Center for Applied Research on Supply Chain Services at Fraunhofer IIS
Center for Applied Research on Supply Chain Services at Fraunhofer IIS

Dr. Ursula Neumann

Expand all Close all

The list of Data Science applications – and challenges – along the supply chain is endless. Some of the most promising applications are expected to transform many supply chain functions, including demand forecasting, distribution, production error analysis and pricing.

Applications include predictive and prescriptive analytics, for example, which can be used to improve the accuracy of demand forecasting by using advanced forecasting algorithms. More accurate forecasts of aftersales all-time-demand lead to increased environmental sustainability in the company. So does resource-efficient production through predictive and explainable production failure analysis, which additionally achieves many savings due to improved production quality and lower scrapping rates.Price forecasts, in turn, provide companies with tools to react to market behavior and achieve enormous savings in purchasing.

That is why Dr. Ursula Neumann, head of the »Data Science« group, is working with her team to adapt existing forecasting methods and develop new ones in order to use them to leverage added value in logistics, retail and production and to promote sustainability for the digitalized supply chain.

Research focus:

  • Demand forecasting
    • Transportation volume forecasting
    • inventory management
    • Life cycle forecasting/ all-time demand of spare parts or components
    • Energy Demand Forecasting
  • Commodity price forecasting
  • Quantification of forecast uncertainties
  • Explainable production error analysis
  • Environmental and social sustainability through forecasting applications and resource-efficient AI

Competencies of the Data Science group:

  • Feature Engineering/Selection
  • Time Series Forecasting
    • Classical statistical models
    • Hierarchical Time Series Forecasting
    • Neural Networks
    • Bayesian models
  • Classification (e.g. Tree-Based Models)Quantification of forecast uncertainties
  • Clustering
  • Root-cause analysis (probabilistic models)
  • ML Ops architecture
  • Quantum Machine Learning

since 2021
Research field manager for the research field »Sustainability in the Digital Supply Chain«

since 2020
Group leader of the group »Data Science« in the »Analytics« department of the Center for Applied Research on Supply Chain Services at Fraunhofer IIS

2019 until 2020
Research associate in the group »Data Science & Optimization« of the department »Analytics« of the Center for Applied Research on Supply Chain Services at Fraunhofer IIS

20017 until 2019
Postdoc at the Philipps University Marburg

2014 until 2017
PhD in Bioinformatics, TU Munich

2013
University of Regensburg, M.Sc. in Mathematics

Publications:

Mera-Gaona, M., López, D. M., Vargas-Canas, R., & Neumann, U. (2021). Framework for the Ensemble of Feature Selection Methods. Applied Sciences, 11(17), 8122.

Mera-Gaona, M., Neumann, U., Vargas-Canas, R., & López, D. M. (2021). Evaluating the impact of multivariate imputation by MICE in feature selection. Plos one, 16(7), e0254720.

Löhnert, M., Neumann, U. 6 Schieder, C. (2020). Lageroptimierung von Vendor-Managed-Inventories - Datenaufbereitung für Advanced Analytics. BI Spektrum, 4/2020

Neumann, B., Angstwurm, K., Mergenthaler, P., Kohler, S., Schönenberger, S., Bösel, J., …, Neumann, U., ... & German Myasthenic Crisis Study Group. (2020). Myasthenic crisis demanding mechanical ventilation: a multicenter analysis of 250 cases. Neurology, 94(3), e299-e313.

Neumann, U., Genze, N., & Heider, D. (2017). EFS: an ensemble feature selection tool implemented as R-package and web-application. BioData mining, 10(1), 1-9.

Neumann, U., Riemenschneider, M., Sowa, J. P., Baars, T., Kälsch, J., Canbay, A., & Heider, D. (2016). Compensation of feature selection biases accompanied with improved predictive performance for binary classification by using a novel ensemble feature selection approach. BioData mining, 9(1), 1-14.

Baars, T., Neumann, U., Jinawy, M., Hendricks, S., Sowa, J. P., Kälsch, J., ... & Canbay, A. (2016). In acute myocardial infarction liver parameters are associated with stenosis diameter. Medicine, 95(6).