Machine Learning
leading company in the field of microcredit
WebTrekk and Uebermetrics
Professor Lessmann's research focuses on machine learning and artificial intelligence (MLAI) methodologies and their use cases in managerial decision support. Areas of interest include but are not limited to explainable AI, causal/interpretable machine learning, natural language processing, predictive analytics and time series forecasting.
He is specialized in MLAI applications in the broad scope of marketing and risk analytics. He is also actively involved in knowledge transfer, professional education and consulting projects with industry partners ranging from start-ups to global players and non-profit organizations.
- Prototyping, evaluation, and benchmarking of ML/AI-based prediction and decision models
- Development of PD, LGD, and EAD forecasting models
- Processing of textual data for knowledge extraction
- Assessment of the information value of commercially available data sources (e.g., credit bureau data) for predictive modeling
- Estimation of personalized, individual-level treatment effects
- Professional education in ML/AI, data science and business analytics
FinTech - Based on concepts of Bayesian statistics and semi-supervised machine learning, Professor Lessmann and his team have developed a system to solve the problem of inference rejection in the lending industry. Their solutions provide significantly better risk scorecards and make it easier for lenders to predict the predictive power of a scorecard (e.g., the PD) in operation. The project was conducted with a leader in the microcredit space.
E-commerce - Together with WebTrekk and Uebermetrics, Lessmanns working group is developing an AI-driven web controlling system that examines web metric time series (page views, visits, bounce rates, checkouts, sales, etc.) and identifies the causes of observed patterns (e.g., anomalies). To this end, their system integrates deep causal detection algorithms based on reinforced learning and xAI methods. To extend the scope of their root cause explanations, they also monitor various social media streams and use advanced NLP algorithms for event detection. The unique combination of these AI concepts provides web controllers and store managers with advanced insights into their business operations.
Digital marketing - Lessman and his team have developed advanced causal machine learning models for real-time targeting of e-coupons and other digital marketing stimuli. Their optimal (i.e., profit-maximizing) methodology includes both single and multiple treatment scenarios and leverages traditional supervised learning algorithms to enable cost-effective deployment.
Professor Lessmann has taught a number of professional education courses in subject areas such as credit risk modeling, fraud detection, advanced analytics, and machine learning, to name a few. Some of these courses are offered as part of the SAS Business Knowledge Series, but are also available on the R and Python platforms. Requests for professional development in the areas of his expertise are welcome.
- funding by various bodies including DFG, DAAD, IBB (e.g. Transfer Bonus, ProFIT)
Prof. Dr. Alan Akbik conducts research in the field of machine learning (ML) and natural language processing (NLP). His goal is to enable machines to capture, understand, and use natural language like a human.
To this end, he has developed one of the world's leading deep learning frameworks for NLP, which is already being used in over 1,000 research and industrial projects.
Consulting in:
- Deep Learning
- Natural Language Processing (NLP)
- Machine Learning (ML)
- 3 Patents at IBM Research
- Zalando Outstanding Achievement Award
workshop on the analysis of Twitter data for Stiftung Wissenschaft und Politik (SWP)
Professor Jäschke and his team develop and optimize methods in the areas of Big Data and Machine Learning, especially in the aplication fields of Natural Language Processing, Social Bookmarking and Recommendation Systems. This includes the Collection (e.g. through focussed Crawling), Compilation, Annotation (e.g. by means of Crowdsourcing) and Curation of suitable records (data sets).
Further, it includes the Adaptation and Improvement of appropriate Algorythms (e.g. Named Entity Recognition, Classification, Clustering, Information Extraction, etc.) culminating in the development of web-based analysis platforms.
- Hadoop-Cluster
- GPU calculator
- diverse datasets
several medium-sized and DAX companies
Mendling's research focuses on the question how business processes can be efficiently and effectively supported by information systems. To this end, Mendling and his team address questions of the information technology as well as of managerial questions.
Within the framework of business process management they developed a series of technical solutions for process mining and also management tools like the BPM Billboard.
The expertise of Mendling and his team is summarized in the seminal textbook "Fundamentals of Business Process Management", which is used by over 250 universities in 70 countries.
