Find Academic Supervisors

Dr. Amin Keramati is an Assistant Professor of Supply Chain Management at Widener University’s School of Business Administration. He holds a PhD in Transportation & Logistics from North Dakota State University and previously served as a graduate research assistant at the Upper Great Plains Transportation Institute. His work includes federally funded projects like the Mountain-Plains Consortium’s MPC-550 project, focusing on highway-rail grade crossing safety. Dr. Keramati teaches courses in enterprise resource planning, decision analytics, database management, transportation/logistics, project management, and data analytics. Education: PhD in Transportation & Logistics, North Dakota State University Graduate Research Assistant at Upper Great Plains Transportation Institute Research Focus: Dr. Keramati develops mathematical, statistical, and machine learning approaches to solve complex problems in transportation, supply chain, and logistics. Key areas include data mining, big data decision support, transportation network analytics, project scheduling, smart manufacturing, and accident analysis. His interdisciplinary work bridges supply chain optimization with emerging technologies like blockchain for healthcare and clinical trials. Awards & Recognition: Student Paper Award, American Association of State Highway and Transportation Officials (2017) Grants & Projects: Lead researcher on the Mountain-Plains Consortium’s MPC-550 project, which expanded his dissertation work on safety systems for highway-rail crossings. Collaborates on federally funded transportation safety initiatives and supply chain optimization for bioethanol and pharmaceutical industries. Labs/Teams: Active in Widener’s School of Business research groups focusing on supply chain innovation and interdisciplinary projects combining logistics with emerging technologies.

• Transportation & Logistics
• Supply Chain Management
• Data Analytics
• +4 more

Michael A Osborne is Professor of Machine Learning at the University of Oxford and leads the Bayesian Exploration Lab . He serves as Director of the EPSRC Centre for Doctoral Training in Autonomous Intelligent Machines and Systems and co-directs the Oxford Martin AI Governance Initiative. His research focuses on Bayesian optimization, Gaussian processes, and probabilistic numerics with applications in quantum devices, battery modeling, and AI governance. Key Positions: Professor of Machine Learning, University of Oxford Official Fellow, Exeter College Co-founder of Mind Foundry Lead Researcher, Oxford Martin Programme on Technology and Employment Research Themes: Probabilistic modeling for quantum systems Uncertainty quantification in energy storage AI safety and societal impact analysis Automated experimental design Quantum device calibration Probabilistic numerical methods Technical Contributions: Bridging reality gap in quantum devices Efficient Bayesian quadrature techniques Personalized neurostimulation algorithms Automated measurement protocols Quantum-classical hybrid ML

• Machine Learning
• Bayesian Optimization
• Gaussian Processes
• +3 more

Professor Nikos Tzavidis is a Professor of Statistical Methodology at the University of Southampton . He has held academic positions at institutions including University College London and the University of Manchester, and currently leads research initiatives integrating statistical methodology with geospatial and survey data. His work focuses on Small Area Estimation, official statistics, and poverty mapping, with applications across global development and public policy. Research interests: Small Area Estimation and Official Statistics Outlier Robust Inference Quantile and M-quantile Models Geospatial Data Analysis Poverty Mapping Machine Learning Applications in Statistics Recent research trends emphasize machine learning integration, geospatial data utilization, and advanced quantile modeling for poverty and demographic studies. His publications span journals like the Journal of Official Statistics and the Journal of the Royal Statistical Society . Scientific awards: ISI Fellow (2013) American Statistical Association (2004) Vice Chancellor's Teaching Award (2013) Johann von Spix Professor (2023) He supervises PhD students in social statistics, demography, and geography, and serves on editorial boards for journals including the Journal of Official Statistics . Externally, he has held leadership roles in the International Statistical Institute and contributed to United Nations and World Bank projects.

