direkt zum Inhalt springen

direkt zum Hauptnavigationsmenü

Sie sind hier

TU Berlin

Inhalt des Dokuments

Anonymous Predictive People Analytics (AnyPPA)


The joint research project AnyPPA is carried out by the DSI group from the TU Berlin in cooperation with FZI, anacision GmbH, Haufe-umantis AG and Exxeta AG. The aim of the project is the investigation and exploration of employee-friendly data collection and analysis, compliant to data protection regulations.

The increased digitization affected the area of the human resource department. Under the keyword "People Analytics", it is possible to accompany the whole "Employee Journey"---from employment, training, and reorientation---with data driven decisions to improve the strategic enterprise success. The main aspect for this success is the processing of employee data, which is under special protection in Germany and the EU. Especially, employee representatives, works committee, and privacy advocates are critical of People Analytics, due to risk of abuse.

The aim of the project is the development of an employee-friendly software, which allows anonymous predictive People Analytics, using employee data from different sources. We want to redefine People Analytics from the employee perspective for personal support, improvement of personnel development and removal of deficit in the human resource departments (e.g. subjectivity, bias in the personal acquisition/ development, improvement of diversity and fairness). Our project results help to adjust human resource management to empirical insights. To protect employee data, we analyze the usage of data anonymization, which allow information about the collection of employees without exposing single identities. Additionally, we investigate the usage of Distributed Ledger Technologies as a transparency-enhancing technology to transparently document data access and data processing. Our solutions are reviewed on legal confirmation concerning the data protection regulation with a legal assessment.

Related Research Areas

  • Privacy-preserving statistics
  • Differential Privacy
  • Probabilistic datastructures
  • Survey techniques for sensitive Questions
  • Blockchain technologies
  • Data Networks


Saskia Nuñez von Voigt and Florian Tschorsch (2019). RRTxFM: Probabilistic Counting for Differentially Private Statistics. TPSIE '19: Workshop on Trust and Privacy Aspects of Smart Information Environments

Erik Daniel and Elias Rohrer and Florian Tschorsch (2019). Map-Z: Exposing the Zcash Network in Times of Transition. LCN '19: Proceedings of the 44th IEEE International Conference on Local Computer Networks

Saskia Nuñez von Voigt and Stephan Fahrenkrog-Petersen and Dominik Janssen and Agnes Koschmider and Florian Tschorsch and Felix Mannhardt and Olaf Landsiedel and Matthias Weidlich (2020). Quantifying the Re-identification Risk of Event Logs for Process Mining. CAiSE '20: International Conference on Advanced Information Systems Engineering

Saskia Nuñez von Voigt and Mira Pauli and Johanna Reichert and Florian Tschorsch (2020). Every Query Counts: Analyzing the Privacy Loss of Exploratory Data Analyses. DPM '20: 15th International Workshop on Data Privacy Management

Saskia Nuñez von Voigt and Erik Daniel and Florian Tschorsch (2021). Self-Determined Reciprocal Recommender System with Strong Privacy Guarantees. ARES '21: Proceedings of the 16th International Conference on Availability, Reliability and Security

Erik Daniel and Florian Tschorsch (2021). Poster: Towards Verifiable Mutability for Blockchains. EuroS&P '21: Proceedings of the 2021 IEEE European Symposium on Security and Privacy, 722-724.

Erik Daniel and Florian Tschorsch (2022). IPFS and Friends: A Qualitative Comparison of Next Generation Peer-to-Peer Data Networks. IEEE Communications Surveys & Tutorials, 31–52.

Zusatzinformationen / Extras

Quick Access:

Schnellnavigation zur Seite über Nummerneingabe

Auxiliary Functions