Dr. Patrick Krennmair

Senior Data Scientist and Researcher

Vienna, Austria

Dr. Patrick Krennmair

My background spans research, consulting, and team leadership at the intersection of technology and global development. I began in academia, using geo-spatial machine learning to explore poverty and inequality. That foundation in digital transformation and international development still shapes how I think today. Most recently, I’ve led teams working on generative AI. I bring an interdisciplinary mindset and a strong passion for AI to every project I take on.

Learn More About Me Get In Touch
Generative AIMachine LearningApplied EconometricsDigital Transformation

Publications & Research

Last updated from Google Scholar on .

View Profile on Google Scholar

Google Scholar is temporarily unavailable. Showing the last verified update (13/10/2026).

101Total Citations
Sort by:
StatisticsPeer-reviewed JournalWorking Paper

Flexible domain prediction using mixed effects random forests

P Krennmair, T Schmid

Journal of the Royal Statistical Society Series C: Applied Statistics 71 (5 …, 2022

74Citations2022

Abstract

This paper promotes the use of random forests as versatile tools for estimating spatially disaggregated indicators in the presence of small area-specific sample sizes. Small area estimators are predominantly conceptualised within the regression-setting and rely on linear mixed models to account for the hierarchical structure of the survey data. In contrast, machine learning methods offer non-linear and non-parametric alternatives, combining excellent predictive performance and a reduced risk of model-misspecification. Mixed effects random forests combine advantages of regression forests with the ability to model hierarchical dependencies. This paper provides a coherent framework based on mixed effects random forests for estimating small area averages and proposes a non-parametric bootstrap estimator for assessing the uncertainty of the estimates. We illustrate advantages of our proposed methodology …

View on Google Scholar View on Publisher/PDF
Statistics

SAEforest: mixed effect random forests for small area estimation

P Krennmair, N Frink

R package version 1 (0), 2022

9Citations2022

Abstract

Description Mixed Effects Random Forests (MERFs) are a data-driven, nonparametric alternative to current methods of Small Area Estimation (SAE).'SAEforest'provides functions for the estimation of regionally disaggregated linear and nonlinear indicators using survey sample data. Included procedures facilitate the estimation of domain-level economic and inequality metrics and assess associated uncertainty. Emphasis lies on straightforward interpretation and visualization of results. From a methodological perspective, the package builds on approaches discussed in Krennmair and Schmid (2022)< arXiv: 2201.10933 v2> and Krennmair et al.(2022)< arXiv: 2204.10736>.

View on Google Scholar View on Publisher/PDF
StatisticsPeer-reviewed Journal

Tree-based machine learning in small area estimation

P Krennmair, N Wurz, T Schmid

The Survey Statistician 86, 22-31, 2022

7Citations2022

Abstract

Reliable estimators of the spatial distribution of socio-economic indicators are essential for evidencebased policy-making. As the accuracy of direct estimates from survey data decrease with spatially finer target levels, small area estimation approaches are promising. In this article, we outline new approaches that combine small area methodology with machine learning methods. The presented semi-parametric approach is promising as it avoids the assumptions of linear mixed models in contrast to classical small area models and builds on random forests. These tree-based machine learning predictors have the advantage of robustness against outliers and implicit model-selection. As for classical small area models, we account for hierarchically dependent data. We present point estimators applicable to full as well as aggregated auxiliary data access and outline their uncertainty measure. We compare methods based on a reproducible and illustrative example using open-source income data from Austria.

View on Google Scholar View on Publisher/PDF
Statistics

Random forests and mixed effects random forests for small area estimation of general parameters: A poverty mapping case study in Mozambique

P Krennmair, N Würz, T Schmid, N Tzavidis

The Annals of Applied Statistics 20 (1), 809-832, 2026

4Citations2026
View on Google Scholar
StatisticsWorking Paper

Analysing opportunity cost of care work using mixed effects random forests under aggregated census data

P Krennmair, N Würz, T Schmid

arXiv preprint arXiv:2204.10736, 2022

4Citations2022

Abstract

Reliable estimators of the spatial distribution of socio-economic indicators are essential for evidence-based policy-making. As sample sizes are small for highly disaggregated domains, the accuracy of the direct estimates is reduced. To overcome this problem small area estimation approaches are promising. In this work we propose a small area methodology using machine learning methods. The semi-parametric framework of mixed effects random forest combines the advantages of random forests (robustness against outliers and implicit model-selection) with the ability to model hierarchical dependencies. Existing random forest-based methods require access to auxiliary information on population-level. We present a methodology that deals with the lack of population micro-data. Our strategy adaptively incorporates aggregated auxiliary information through calibration-weights - based on empirical likelihood - for the estimation of area-level means. In addition to our point estimator, we provide a non-parametric bootstrap estimator measuring its uncertainty. The performance of the proposed point estimator and its uncertainty measure is studied in model-based simulations. Finally, the proposed methodology is applied to the Socio-Economic Panel and aggregate census information from the same year to estimate the average opportunity cost of care work for regional planning regions in Germany.

