Master Thesis MSTR-2017-97

BibliographyVolga, Yuliya: ACP Dashboard: an interactive visualization tool for selecting analytics configurations in an industrial setting.
University of Stuttgart, Faculty of Computer Science, Electrical Engineering, and Information Technology, Master Thesis No. 97 (2017).
75 pages, english.
Abstract

The production process on a factory can be described by big amount of data. It is used to optimize the production process, reduce number of failures and control material waste. For this, data is processed, analyzed and classified using the analysis techniques - text classification algorithms. Thus there should be an approach that supports choice of algorithms on both, technical and management levels. We propose a tool called Analytics Configuration Performance Dashboard which facilitates process of algorithm configurations comparison. It is based on a meta-learning approach. Additionally, we introduce three business metrics on which algorithms are compared, they map onto machine learning algorithm evaluation metrics and help to assess algorithms from industry perspective. Moreover, we develop a visualization in order to provide clear representation of the data. Clustering is used to define groups of algorithms that have common performance in business metrics. We conclude with evaluation of the proposed approach and techniques, which were chosen for its implementation.

Full text and
other links
Volltext
Department(s)University of Stuttgart, Institute of Parallel and Distributed Systems, Applications of Parallel and Distributed Systems
Superviser(s)Mitschang, Prof. Bernhard; Villanueva Zacarias, Alejandro Gabriel
Entry dateJune 18, 2019
   Publ. Computer Science