Home | Opportunities | MLCU

MCML - Machine Learning Consulting Unit

The Machine Learning Consulting Unit (MLCU) is part of the of the MCML and offers applied researchers scientific consulting regarding the application and evaluation of machine learning methods.

Empowering Research Through Expert Consulting

Our primary goal is to provide consulting to applied sciences, for example medicine, psychology, biology and others. We aim to provide solutions, that based on our experience and expertise are most suitable to answer the research question at hand.

Consulting is free of charge (ca. 8h per project) for members of the MCML and the LMU. Consulting outside the MCML and LMU is also possible, but needs to be negotiated on a case by case basis. We also welcome joint research projects with the goal of publication and other forms of cooperation.

If you are interested in consulting, please contact us. Our experience shows, that it is advisable to register for consulting as early in the project as possible or even at the planning stage.

Team

Link to Andreas Bender

Andreas Bender

Dr.

Coordinator Statistical and Machine Learning Consulting

Machine Learning Consulting Unit (MLCU)

Link to Bernd Bischl

Bernd Bischl

Prof. Dr.

Statistical Learning & Data Science

Link to Ludwig Bothmann

Ludwig Bothmann

Dr.

Statistical Learning & Data Science

Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group


Contact

If you are interested in consulting, please register using our webform.

For other request contact mlcu[at]stat.uni-muenchen.de

For statistical consulting also consider contacting the Statistical Consulting Unit (StaBLab).


Recent and Current Projects

Find a selection of projects that resulted from consulting requests in the past

  • Personality prediction from eye-tracking data

  • Landmark recognition from satellite imaging

  • Survival prediction based on radiomics and image data

  • Classifying neck pain status using scalar and functional biomechanical variables using functional data boosting

  • Interpretable machine learning models for classifying low back pain status using functional physiological variables

  • Wildlife image classification

  • Clinical predictive modeling of post-surgical recovery in individuals with cervical radiculopathy

  • Automated classification of atmospheric circulation patterns using Deep Learning

  • Classification of rain types

  • Clustering of German tourist types

  • Prediction of sports injuries in football

Publications of the MLCU

2024


[28]
A. Mittermeier, M. Aßenmacher, B. Schachtner, S. Grosu, V. Dakovic, V. Kandratovich, B. Sabel and M. Ingrisch.
Automatische ICD-10-Codierung.
Die Radiologie 64 (Aug. 2024). DOI.
MCML Authors
Link to Andreas Mittermeier

Andreas Mittermeier

Dr.

Clinical Data Science in Radiology

C1 | Medicine

Link to Matthias Aßenmacher

Matthias Aßenmacher

Dr.

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to Balthasar Schachtner

Balthasar Schachtner

Dr.

Clinical Data Science in Radiology

C1 | Medicine

Link to Michael Ingrisch

Michael Ingrisch

Prof. Dr.

Clinical Data Science in Radiology

C1 | Medicine


[27]
A. Solderer, S. P. Hicklin, M. Aßenmacher, A. Ender and P. R. Schmidlin.
Influence of an allogenic collagen scaffold on implant sites with thin supracrestal tissue height: a randomized clinical trial.
Clinical Oral Investigations 28.313 (May. 2024). DOI.
MCML Authors
Link to Matthias Aßenmacher

Matthias Aßenmacher

Dr.

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability


[26]
F. Coens, N. Knops, I. Tieken, S. Vogelaar, A. Bender, J. J. Kim, K. Krupka, L. Pape, A. Raes, B. Tönshoff, A. Prytula and C. Registry.
Time-Varying Determinants of Graft Failure in Pediatric Kidney Transplantation in Europe.
Clinical Journal of the American Society of Nephrology 19.3 (Mar. 2024). DOI.
Abstract

Little is known about the time-varying determinants of kidney graft failure in children. We performed a retrospective study of primary pediatric kidney transplant recipients (younger than 18 years) from the Eurotransplant registry (1990-2020). Piece-wise exponential additive mixed models were applied to analyze time-varying recipient, donor, and transplant risk factors. Primary outcome was death-censored graft failure.

