Cyprien Hoelzl

Predictive systems that anticipate failures and optimize operations.

Trained as a civil engineer and PhD researcher, I specialize in turning sensor data and complex systems into reliable forecasts and actionable risk insights. My work spans predictive maintenance, operational monitoring, and decision-support systems for high-stakes environments.
6+ yrs
Predictive modeling & risk analytics
Co-founded
Irmos Technologies AG
ETH PhD
Infrastructure Monitoring

Core experience

Predictive modeling

Time-series forecasting and anomaly detection on high-frequency sensor data. Built early-warning systems that reduced operational downtime and improved reliability.

Risk analysis

Monte Carlo simulation, Bayesian inference, and stochastic processes applied from railway maintenance planning to investment risk assessment.

Team leadership

Led cross-functional projects as Head of Innovation, managing stakeholders, contracts, and delivering systems under tight deadlines.

Production ML

Deployed scalable pipelines on GCP (Python, TensorFlow, BigQuery). Built dashboards translating technical metrics into business decisions.

Research

Railway weld monitoring

Fusing expert knowledge with sensor data for condition assessment. Published in Sensors, 2023.

Read paper

Reinforcement learning for maintenance

Comparing value-based and policy-based Reinforcement Learning for infrastructure planning. Published in Structural Health Monitoring, 2023.

Read paper

Selected projects

Real-time Anomaly Detection at Scale

Built distributed monitoring system processing sensor data across multiple sites. Machine Learning models detected to detect asset health, enabling proactive maintenance and reducing downtime.

Technical details

Data-Informed Decision Making

Developed analytics platform combining operational metrics with data-driven indicators. Monte Carlo simulations provided confidence intervals for resource allocation decisions.

Case study

Railway Infrastructure Deterioration Models

PhD research using Bayesian networks to fuse expert knowledge with inspection data. Algorithms estimate remaining service life of railway welds. Collaboration with Swiss Federal Railways.

Read paper

Smart Garment Sizing Recommendation

ETH Entrepreneurship Award 2020. Concept combining camera, accelerometer, and gyroscope data to estimate body measurements and reduced the fashion e-commerce return rates.

Wind Turbine Fatigue Estimation

Applied unsupervised learning to identify operational modes from turbine sensor data. Estimated remaining lifetime via fatigue damage accumulation models.

Home Automation

Adøn Power Down project. Developed user detection system to automatically cut standby power consumption, combining motion sensors with usage pattern learning.