• Small Area Estimation
• Official Statistics
• Outlier Robust Inference
• +7 more

Dino Pedreschi is a Full Professor of Computer Science at the University of Pisa, affiliated with the Department of Computer Science (DI-UNIPI). He co-leads the Pisa KDD Lab, a joint research initiative between the University of Pisa and the Italian National Research Council’s Institute of Information Science and Technology, one of the earliest labs focused on data mining and knowledge discovery. His research spans Big Data Analytics , Social Network Analysis , Human Mobility Analysis , Privacy-by-Design , Explainable AI (XAI) , and ethical data mining . He is a pioneer in privacy-preserving data mining and has contributed significantly to understanding societal impacts of AI and big data. Recent publications highlight trends in explainable AI , fairness-aware data mining , urban mobility modeling , and socio-economic nowcasting , reflecting a strong interdisciplinary focus combining computer science, social science, and policy. Notable scientific awards include: Google Research Award on Privacy (2009) University of Pisa Ordine del Cherubino (2017) Pedreschi has played leadership roles in major conferences such as ECML/PKDD (Co-Chair 2004), ICDM (Vice-Chair 2005), and ICDE (Vice-Chair 2014). He founded the Business Informatics MSc program at the University of Pisa to train interdisciplinary data scientists. He has been a visiting scientist at the University of Texas at Austin, CWI Amsterdam, UCLA, and the Barabási Lab at Northeastern University. He actively contributes to European research initiatives including SoBigData++, FAIR, and TAILOR, and has advised on AI policy, including testimony before the Italian Parliament on AI and labor markets. He is a key member of the Pisa KDD Lab, a leading research group in data science and AI ethics, fostering collaboration between academia and public institutions.

• Big Data Analytics
• Social Network Analysis and Mining
• Analysis of Human Mobility
• +17 more

Dr Donya Hajializadeh is an Associate Professor of Structural Engineering at the University of Surrey's School of Sustainability, Civil and Environmental Engineering. She holds multiple professional qualifications including Chartered Engineer (CEng) and European Engineer (EUR ING), and is a Fellow of the Higher Education Academy (FHEA). Her roles include Director of Employability (since 2020), Deputy Coordinator of the Surrey/ICE Scholarship (since 2019), and IStructE Liaison Officer (since 2021). She is also affiliated with the Surrey Institute for People-Centred Artificial Intelligence (PAI). Her education includes a BEng (Hons), MEng, and PhD in relevant fields. Research focuses on structural health monitoring (SHM), machine learning applications in asset management, and deep learning for damage identification. Key areas include railway bridge dynamics, vibration analysis, and resilience assessment under seismic and environmental hazards. Current PhD students include Chia Sadik (Transport Infrastructure Failure Assessment) and Michael Millgate (Dynamic Characterisation of Tall RC Buildings). Teaching responsibilities include ENG1073 Fluid Mechanics and ENGM054 Earthquake Engineering. Research aligns with sustainable development goals, emphasizing infrastructure sustainability and carbon reduction strategies. Notable projects include rail bridge innovation recognized by the Chief Scientific Adviser Award and presentations on damage identification techniques to government officials. She contributes actively to interdisciplinary initiatives, integrating AI with civil engineering for smarter infrastructure solutions.

• Structural Health Monitoring
• Machine Learning
• Asset Management Systems
• +4 more

Tyler Simko is an Assistant Professor of Political Science at the University of Michigan, specializing in US state and local politics, political geography, and computational social science. His research focuses on understanding and addressing inequality in American public policy through innovative methodological approaches. Education: Ph.D. in Government, Harvard University (2024) A.B. in Politics, Princeton University Simko's research examines state and local politics in the United States with particular focus on political geography and subnational policymaking. His active research agendas include legislative redistricting ("gerrymandering"), local public meetings, school segregation, affordable housing, and data privacy. Methodologically, he develops new techniques in computational social science and machine learning to evaluate subnational inequality and how it can be reduced. His work regularly involves partnerships with federal, state, and local officials to improve the design of public policy. His recent publications demonstrate a strong focus on applying computational methods to address real-world policy challenges, particularly in school desegregation, redistricting, and local government transparency. His research often leverages large-scale data collection efforts, such as LocalView (the largest database of local government meetings in the US), to analyze patterns of political behavior and policy outcomes across different jurisdictions. Awards and Recognition: APSA 2024-25 Best Paper in Education Politics and Policy Award APSA 2024-25 Best Paper in Urban and Local Politics, Honorable Mention MPSA 2024 Robert H. Durr Award for "the best paper applying quantitative methods to a substantive problem" Derek C. Bok Award for Excellence in Graduate Student Teaching of Undergraduates (2023) Simko teaches graduate and undergraduate courses in American Politics and Political Methodology at the University of Michigan. His teaching experience spans multiple institutions, including Harvard University and Princeton University. He has designed innovative courses on US Local Policymaking, data science, and computational social science. As a Data Scientist at the Office of Evaluation Sciences, he partners with federal, state, and local officials to improve program design and reduce administrative burdens. He is a co-PI of the Algorithm-Assisted Redistricting Methodology (ALARM) Project and co-creator of LocalView, the largest audio, video, and text database of local government meetings in the United States. These projects represent significant contributions to the field of computational social science and provide valuable resources for researchers studying local governance and policy-making.