MCML Authors
Link to Andreas Bender

Andreas Bender

Dr.

Statistical Learning & Data Science

Coordinator Statistical and Machine Learning Consulting

A1 | Statistical Foundations & Explainability


[25]
W. H. Hartl, P. Kopper, L. Xu, L. Heller, M. Mironov, R. Wang, A. G. Day, G. Elke, H. Küchenhoff and A. Bender.
Relevance of Protein Intake for Weaning in the Mechanically Ventilated Critically Ill: Analysis of a Large International Database.
Critical Care Medicine 50.3 (Mar. 2024). DOI.
Abstract

The association between protein intake and the need for mechanical ventilation (MV) is controversial. We aimed to investigate the associations between protein intake and outcomes in ventilated critically ill patients.

MCML Authors
Link to Helmut Küchenhoff

Helmut Küchenhoff

Prof. Dr.

Statistical Consulting Unit (StaBLab)

C4 | Computational Social Sciences

Link to Andreas Bender

Andreas Bender

Dr.

Statistical Learning & Data Science

Coordinator Statistical and Machine Learning Consulting

A1 | Statistical Foundations & Explainability


[24]
B. X. Liew, F. Pfisterer, D. Rügamer and X. Zhai.
Strategies to optimise machine learning classification performance when using biomechanical features.
Journal of Biomechanics 165 (Mar. 2024). DOI.
MCML Authors
Link to Florian Pfisterer

Florian Pfisterer

Dr.

* Former member

A1 | Statistical Foundations & Explainability

Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability


[23]
B. X. W. Liew, D. Rügamer and A. V. Birn-Jeffery.
Neuromechanical stabilisation of the centre of mass during running.
Gait and Posture 108 (Feb. 2024). DOI.
MCML Authors
Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability


[22]
T. Weber, M. Ingrisch, B. Bischl and D. Rügamer.
Constrained Probabilistic Mask Learning for Task-specific Undersampled MRI Reconstruction.
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2024). Waikoloa, Hawaii, Jan 04-08, 2024. DOI.
MCML Authors
Link to Tobias Weber

Tobias Weber

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to Michael Ingrisch

Michael Ingrisch

Prof. Dr.

Clinical Data Science in Radiology

C1 | Medicine

Link to Bernd Bischl

Bernd Bischl

Prof. Dr.

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability


[21]
J. Gertheiss, D. Rügamer, B. Liew and S. Greven.
Functional Data Analysis: An Introduction and Recent Developments.
Biometrical Journal (2024). To be published. Preprint at arXiv. arXiv. GitHub.
MCML Authors
Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability


2023


[20]
L. Bothmann, L. Wimmer, O. Charrakh, T. Weber, H. Edelhoff, W. Peters, H. Nguyen, C. Benjamin and A. Menzel.
Automated wildlife image classification: An active learning tool for ecological applications.
Ecological Informatics 77 (Nov. 2023). DOI.
MCML Authors
Link to Ludwig Bothmann

Ludwig Bothmann

Dr.

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to Lisa Wimmer

Lisa Wimmer

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to Tobias Weber

Tobias Weber

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability


[19]
T. Weber, M. Ingrisch, B. Bischl and D. Rügamer.
Unreading Race: Purging Protected Features from Chest X-ray Embeddings.
Under review. Preprint at arXiv (Nov. 2023). arXiv.
MCML Authors
Link to Tobias Weber

Tobias Weber

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to Michael Ingrisch

Michael Ingrisch

Prof. Dr.

Clinical Data Science in Radiology

C1 | Medicine

Link to Bernd Bischl

Bernd Bischl

Prof. Dr.

