Curriculum vitae

Oliver Hennhöfer

Research in machine learning and statistical methodology, with a focus on uncertainty, anomaly detection, and conformal inference.

Karlsruhe University of Applied Sciences
oliver.hennhoefer@h-ka.de

Experience

Research Associate

Intelligent Systems Research Group, Karlsruhe University of Applied Sciences
September 2023 — Present

Research on uncertainty quantification for anomaly detection in data streams, with a focus on conformal inference and statistical error control.

Within BiFlex-Industrie, I lead development of off-key, translating research into a practical platform for online anomaly detection. The initial application is monitoring bidirectional charging infrastructure, with the aim of supporting uses beyond the project.

I set technical direction and development priorities, write most of the code, and supervise student contributors. Deployment is primarily handled by a student research assistant under my guidance and overall responsibility.

Software Engineer · Machine Learning

INIT Group · May 2022 — September 2023

Developed a cloud-based real-time application for public transport, with sole responsibility for the machine-learning pipeline used to predict passenger numbers.

Business Analyst · Project Coordination

INIT Group · January 2021 — May 2022

Student Research Assistant · Statistics with R

Karlsruhe University of Applied Sciences · October 2018 — January 2021

Master’s Thesis Research

Disy Informationssysteme · March 2020 — September 2020

Applied geostatistics and spatial econometrics to anomaly detection in environmental data. Deployed methods through an API and improved the project’s data preprocessing.

Working Student · Data Analysis & Quality Assurance

1&1 IONOS · March 2018 — February 2020

Quality assurance from March 2018 to June 2019; data analysis from June 2019 to February 2020.

Intern · Traffic Statistics

Modus Consult Gericke · October 2015 — March 2016

Teaching

Lecturer

Karlsruhe University of Applied Sciences · September 2023 — Present

Master’s courses: Unsupervised Learning; Data Science.
Bachelor’s courses: Software Engineering; Environmental Monitoring.

Education

M.Sc. Geomatics

Karlsruhe University of Applied Sciences · 2018 — 2020

Thesis: Anomaly Detection in Precision Farming with R.

Coursework in object-oriented and web programming, software engineering, spatial databases, geostatistics, web services and geomonitoring, and open-source GIS.

B.Sc. Geoinformation Management

Karlsruhe University of Applied Sciences · 2013 — 2017

Thesis: Statistik und Geoanalyse mit R im hochschulischen Kontext.

Technical background

Statistics & inference. Statistical modelling, econometrics, resampling, density estimation, and uncertainty quantification; conformal inference, sequential testing, and false discovery rate control with p-values and e-values.
Machine learning. Anomaly and change-point detection, online learning, model evaluation, and prediction pipelines; deep learning and NLP with language models. Tools include scikit-learn, PyOD, PyTorch, and Hugging Face Transformers.
Geospatial analysis. GIS, geostatistics, spatial econometrics, clustering, hotspot and spatial outlier detection, and environmental data analysis; ArcGIS and ArcPy.
Programming & applications. Python, R, Java, SQL, and TypeScript/JavaScript; object-oriented design, REST APIs with FastAPI, and interactive interfaces with React and Shiny.
Data systems. Relational data modelling and PostgreSQL, asynchronous services, MQTT sensor streams, telemetry processing, and monitoring dashboards.
Scientific software & delivery. Python and R package development, reproducible experiments, automated testing, documentation, and release workflows; Git, GitHub Actions, and Docker, with oversight of containerized deployment.

Research software

off-key

A platform for online anomaly detection, connecting sensor data, conformal inference, and monitoring interfaces. Developed within BiFlex-Industrie for charging infrastructure, with broader applications in mind.

nonconform

Conformal anomaly detection in Python: score calibration, false discovery rate control, and sequential change monitoring. Integrates with scikit-learn, PyOD, and custom detectors.

online-fdr

Sequential hypothesis testing with p-values and e-values. Python implementations of online false discovery rate control.

aberrant

Online anomaly detection for streaming data. Python methods and tooling for identifying unusual observations as a stream unfolds.

talk-tag

LLM-based annotation of morphosyntactic errors in speech transcripts, developed for language research with limited training data.

Publications

Between Resolution Collapse and Variance Inflation: Weighted Conformal Anomaly Detection in Low-Data Regimes
O Hennhöfer, C Preisach
arXiv preprint arXiv:2603.23205 · 2026
TalkTag: Fine-Grained Morphosyntactic Error Annotation for Transcribed Speech
S Venturini, O Hennhöfer, S Kinkel, J Strötgen
Proceedings of the 20th Linguistic Annotation Workshop (LAW XX), 309–322 · 2026
Conformal Anomaly Detection in Python: Moving Beyond Heuristic Thresholds with nonconform
O Hennhöfer, M Kirsch, C Preisach
Fifteenth Symposium on Conformal and Probabilistic Prediction with Applications (COPA), PMLR 329, 613–632 · 2026
Interdisciplinary Harmonies: A Story-Driven Course on AI and Music to Increase Interest in Computer Science
K Marquardt, Q Shang, O Hennhöfer, L Happe
Proceedings of the 6th European Conference on Software Engineering Education (ECSEE), 145–153 · 2025
Leave-One-Out-, Bootstrap- and Cross-Conformal Anomaly Detectors
O Hennhöfer, C Preisach
IEEE International Conference on Knowledge Graph (ICKG), 110–119 · 2024
Multidimensional Exploratory Spatial Data Analysis
O Hennhöfer, J Bruns, P Ullrich, A Heiß, G Sharipov, D Paraforos
GI_Forum, 9(2), 136–151 · 2021