The research project at the University of Würzburg (JMU) received 137,000 euros in funding from the federal government. This project will develop an AI early warning system to prevent errors in new software development.
This research project is being carried out by a team led by Professor Ingo Scholtes, Head of Machine Learning for Complex Networks at the CAIDAS Center for Artificial Intelligence and Data Science. “Our goal is to create his AI-based early warning system for software development,” he explains. “It should help detect problems in organizational structures, provide early signs of emerging problems, and help managers take action.” This is especially true for complex software development where many people are involved over long periods of time. Making this a real game changer. “Managers can use this platform to quickly see who is working on which tasks, where key roles are located within the team, and what are the sources of potential errors. ” The project is scheduled to start in April 2024.
Funding from an exclusive federal funding pot
Würzburg's research has been funded with €137,000 from the coveted 'Software Campus' funding programme. This program for the education and training of IT managers, announced by the German Federal Ministry of Education and Research (BMBF), is currently only available to a small number of universities. We focus on translating research into practice and promoting researchers early in their careers. “This is also an important criterion for our research,” Scholz says. “The team is not led by me, but by a PhD student, Rishi Kalkasiya. He is a research assistant in my chair and is researching new deep learning techniques as part of his PhD.”
Scholtes has welcomed DATEV, an IT services provider for tax consultants, accountants, law firms and their primarily mid-sized customers, as an industry partner. “This collaboration is absolutely a win-win situation,” says the professor. “We researchers can observe first-hand where the biggest challenges lie in managing real-world large-scale software projects. Our partners can also draw from our research the latest his AI techniques. will be able to access it.”
Past research is the basis
The development of the new AI platform builds on Scholtes' previous research on the social organization of software teams. For example, in these studies, computer scientists were able to show that the so-called Ringelmann effect also occurs in software projects. This is a phenomenon known in social psychology and explains how team members' individual contributions tend to decrease as team size increases. More simply, larger teams tend to require less effort from people because responsibility for results is spread across more shoulders. Scholtes' team was also able to show that the structure of the collaboration network (i.e., who collaborates with whom) influences how strongly this effect manifests itself within a team. The new project will use these findings to identify problematic collaboration structures and provide information on how to improve them.
Researchers in Würzburg recently started creating a database for this project. They use his git2net, a software developed by the chairman. It automatically analyzes data from the online collaboration platform github.com and generates a temporarily resolved collaboration network between the members of the software's team. These form the basis for further analysis, visualization and AI applications.
The original title of the research project was “Data-driven platform for proactive risk management in software development projects.”
/Open to the public. This material from the original organization/author may be of a contemporary nature and has been edited for clarity, style, and length. Mirage.News does not take any institutional position or stance, and all views, positions, and conclusions expressed herein are solely those of the authors. Read the full text here.