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability


[18]
B. X. W. Liew, F. M. Kovacs, D. Rügamer and A. Royuela.
Automatic variable selection algorithms in prognostic factor research in neck pain.
Journal of Clinical Medicine (Sep. 2023). DOI.
MCML Authors
Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability


[17]
F. Ott, D. Rügamer, L. Heublein, B. Bischl and C. Mutschler.
Auxiliary Cross-Modal Representation Learning With Triplet Loss Functions for Online Handwriting Recognition.
IEEE Access 11 (Aug. 2023). DOI.
MCML Authors
Link to Felix Ott

Felix Ott

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability

Link to Bernd Bischl

Bernd Bischl

Prof. Dr.

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability


[16]
B. X. W. Liew, D. Rügamer, Q. Mei, Z. Altai, X. Zhu, X. Zhai and N. Cortes.
Smooth and accurate predictions of joint contact force timeseries in gait using overparameterised deep neural networks.
Frontiers in Bioengineering and Biotechnology 11 (Jul. 2023). DOI.
MCML Authors
Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability

Link to Xiaoxiang Zhu

Xiaoxiang Zhu

Prof. Dr.

Data Science in Earth Observation

C3 | Physics and Geo Sciences


[15]
K. Rath, D. Rügamer, B. Bischl, U. von Toussaint and C. Albert.
Dependent state space Student-t processes for imputation and data augmentation in plasma diagnostics.
Contributions to Plasma Physics 63.5-6 (May. 2023). DOI.
MCML Authors
Link to Katharina Rath

Katharina Rath

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability

Link to Bernd Bischl

Bernd Bischl

Prof. Dr.

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability


2022


[14]
I. Ziegler, B. Ma, E. Nie, B. Bischl, D. Rügamer, B. Schubert and E. Dorigatti.
What cleaves? Is proteasomal cleavage prediction reaching a ceiling?.
Workshop on Learning Meaningful Representations of Life (LMRL 2022) at the 36th Conference on Neural Information Processing Systems (NeurIPS 2022). New Orleans, LA, USA, Nov 28-Dec 09, 2022. URL.
MCML Authors
Link to Bolei Ma

Bolei Ma

Social Data Science and AI Lab

C4 | Computational Social Sciences

Link to Ercong Nie

Ercong Nie

Statistical NLP and Deep Learning

B2 | Natural Language Processing

Link to Bernd Bischl

Bernd Bischl

Prof. Dr.

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability

Link to Emilio Dorigatti

Emilio Dorigatti

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability


[13]
E. Pretzsch, V. Heinemann, S. Stintzing, A. Bender, S. Chen, J. W. Holch, F. O. Hofmann, H. Ren, F. Küchenhoff, J. Werner and W. K. Angele.
EMT-Related Genes Have No Prognostic Relevance in Metastatic Colorectal Cancer as Opposed to Stage II/III: Analysis of the Randomised, Phase III Trial FIRE-3 (AIO KRK 0306; FIRE-3).
Cancers 14.22 (Nov. 2022). DOI.
MCML Authors
Link to Andreas Bender

Andreas Bender

Dr.

Statistical Learning & Data Science

Coordinator Statistical and Machine Learning Consulting

A1 | Statistical Foundations & Explainability

Link to Shuo Chen

Shuo Chen

Database Systems & Data Mining

A3 | Computational Models


[12]
K. Rath, D. Rügamer, B. Bischl, U. von Toussaint, C. Rea, A. Maris, R. Granetz and C. Albert.
Data augmentation for disruption prediction via robust surrogate models.
Journal of Plasma Physics 88.5 (Oct. 2022). DOI.
Abstract

The goal of this work is to generate large statistically representative data sets to train machine learning models for disruption prediction provided by data from few existing discharges. Such a comprehensive training database is important to achieve satisfying and reliable prediction results in artificial neural network classifiers. Here, we aim for a robust augmentation of the training database for multivariate time series data using Student $t$ process regression. We apply Student $t$ process regression in a state space formulation via Bayesian filtering to tackle challenges imposed by outliers and noise in the training data set and to reduce the computational complexity. Thus, the method can also be used if the time resolution is high. We use an uncorrelated model for each dimension and impose correlations afterwards via colouring transformations. We demonstrate the efficacy of our approach on plasma diagnostics data of three different disruption classes from the DIII-D tokamak. To evaluate if the distribution of the generated data is similar to the training data, we additionally perform statistical analyses using methods from time series analysis, descriptive statistics and classic machine learning clustering algorithms.

