Database and Information Systems and head of the department’ Applications of Parallel and Distributed Systems’ that is part of the Institute of Parallel and Distributed Systems (IPVS) at the Faculty of Computer Science, Electrical Engineering, and Information Technology at the Universität Stuttgart, Stuttgart, Germany. From 1994 to 1998 I held the position of a professor at the Technische Universität München. In 1988 I received the Ph.D. degree (Dr.-Ing.) in Computer Science from the University of Kaiserslautern, and in 1994 I got the venia legendi for practical Computer Science from the University of Kaiserslautern. From 1989 to 1990 I was on leave to IBM Almaden Research Center, San Jose, CA as a visiting scientist, and in 2003, 2008, 2013, and 2019 I was on sabbatical leave to IBM Research and Development Lab in Böblingen, Germany. Since 2015, I am Chair and member of the Graduate School of Excellence on Advanced Manufacturing Engineering, part of the German Excellence Initiative. The research, as well as teaching spectrum of my department, covers both the broad spectrum of database applications ranging from business applications to engineering systems as well as database kernel, database middleware, and mobile technologies. Currently, there is much focus on data analytics and data-intensive applications as well as on scalable data processing architectures.
DIETMAR JANNACH (AAU Klagenfurt, Austria)
Recommender Systems – Value, Methods, Measurement
Recommender systems are one of the most visible and successful applications of AI/ Machine Learning today. They are not only helpful for end users to discover things they might be interested in, but they can also lead to a substantial value for the business, e.g., by stimulating more sales or by increasing customer engagement. In this talk, we will first discuss the various types of value recommenders can have for different stakeholders in practice. We will review case studies of recommender systems deployments and discuss how their effects can be measured. We will then move on to the academic perspective, where we describe common problem abstractions, the main technical approaches, as well as evaluation procedures. The talk ends with a discussion of open challenges in our field and an outlook on possible future directions.
Dietmar Jannach is a full professor of Information Systems at AAU Klagenfurt, Austria. Before joining AAU in 2017, he was a full professor of Computer Science at TU Dortmund, Germany. In his research, he focuses on the application of intelligent system technology to practical problems and the development of methods for building knowledge-intensive software applications. In the last years, Dietmar Jannach worked on various practical aspects of recommender systems. He is the main author of the first textbook on the topic published by Cambridge University Press in 2010 and was the co-founder of a tech startup that created an award-winning product for interactive advisory solutions.
KARIN BECKER (UFRGS, Brazil)
Reading Between the Lines: Applications and Challenges
Nowadays, huge volumes of data are and stored daily at an unprecedented rate, creating a unique opportunity to extract patterns, concepts, and anomalies that adds value for decision-making. While increasingly sophisticated techniques and algorithms are developed for the data mining task, one must bear in mind that knowledge discovery in large volumes of data is a complex process. It is driven by the search of information that is relevant to the business, the definition of proper mining objectives, and the existence of data that can answer questions consistently. In this talk, I discuss the challenges and contributions to this process using projects aimed at extracting patterns underlying different types of data, including educational environments, social networks, software artifacts, and online games.
Karin is an associate professor at the Informatics Institute of the Universidade Federal do Rio Grande do Sul (UFRGS), Brazil. She has extensive research experience both at the academy and in the industry, especially in the areas of database, data mining, and software engineering. Her current research projects involve sentiment analysis and data mining on diverse sources, such as social networks, software repositories, online games, health-related repositories, among others. Over the years, she has supervised 33 Graduate students, published nearly 120 papers in journals and conferences, and received three scientific awards. Karin has obtained her doctor’s degree in Computer Science from the Facultés Universitaires Notre-Dame de la Paix – Belgium (1993), and her BSc and MSc degrees from UFRGS. She also participated in research programs at the University of Southern California (2014-2015) and the of Hiroshima (1984-1986). She has been an active member of the SBBD community since its second edition, in 1987.