Predictive Analytics

Within this field, we develop state-of-the-art predictive AI-based systems that support decision-makers or decision tools by providing valuable information. We utilize multimodal data (e.g., images, videos, texts, tabular sensor data) to build state-of-the-art prediction models. We combine AI methods such as neural nets or random forests with theory-based mathematical analysis to develop prediciton tools for option pricing, vehicle routing, inventory management. These tools can handle large amounts of operational data and provide key performance indicators for companies as well as valuable additional information for customers.

Contacts: 

Jun.-Prof. Dr. Kai Heinrich, Prof. Dr. Janis Neufeld, Prof. Dr. Elmar Lukas, Prof. Dr. Marlin Ulmer

We work on projects including:
  • AI-based yield prediction of end-of-life solar panel recycling
  • Designing prediction models for strategic decision-making
  • Demand prediciton for ATM inventory optimization
  • Demand prediciton in mobility and delivery systems to allow for a proactive resource allocation
  • Arrival time prediction for restaurant meal delivery to ensure a successful handover and high-quality customer experience
  • Service time prediction for technician services to communicate accurate and narrow time windows to customers
  • Behavior prediction of participants in mobility and transportation platforms to improve experience for both drivers and customers
  • AI-based valuation of American options
Publications:
  • Graf, J., Lancho, G., Heinrich, K., Möller, F., Schoormann, T., & Zschech, P. (2025). Designing a Neural Question-Answering System for Times of (Information) Pandemics. Information Systems Management, 1-21. https://doi.org/10.1080/10580530.2025.2507175
  • Heinrich, K., & Keshavarzi, A. (2024). Are Our Predictions Healthy? A Comparative Meta-Analysis of Machine Learning Studies in Predictive Healthcare. ECIS 2024 Proceedings.
  • Ulmer, M.W., Goodson, J.C., & Thomas, B.W. (2024). Optimal Service Time Windows. Transportation Science, 58(2), 394-411. https://doi.org/10.1287/trsc.2023.0004
  • Haferkamp, J., Ulmer, M.W., & Ehmke, J.F. (2023). Heatmap-Based Decision SUpport for Repositioning in Ride-Sharing Systems. Transportation Science, 58(1), 110-130. https://doi.org/10.1287/trsc.2023.1202
  • Ausseil, R., Pazour, J.A., & Ulmer, M.W. (2022). Supplier Menus for Dynamic Matching in Peer-to-Peer Transportation Platforms. Transportations Science, 56(5), 1304-1326. https://doi.org/10.1287/trsc.2022.1133
  • Ulmer, M.W., Erera, A., & Savelsbergh, M. (2022). Dynamic service area sizing in urban delivery. OR Spectrum, 44, 763-793. https://doi.org/10.1007/s00291-022-00666-z
  • Hildebrandt, F.D., & Ulmer, M.W. (2021). Supervised Learning for Arrival Time Estimations in Restaurant Meal Delivery. Transportation Science, 56(4), 1058-1084. https://doi.org/10.1287/trsc.2021.1095
  • Brinkmann, J., Ulmer, M.W., & Mattfeld, D.C. (2019). Dynamic Lookahead Policies for Stochastic-Dynamic Inventory Routing in Bike Sharing Systems. Computers & Operations Research, 106, 260-279. https://doi.org/10.1016/j.cor.2018.06.004
  • Ulmer, M.W., & Thomas, B.W. (2019). Enough Waiting for the Cable Guy - Estimating Arrival Times for Service Vehicle Routing. Transportation Science, 53(3), 897-916. https://doi.org/10.1287/trsc.2018.0846

Last Modification: 27.10.2025 -
 Contact Person: Webmaster