MCML Authors
Link to Katharina Rath

Katharina Rath

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability

Link to Bernd Bischl

Bernd Bischl

Prof. Dr.

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability


[11]
W. Ghada, E. Casellas, J. Herbinger, A. Garcia-Benadí, L. Bothmann, N. Estrella, J. Bech and A. Menzel.
Stratiform and Convective Rain Classification Using Machine Learning Models and Micro Rain Radar.
Remote Sensing 14.18 (Sep. 2022). DOI.
MCML Authors
Link to Julia Herbinger

Julia Herbinger

Dr.

* Former member

A1 | Statistical Foundations & Explainability

Link to Ludwig Bothmann

Ludwig Bothmann

Dr.

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability


[10]
M. Mittermeier, M. Weigert, D. Rügamer, H. Küchenhoff and R. Ludwig.
A deep learning based classification of atmospheric circulation types over Europe: projection of future changes in a CMIP6 large ensemble.
Environmental Research Letters 17.8 (Jul. 2022). DOI.
MCML Authors
Maximilian Weigert

Maximilian Weigert

* Former member

C4 | Computational Social Sciences

Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability

Link to Helmut Küchenhoff

Helmut Küchenhoff

Prof. Dr.

Statistical Consulting Unit (StaBLab)

C4 | Computational Social Sciences


[9]
F. Ott, D. Rügamer, L. Heublein, B. Bischl and C. Mutschler.
Joint Classification and Trajectory Regression of Online Handwriting Using a Multi-Task Learning Approach.
IEEE/CVF Winter Conference on Applications of Computer Vision (WACV 2022). Waikoloa, Hawaii, Jan 04-08, 2022. DOI.
MCML Authors
Link to Felix Ott

Felix Ott

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability

Link to Bernd Bischl

Bernd Bischl

Prof. Dr.

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability


[8]
A. Python, A. Bender, M. Blangiardo, J. B. Illian, Y. Lin, B. Liu, T. C. D. Lucas, S. Tan, Y. Wen, D. Svanidze and J. Yin.
A downscaling approach to compare COVID-19 count data from databases aggregated at different spatial scales.
Journal of the Royal Statistical Society. Series A (Statistics in Society) 185.1 (Jan. 2022). DOI.
MCML Authors
Link to Andreas Bender

Andreas Bender

Dr.

Statistical Learning & Data Science

Coordinator Statistical and Machine Learning Consulting

A1 | Statistical Foundations & Explainability


2021


[7]
T. Weber, M. Ingrisch, M. Fabritius, B. Bischl and D. Rügamer.
Survival-oriented embeddings for improving accessibility to complex data structures.
Workshop on Bridging the Gap: from Machine Learning Research to Clinical Practice at the 35th Conference on Neural Information Processing Systems (NeurIPS 2021). Virtual, Dec 06-14, 2021. arXiv.
MCML Authors
Link to Tobias Weber

Tobias Weber

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to Michael Ingrisch

Michael Ingrisch

Prof. Dr.

Clinical Data Science in Radiology

C1 | Medicine

Link to Bernd Bischl

Bernd Bischl

Prof. Dr.

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability


[6]
T. Weber, M. Ingrisch, B. Bischl and D. Rügamer.
Towards modelling hazard factors in unstructured data spaces using gradient-based latent interpolation.
Workshop on Deep Generative Models and Downstream Applications at the 35th Conference on Neural Information Processing Systems (NeurIPS 2021). Virtual, Dec 06-14, 2021. PDF.
MCML Authors
Link to Tobias Weber

Tobias Weber

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to Michael Ingrisch

Michael Ingrisch

Prof. Dr.