• State and Local Politics
• Political Geography
• Subnational Policymaking
• +5 more

Ridhi Kashyap is a Professor of Demography and Computational Social Science at the University of Oxford, where she contributes significantly to demographic research through innovative computational approaches. She is affiliated with the Leverhulme Centre for Demographic Science, where she co-leads the Digital and Computational Science strand. Her work bridges traditional demographic methods with cutting-edge computational techniques to address pressing social issues related to population dynamics and inequalities. Dr. Kashyap's research spans multiple areas of demography, with particular focus on: Mortality and population health, including pandemic impacts on life expectancy Gender inequality, especially son preference and digital gender gaps Marriage and family dynamics in relation to educational expansion and gender norms Migration and ethnicity patterns using digital data sources Sustainable development goals related to digital access and gender equality Her methodological expertise lies at the intersection of demography and computational social science. She leverages agent-based models, microsimulation, and machine learning techniques applied to novel data streams such as digital trace data from social media platforms. A notable example of her work is the digitalgendergaps.org platform, which nowcasts global digital gender inequalities in internet and mobile access - a key sustainable development goal indicator where official data is lacking. Her research demonstrates how computational approaches can fill critical data gaps and provide timely insights for policy decision-making. Analysis of Dr. Kashyap's recent publications reveals a strong focus on digital demography and computational approaches to understanding population dynamics. Her work frequently examines gender inequalities through digital lenses, including analyses of LinkedIn data to understand professional gender gaps and social media data to track digital access disparities. She has made significant contributions to understanding pandemic mortality patterns, particularly in India and the US, and has pioneered methods for using social media data to nowcast demographic phenomena. Her research consistently bridges theoretical demographic concepts with practical computational methodologies. Dr. Kashyap has been actively involved in several significant research initiatives, including leading the development of the Digital Gender Gaps dashboard and contributing to the creation of the World Cybercrime Index. Her work with the Leverhulme Centre for Demographic Science has positioned her at the forefront of computational demographic research. Within her academic role, Dr. Kashyap supervises graduate students and collaborates with interdisciplinary teams across demography, computer science, and public health. She has secured funding for projects that leverage digital data to address demographic research questions, particularly those related to gender inequality and sustainable development goals. Her work with social media data platforms demonstrates innovative approaches to overcoming traditional data limitations in demographic research. Dr. Kashyap co-leads the Digital and Computational Science strand at the Leverhulme Centre for Demographic Science, where she oversees a team of researchers working at the intersection of demography and computational methods. Her team develops innovative approaches to using digital trace data for demographic research, with particular focus on gender inequality metrics and pandemic impact assessment. The Digital Gender Gaps project represents one of her team's flagship initiatives, providing near-real-time monitoring of a key sustainable development indicator.

