Big Data and Service Science

Selected Projects

Advanced Customer Insights

The project Advanced Customer Insights is a joint research project of FZI and 1&1. The research project aims at modeling and predicting the behavior of telecommunication customers. The objective is the development of autonomically triggered, customized marketing campaigns based on high-dimensional, sequential association rules and angle-based techniques for characterizing and predicting customer preferences and product affinities. Particular challenges are the intelligent reduction of high-dimensional customer data, high behavioral and technical dynamics, and the appropriate consideration of the influence of communication network structures on customer behavior.

Contact: Prof. Dr. Thomas Setzer

BigGIS

In the project BigGIS, a new generation of GIS is developed and researched, which supports decisions in various scenarios, by means of new mechanisms and on the basis of large amounts of heterogeneous data, better and faster. The innovation lies in the comprehensive cooperation of time and space in the analysis, the consideration of significantly larger amounts of even unstructured and unreliable amounts of data and a continuous processing pipeline, which supports not only descriptive but also predicative and prescriptive as well as visual analyses.  In the three application scenarios "Civil Protection", "Environment" and "Smart City and Health", prototypical problems are addressed and solutions are elaborated, empirically validated as well as further developed.

Contact: Dr. Tim Straub

more

CloUIT

CloUIT deals with the establishment of new IT sourcing models at an investment firm in Frankfurt (Main). In the context of an already fully outsourced infrastructure and service landscape, the focus is set on the selection of new service offerings and providers together with data privacy and security questions. The selection and seamless integration of new services into existing infrastructures, with the option of a provider transition at any time, requires explicit acquaintance of the current IT risk situation. This is obtained through the analysis of monitoring data with data mining methods and their aggregation.

Contact: Dr.-Ing. Nico Rödder

Data Quality Management im Corporate Financial Controlling

The research project Data Quality Management in Corporate Financial Controlling, conducted in collaboration with Bayer AG aims at defining early indicators for planning accuracy and systematic planning errors of financial planning processes.  Leveraging techniques such as robust prediction, high-dimensional pattern detection, novel quality metrics for planning quality and temporal Bayesian networks we learn complex rules from millions of historic planning observations to anticipate and manage suspicious sets of delivered planning long before actual values are available.

Contact: Prof. Dr. Thomas Setzer

MOPS – Management-Modul für On-Premise Software

In the cooperative research project "MOPS – Management module for on-premise software" software solutions to enable monitoring and detection of error and overload situations in heterogeneous IT installations are developed. Complex Event Processing (CEP) technology is applied to automatically prevent these situations by appropriate countermeasures. The main goals include increased transparency and reduced maintenance cost while increasing the service quality.

Contact: Dr.-Ing. Anne Meyer

more

RELATE FP7 Marie Curie TN

The FP7 Marie Curie Initial Training Network “RELATE” provides an opportunity for young researchers to study the latest technologies, platforms and tools in the area of engineering and provisioning of service-based Cloud applications. The ITN consists of seven leading European research institutes and five associated partners. The ITN organizes regular workshops and summer schools, so that the trained Early Stage Researchers (ESRs) and Experienced Researchers (ERs) can exchange research experience, insights and ideas. A total of 19 fellow

15 ESR fellows who are registered for PhD degrees and four ER fellows, have been recruited so far (for open positions please see the link above). Through an integrative and multidisciplinary research approach, RELATE promotes the advancement of the state-of-the-art in the related areas of model-driven development of Software-as-a-Service (SaaS) applications, formal methods, service-based mash-ups and application integration, security and performance of SaaS applications, as well as quality management and business model innovation.

FZI status: Associated Partner

RealMoves

Moderne Fahrzeuge werden serienmäßig mit zahlreichen Sensoren ausgestattet, durch welche der Betriebszustand und zu einem gewissen Grad auch das Umfeld der Fahrzeuge erfasst werden können. In einem Kooperationsprojekt soll geprüft werden, inwiefern eine weitergehende Auswertung dieser Routinemessungen mittels statistischer Auswertung Rückschlüsse auf die Beschaffenheit der Straßeninfrastruktur erlaubt. Das Gesamtvorhaben umfasst die sensorbasierte Merkmalserfassung, deren Vorverarbeitung, die Datengenerierung zur Funktionsabsicherung, die statistische Auswertung geo-temporaler Daten durch Methoden des statistischen Lernens sowie die Entwicklung der zugrundeliegenden Datenverarbeitungsinfrastruktur.

Contact: Stefan Otten

more

CLUSS - Cloud Services Scalability

In the project CLUSS, which is funded in the framework of the funding initiative "KMU-innovativ", it is worked on the technical realisation of granular scalable, internet-based services and their dynamic pricing. Through the use of diagonal scaling technologies, a needs-oriented adjustment of necessary resources is made possible. Primarily realised by the suitable control of peak load, simulation results and test implementations show a efficient resource use.

Contact: Kevin Laubis

more