View on Google Scholar View on Publisher/PDF
Statistics

Analysing opportunity cost of care work using mixed effects random forests under aggregated auxiliary data

P Krennmair, N Würz, T Schmid

Journal of the Royal Statistical Society Series C: Applied Statistics 75 (1 …, 2026

3Citations2026

Abstract

Evidence-based policy-making requires reliable, spatially disaggregated indicators. The framework of mixed effects random forests leverages the advantages of random forests and hierarchical data in small area estimation. These methods require typically access to auxiliary information on population level, which is a strong limitation for practitioners. In contrast, our proposed method—for point and uncertainty estimation—abstains from access to unit-level population data but adaptively incorporates aggregated auxiliary information through calibration weights. We demonstrate its usage for estimating opportunity cost of care work for Germany from the Socio-Economic Panel and census aggregates. Simulation studies evaluate our proposed method.

View on Google Scholar View on Publisher/PDF
StatisticsDissertation

A Framework for the Estimation of Disaggregated Statistical Indicators Using Tree-Based Machine Learning Methods

P Krennmair

0Citations2023

Abstract

The thesis combines four papers that introduce a coherent framework based on MERFs for the estimation of spatially disaggregated economic and inequality indicators and associated uncertainties. Chapter 1 focusses on flexible domain prediction using MERFs. We discuss characteristics of semi-parametric point and uncertainty estimates for domain-specific means. Extensive model- and design-based simulations highlight advantages of MERFs in comparison to 'traditional' LMM-based SAE methods. Chapter 2 introduces the use of MERFs under limited covariate information. The access to population-level micro-data for auxiliary information imposes barriers for researchers and practitioners. We introduce an approach that adaptively incorporates aggregated auxiliary information using calibration-weights in the absence of unit-level auxiliary data. We apply the proposed method to German survey data and use aggregated covariate census information from the same year to estimate the average opportunity cost of care work for 96 planning regions in Germany. In Chapter 3, we discuss the estimation of non-linear poverty and inequality indicators. Our proposed method allows to estimate domain-specific cumulative distribution functions from which desired (non-linear) poverty estimators can be obtained. We evaluate proposed point and uncertainty estimators in a design-based simulation and focus on a case study uncovering spatial patterns of poverty for the Mexican state of Veracruz. Additionally, Chapter 3 informs a methodological discussion on differences and advantages between the use of predictive algorithms and (linear) statistical models …

View on Google Scholar View on Publisher/PDF
StatisticsPeer-reviewed JournalWorking Paper

Flexible domain prediction using mixed effects random forests

T Schmid, P Krennmair

Otto-Friedrich-Universität 71 (5), 2022

0Citations2022

Abstract

This paper promotes the use of random forests as versatile tools for estimating spatially disaggregated indicators in the presence of small area-specific sample sizes. Small area estimators are predominantly conceptualised within the regression-setting and rely on linear mixed models to account for the hierarchical structure of the survey data. In contrast, machine learning methods offer non-linear and non-parametric alternatives, combining excellent predictive performance and a reduced risk of model-misspecification. Mixed effects random forests combine advantages of regression forests with the ability to model hierarchical dependencies. This paper provides a coherent framework based on mixed effects random forests for estimating small area averages and proposes a non-parametric bootstrap estimator for assessing the uncertainty of the estimates. We illustrate advantages of our proposed methodology using Mexican income-data from the state Nuevo León. Finally, the methodology is evaluated in model-based and design-based simulations comparing the proposed methodology to traditional regression-based approaches for estimating small area averages.

View on Google Scholar View on Publisher/PDF
EconomicsPeer-reviewed Journal

Die Macht der Schulden: Interdisziplinäre Perspektiven auf die sozioökonomischen Implikationen von Staatsverschuldung im Kontext der Sustainable Development Goals

M Thalhammer, P Krennmair

Shrinking Spaces: Mehr Raum für globale Zivilgesellschaft, 171-208, 2020

0Citations2020

Abstract

Die Macht der Schulden: Interdisziplinäre Perspektiven auf die sozioökonomischen Implikationen von Staatsverschuldung im Kontext der Sustainable Development Goals — University of Vienna Skip to main navigation Skip to search Skip to main content University of Vienna Home University of Vienna Logo u:cris Info Deutsch English Home Persons Units and bodies Projects Publications Activities Prizes Press/Media Search by expertise, name or affiliation Die Macht der Schulden: Interdisziplinäre Perspektiven auf die sozioökonomischen Implikationen von Staatsverschuldung im Kontext der Sustainable Development Goals Martin Thalhammer, Patrick Krennmair StudiesServiceCenter Social Sciences Vienna Center for Experimental Economics Publications: Contribution to book › Chapter Overview Original language German Title of host publication Shrinking Spaces Subtitle of host publication Mehr Raum für …