- cooperation with businesses from different branches
- design of training concepts for process management
- performance of training courses and projects for process improvement
- development of new analysis software for business processes
In the context of his projects, Mendling worked together with many medium-sized companies and DAX-companies from different branches.
LL.M. Digitalization and Tax Law
Accor Hotels Germany
SHS VIVEON realisation of training for interviewers
International executive headhunting company: development of customised personality test
Prof. Ziegler's expertise and that of his team lies in the field of psychological diagnostics and deals with all topics of personnel diagnostics in the HR life cycle. They focus on personality, intelligence and situational awareness. Ziegler and his team develop solutions to measure these in relation to requirements and to use them for performance or learning prediction. Therefore they use the full range of qualitative (e.g. interviews) and quantitative methods (e.g. tests, questionnaires, machine learning).
Prof. Ziegler has already carried out several successful projects with well-known companies in this area, involving the creation of competency models, employee surveys, annual appraisals or job aptitude diagnostics. Prof. Ziegler's working group also trains individuals or teams on topics of personnel diagnostics (e.g. assessment centers or interviews). In addition, Prof. Ziegler develops customized diagnostic processes or evaluates them.
- PC lab with 10 workstations and various performance and personality tests
- Online surveys
- Data analysis
- Consulting
- Trainings - wide range of topics
-
Competence model development - Prof. Ziegler and his team have developed competence models for different professions for various clients and made them measurable
-
Accor Hotellerie Deutschland GmbH: Development of competence models
-
SHS VIVEON AG: Implementation of interviewer trainings
-
International headhunting company for executives: Development of a customized personality test
-
Evaluation and optimization - In these projects Prof. Ziegler looks at existing personnel processes, evaluates their quality from a psychological point of view and develops optimizations.
alta4
Geoinformatics AG
NGOs, authorities and global tech- and logistics companies
Prof. Hostert’s explores cutting-edge satellite data analysis. His main focus lies on questions regarding the global change, particularly large-scale mapping in agrarian- and forestry systems and near-nature ecological systems worldwide. He analyses the change of the earth’s surface through different methods, for example with machine learning, big data, time series analyses, hyperspectral and multisensor approaches, as well as multiscale analyses. Regional expertise of the team covers Germany, the mediterranean areas and South America, as well as Central Asia.
- satellite data analysis
- AI in remote sensing
- large-scale remote sensing analysis with big data approaches (particularly Sentinel-2, Landsat), funded through projects of the BMWi, BMBF, BMEL, as well as the EU
- scientific monitoring of satellite missions (Landsat Science Team, EnMAP ScientificAdvisory Group)
- satellite based mapping and land use analysis for NGOs, authorities and global tech- and logistics companies
Prof. Haerdle’s main research interests are quantitative finance, esp. multivariate methods in banking and finance, dimension reduction techniques, and computational statistics. In his roles both as coordinator of the Collaborative Research Center “Economic Risk” (CRC 649) and director of the interdisciplinary Center for Applied Statistics and Economics (C.A.S.E.) he primarily investigates economic risks on a global scale. Prof. Haerdle’s research aims at facilitating the evaluation of such risks and to reduce uncertainty to improve economic actors’ decision-making.
Prof. Haerdle is Distinguished Visiting Professor Wang Yanan Institute for Studies in Economics (WISE) at Xiamen University, China, as well as director of the International Research Training Group “High Dimensional Non Stationary Time Series” (ITRG 1792). Among other distinctions he received the “Econometric Theory Multa Scripsit Award” in 2012.
- multivariate statistical analysis (factor analysis, cluster Analysis, etc.)
- portfolio optimisation
- risk management
- hedging
- pricing derivatives
- functional data analysis
- non- and semi-parametric methods
- data visualisation
- Ongoing cooperation with and lecturing for leading international financial institutions
- Center for Applied Statistics and Economics (C.A.S.E.): interdisciplinary research centre with the goal to analyze and solve current complex economic problems and those arising in related fields with the help of quantitative methods and computing. Its research subjects range from weather risk, aging societies, crime to property markets
- Collaborative Research Center “Economic Risk” (CRC 649): center of transdisciplinary research where insights from economics, mathematics and statistics converge to analyze economic risks and risk factors. The CRC offers an international platform for discussion of the latest research results and collaborations