• Demography
• Computational Social Science
• Digital Demography
• +5 more

Prof. Peter van der Heijden is a Professor of Statistics for the Social and Behavioural Sciences at Utrecht University's Department of Methodology and Statistics. He also holds a professorship in Social Statistics at the University of Southampton. His roles include chairing the Ethical Review Board and the Committee for Policy on Integrity at Utrecht's Faculty of Social and Behavioural Sciences. He chairs the Advisory Council on Methodology and Quality of Statistics Netherlands and serves on the Executive Board of the European Statistical Advisory Committee (ESAC). Since 2017, he has led Utrecht's Applied Data Science focus area, focusing on human-centered AI and data-driven solutions. His research emphasizes population size estimation, fraud detection, and categorical data analysis, with applications for Dutch ministries and international bodies like the UN. He has pioneered methods for estimating human trafficking victims and optimizing healthcare treatments using multilevel models and neural networks. Key projects include the AI for Health initiative with Utrecht Medical Center and Wageningen University. His work bridges statistical rigor with societal impact, addressing challenges in criminal justice, public health, and policy-making through innovative methodologies. Universities: Utrecht University (Primary), University of Southampton Key Committees: European Statistical Advisory Committee, UN Human Trafficking Monitoring Research Themes: Multiple Systems Estimation, Data Science for Social Issues Research interests span statistical methods for complex societal problems, including: Register linkage and fraud detection Machine learning applications in healthcare Human trafficking prevalence estimation His publications (2019-2023) highlight advancements in multilevel modeling, randomized response techniques, and AI-driven clinical data classification. He has advised on policy frameworks for official statistics and contributed to global initiatives like the UN Sustainable Development Goals (Target 16.2). Grants and collaborations include projects with Dutch ministries, the EU, and international organizations. Current initiatives involve optimizing Hepatitis C treatment networks and improving criminal recidivism prediction models. His leadership in interdisciplinary teams ensures methodological innovation addresses real-world challenges.

• Categorical Data Analysis
• Data Science
• Multivariate Statistics
• +3 more

Matthias Bannert is a Lecturer at the Department of Management, Technology, and Economics at ETH Zürich, where he works at the KOF Swiss Economic Institute (Konjunkturforschungsstelle). His work focuses on the intersection of economics, software development, and data management, with particular expertise in time series analysis and official statistics. Bannert designs solutions for state-of-the-art data processing, management, and publishing of economic data and research. Bannert completed his doctoral thesis titled "Survey Based Research in Economics - Essays on Methodology, Economic Applications and Long Term Processing of Economic Survey Data" at ETH Zürich in 2016. His academic journey began when he joined KOF in late 2008, initially working as a researcher for the Business Tendency Survey group before transitioning to the institute's IT department. Dr. Bannert's research interests span several interconnected domains at the nexus of economics and data science. He specializes in developing software environments for official statistics, with particular focus on processing and managing economic time series data through open-source driven data pipelines. His technical expertise includes R programming and PostgreSQL database systems, which he applies to create robust solutions for economic data analysis. Bannert is particularly interested in survey methodology, nowcasting techniques, and the development of reproducible research workflows. His work bridges the gap between theoretical economics and practical software implementation, ensuring that economic research can leverage state-of-the-art data processing techniques. Analysis of Bannert's publication record reveals a consistent focus on the application of data science techniques to economic research problems, particularly in the domain of official statistics and survey-based economics. His work demonstrates a progression from theoretical survey methodology to practical software implementation, with increasing emphasis on real-time economic forecasting and data management systems. A distinctive feature of his research is the development of open-source R packages that make advanced economic data analysis more accessible to researchers and practitioners. As an active contributor to the R language for Statistical computing and the open source community, Bannert has developed several notable software packages including timeseriesdb, tstools, and kofdata, which are available on CRAN. These tools reflect his commitment to creating reproducible, transparent, and efficient workflows for economic data analysis. Bannert serves as a data science supervisor for multiple KOF research projects and is a co-Principal Investigator in an SNF-funded Digital Lives project in collaboration with KOF's labor market expert group. His teaching activities include "Hacking for Sciences - An Applied Guide to Programming with Data" and involvement in the Nowcasting Lab, which provides live out-of-sample forecasting and model testing capabilities for economic researchers. Dr. Bannert is affiliated with the KOF Swiss Economic Institute, where he contributes to several research groups including the KOF Macroeconomic Forecasting group and the KOF Data Science and Macroeconomic Methods group. His work at KOF bridges the institute's traditional economic research with modern data science approaches, helping to position the institute at the forefront of data-driven economic analysis.