View on Google Scholar View on Publisher/PDF
EconomicsWorking Paper

Die Macht der Schulden: Interdisziplinäre Perspektiven auf die sozioökonomischen Implikationen von Staatsverschuldung im Kontext der Sustainable Development Goals

P Krennmair, M Thalhammer

0Citations

Abstract

The achievement of the United Nations Sustainable Development Goals depends not least on the burden of debt borne by each country. In the 2030 Agenda the subject of „debt “is barely mentioned, but for many countries of the Global South it represents an oppressive reality. This article takes the form of a historical, cultural and socio-anthropological analysis illustrating that the moral norm that debts are to be repaid as quickly as possible is relatively new in the history of the human race, and sees the root of the problem of debt in (neo-) colonialism, which placed many countries under a heavy burden of debt. Haiti, for instance, which today is one of the poorest countries on the American continent, had to pay an enormous „independence debt “for its independence from France in 1804, the consequences of which it is still experiencing even today. Structural Adjustment Programs represent a heavy burden for countries which are compelled to submit to neoliberal political and economic programmes in exchange for loans. This paper proposes as a solution a state insolvency process to be carried out on an internationally regulated legal basis.

View on Google Scholar View on Publisher/PDF

Education

Dr.rer.pol. in Applied Statistics

Freie Universität Berlin

2019 - 2022

MSc in Economics

Universität Wien

2016 - 2018

MA in Development Studies

Universität Wien

2016 - 2019

BSc in Statistics

Universität Wien

2015 - 2018

BSc in Economics

Universität Wien

2013 - 2016

Research Interests

Generative AI

Exploring cutting-edge AI technologies and their practical applications

Machine Learning & Statistics

Predictive methods and computational statistics for data-driven insights

Economic Development

Applied econometrics and small area estimation for emerging markets

Digital Transformation

Bridging traditional economics with modern data science approaches

Professional Experience

My journey in data science, statistics, and consulting spanning academia and industry

July 2025 - Present

Current

Senior Data Scientist and Team Lead

Dynatrace

Vienna, Austria•Full-time

I lead a high-impact team focused on advancing Generative AI capabilities within Dynatrace CoPilot. My work combines hands-on data science with leadership and mentoring. I drive the deployment of LLM-powered applications into production, ensuring scalable and reliable performance in cloud environments. Collaboration across product and engineering and research teams is central to aligning our technical innovation with business goals.

Key Achievements:

  • Team Leadership & Mentoring
  • Generative AI & LLMs
  • Cloud-native Deployment
  • Agile Collaboration

2022 - June 2025

Data Science Consultant

Accenture

Vienna, Austria•Full-time

Leading data science initiatives and digital transformation projects for enterprise clients. Specializing in machine learning implementation, statistical analysis, and AI strategy consulting.

Key Achievements:

  • Implementing generative AI solutions for business processes
  • Developing predictive models for operational optimization
  • Leading cross-functional teams in digital transformation projects
  • Providing statistical consulting for strategic decision making

2019 - 2022

PhD Researcher & Statistical Consultant

Freie Universität Berlin & fu:stat

Berlin, Germany•Academic / Consulting

Conducted doctoral research in applied statistics and provided specialized statistical consulting through the fu:stat unit to researchers, institutions, and businesses.

Key Achievements:

  • Conducted research in small area estimation techniques
  • Published peer-reviewed papers on computational statistics
  • Applied econometric methods to real-world problems
  • Designed and analyzed surveys and experiments
  • Developed custom statistical solutions for clients
  • Supervised and trained students and clients

Technical Expertise

AI/ML & Advanced Analytics

Core AI & Machine Learning

Generative AILLM ApplicationsNeural NetworksMachine LearningPredictive AnalyticsMonte Carlo Simulation

Programming & Data Engineering

Languages & Infrastructure

PythonRData ProcessingData EngineeringCloud-native DeploymentBig DataScientific Programming

Research & Statistical Methods

Statistical Analysis

Applied ResearchStatistical Data AnalysisGeo-Spatial StatisticsData ModelingData VisualizationEconomic Research

Professional & Consulting

Leadership & Communication

Stakeholder ManagementTeam Leadership & MentoringConsultancy ServicesPublic SpeakingScientific WritingUniversity Teaching

Get In Touch

I'm always interested in discussing new opportunities, research collaborations, or consulting projects. Let's connect and explore how we can work together.

Send a Message