Clinical Data Science in Radiology

C1 | Medicine

Link to Bernd Bischl

Bernd Bischl

Prof. Dr.

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability

Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability


[5]
M. Mittermeier, M. Weigert and D. Rügamer.
Identifying the atmospheric drivers of drought and heat using a smoothed deep learning approach.
Workshop on Tackling Climate Change with Machine Learning at the 35th Conference on Neural Information Processing Systems (NeurIPS 2021). Virtual, Dec 06-14, 2021. PDF.
Abstract

Europe was hit by several, disastrous heat and drought events in recent summers. Besides thermodynamic influences, such hot and dry extremes are driven by certain atmospheric situations including anticyclonic conditions. Effects of climate change on atmospheric circulations are complex and many open research questions remain in this context, e.g., on future trends of anticyclonic conditions. Based on the combination of a catalog of labeled circulation patterns and spatial atmospheric variables, we propose a smoothed convolutional neural network classifier for six types of anticyclonic circulations that are associated with drought and heat. Our work can help to identify important drivers of hot and dry extremes in climate simulations, which allows to unveil the impact of climate change on these drivers. We address various challenges inherent to circulation pattern classification that are also present in other climate patterns, e.g., subjective labels and unambiguous transition periods.

MCML Authors
Maximilian Weigert

Maximilian Weigert

* Former member

C4 | Computational Social Sciences

Link to David Rügamer

David Rügamer

Prof. Dr.

Data Science Group

A1 | Statistical Foundations & Explainability


[4]
M. P. Fabritius, M. Seidensticker, J. Rueckel, C. Heinze, M. Pech, K. J. Paprottka, P. M. Paprottka, J. Topalis, A. Bender, J. Ricke, A. Mittermeier and M. Ingrisch.
Bi-Centric Independent Validation of Outcome Prediction after Radioembolization of Primary and Secondary Liver Cancer.
Journal of Clinical Medicine 10.16 (Aug. 2021). DOI.
MCML Authors
Link to Andreas Bender

Andreas Bender

Dr.

Statistical Learning & Data Science

Coordinator Statistical and Machine Learning Consulting

A1 | Statistical Foundations & Explainability

Link to Andreas Mittermeier

Andreas Mittermeier

Dr.

Clinical Data Science in Radiology

C1 | Medicine

Link to Michael Ingrisch

Michael Ingrisch

Prof. Dr.

Clinical Data Science in Radiology

C1 | Medicine


[3]
A. Python, A. Bender, A. K. Nandi, P. A. Hancock, R. Arambepola, J. Brandsch and T. C. D. Lucas.
Predicting non-state terrorism worldwide.
Science Advances 7.31 (Jul. 2021). DOI.
MCML Authors
Link to Andreas Bender

Andreas Bender

Dr.

Statistical Learning & Data Science

Coordinator Statistical and Machine Learning Consulting

A1 | Statistical Foundations & Explainability


2019


[2]
G. König and M. Grosse-Wentrup.
A Causal Perspective on Challenges for AI in Precision Medicine.
2nd International Congress on Precision Medicine (PMBC 2019). Munich, Germany, Oct 14-15, 2019.
MCML Authors
Link to Gunnar König

Gunnar König

Dr.

* Former member

A1 | Statistical Foundations & Explainability

Moritz Grosse-Wentrup

Moritz Grosse-Wentrup

Prof. Dr.

* Former member

A1 | Statistical Foundations & Explainability


[1]
J. Goschenhofer, F. M. J. Pfister, K. A. Yuksel, B. Bischl, U. Fietzek and J. Thomas.
Wearable-based Parkinson's Disease Severity Monitoring using Deep Learning.
European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD 2019). Wuerzburg, Germany, Sep 16-20, 2019. DOI.
MCML Authors
Link to Jann Goschenhofer

Jann Goschenhofer

* Former member

A1 | Statistical Foundations & Explainability

Link to Bernd Bischl

Bernd Bischl

Prof. Dr.

Statistical Learning & Data Science

A1 | Statistical Foundations & Explainability