{"id":2341,"date":"2024-10-11T11:00:53","date_gmt":"2024-10-11T11:00:53","guid":{"rendered":"https:\/\/dataninja.nrw\/?page_id=2341"},"modified":"2025-02-10T15:00:31","modified_gmt":"2025-02-10T15:00:31","slug":"ml4prom-machine-learning-and-drift-detection-methods-for-predictive-prevention-technologies-in-process-mining","status":"publish","type":"page","link":"https:\/\/dataninja.nrw\/?page_id=2341","title":{"rendered":"ML4ProM: Machine Learning and Drift Detection Methods for Predictive Prevention Technologies in Process Mining"},"content":{"rendered":"
\n\n\n

The faces behind project ML4ProM<\/h3>\n\n\n\n
\n
\n
\"\"<\/figure><\/div>\n\n\n

Ali Norouzifar<\/a><\/h4>\n\n\n\n

RWTH Aachen University<\/p>\n<\/div>\n\n\n\n

\n
\"\"<\/figure><\/div>\n\n\n

Riza Velioglu<\/a><\/h4>\n\n\n\n

Bielefeld University<\/p>\n<\/div>\n<\/div>\n\n\n<\/div>\n\n\n

<\/div>\n\n\n\n

The Future of Business: Improving Processes and Customer Experiences with AI<\/h1>\n\n\n\n
\n
\n
\"\"<\/figure>\n<\/div>\n\n\n\n
\n

Organizations and companies store vast amounts of data about their processes and operations. Take, for example, the process of handling applications at a state insurance agency. The goal is to evaluate applicants who seek social support during difficult times, such as unemployment or disability. Our job is to dive into the recorded data from thousands of insurance cases and develop automated methods to gain insights, identify problems, and help companies improve their processes.<\/p>\n\n\n\n

Typically, business processes have a planned structure, but in reality, things often don\u2019t go exactly as planned. <\/p>\n<\/div>\n<\/div>\n\n\n\n

Our research focuses on identifying unwanted behaviors by analyzing the available historical data. To achieve this, we use prior knowledge and common sense to highlight the differences between good and bad cases. <\/p>\n\n\n\n

Additionally, we compare different cases and provide diagnoses that help experts better understand problems in their workflows. These valuable insights not only shed light on historical patterns but also serve as a guide for companies to improve their processes by learning from their own experiences.<\/p>\n\n\n\n

We also use our findings from process modeling to ensure businesses run smoothly online, such as in e-commerce. For this, we\u2019ve developed special AI-powered programs that offer product recommendations\u2014like a friend suggesting a good book. Our programs not only use historical data but also analyze the products themselves to keep learning and improving.<\/p>\n\n\n\n

What makes our work special is that we can detect when our programs make mistakes! In both areas, we focus on providing trustworthy solutions that offer clear explanations for detected process deviations and product recommendations. This gives our research a significant advantage over typical AI systems, which are often not transparent or difficult to understand.<\/p>\n\n\n\n

Cooperation<\/h3>\n\n\n\n
\n
\n \"RWTH<\/a>\n <\/div>\n
<\/div>\n
\n

Process and Data Science Group<\/p><\/b><\/a>\n

Prof. Wil van der Aalst<\/p><\/a>\n

PhD student: Ali Norouzifar<\/a><\/p>\n <\/div>\n<\/div>\n

\n
\n \"\"<\/a>\n <\/div>\n
<\/div>\n
\n

Machine Learning Group<\/p><\/b><\/a>\n

Prof. Dr. Barbara Hammer<\/p><\/a>\n

PhD student: Riza Velioglu<\/a><\/p>\n <\/div>\n<\/div>\n\n\n\n

Project Publications<\/h3>\n\n\n\n