• Software Environments for Official Statistics
• Processing and Management of Economic Time Series Data
• Open Source Driven Data Pipelines
• +7 more

Pedro Duarte Silva is an Associate Professor at Católica Porto Business School, Universidade Católica Portuguesa. His research focuses on statistical methods for distributional and interval data, developing parametric models and classification techniques. Recent work includes developing the MAINT.Data R package for interval data analysis and investigating outlier detection methodologies. As part of the Research Center in Management and Economics (CEGE), he contributes to methodological advances in data analysis with applications to management science. Current projects examine optimization approaches for classification problems and symbolic data analysis for official statistics.

• Statistical Modeling
• Discriminant Analysis
• Interval Data Analysis
• +1 more

Jan van den Brakel is an Extraordinary Professor of Survey Methodology at Maastricht University and a Senior Statistician at Statistics Netherlands. He holds a position in the Department of Quantitative Economics within the School of Business and Economics. His primary affiliation is with the methodology department at Statistics Netherlands, where he focuses on advancing statistical methods for official statistics. **Research Interests:** Professor van den Brakel specializes in survey methodology, with a focus on mixed-mode surveys, time series modeling, small area estimation, and discontinuity analysis. He explores topics such as sampling techniques, variance estimation, and the integration of non-probability data sources (e.g., social media) into official statistics. His work addresses challenges in labor force surveys, health surveys, and the impact of technological changes like tablet-based data collection. **Key Projects:** Current projects include mixed-frequency time series modeling for short-term statistics, accuracy assessments of non-probability web panels, and modeling discontinuities in official surveys. He has contributed to high-impact studies, such as analyzing mobility patterns during the pandemic and improving unemployment rate estimation using Bayesian models. **Awards:** His 2013 paper on factorial designs in probability samples was honored as the best journal paper by Survey Methodology in 2014. He is a member of the Advisory Committee on Statistical Methods at Statistics Canada, reflecting his international leadership in statistical methodology. **Professional Roles:** In addition to his academic role, he collaborates extensively with national statistical offices, advising on methodological challenges. His work bridges theory and practice, ensuring statistical methods are robust and applicable to real-world data collection and analysis.

• Survey Methodology
• Statistical Analysis
• Time Series Modeling
• +7 more

Krish Muralidhar is the Baldwin Chair and Professor of Marketing & Supply Chain Management at the University of Oklahoma's Price College of Business. He holds a Ph.D. from Texas A&M University, an MBA from Sam Houston State University, and a B.Sc. from the University of Madras, India. His research centers on data privacy , developing techniques for secure data analysis, sharing, and dissemination. Key areas include statistical disclosure limitation, differential privacy, database reconstruction risks, and perturbation methods. He patented the Data Shuffling technique for secure data release. Recent publications (2022–2025) focus on census data privacy, reidentification vulnerabilities, and critiques of differential privacy in machine learning. Trends highlight rigorous evaluations of privacy risks in statistical databases and policy-relevant solutions. Awards: Distinguished Doctoral Alumni Award (Texas A&M, 2006) Teaching Incentive Program Award (1994) Excellence in Research Award (1995) Best Inter-disciplinary Paper Award (2002) Best Paper Award (2005) No advising, grant, lab, or team details were provided.

• Data Privacy
• Statistical Disclosure Limitation
• Database Security
• +3 more

Associate Professor Wayne Wobcke is a faculty member in the School of Computer Science and Engineering at the University of New South Wales (UNSW), where he has been employed since 2002. His academic career includes previous positions at the University of Sydney until 1998, British Telecom Labs in the UK for three years, and the University of Melbourne for one year. He holds a PhD in Computer Science from the University of Essex (1989), an MSc from the University of Queensland (1985), and a BSc (Hons) in Mathematics/Computer Science from the University of Queensland (1984). Dr. Wobcke's research spans both theoretical and practical aspects of artificial intelligence and data science. His work encompasses intelligent agents, data mining, agent-based modeling, dialogue management, personal assistants, recommender systems, and computational social science. He has collaborated extensively with industry through three Cooperative Research Centres (Smart Internet Technology CRC, Smart Services CRC, and Data to Decisions CRC), where he served as a Programme Manager and Project Leader for over 10 years. Notable achievements include developing a voice-controlled mobile application for email and calendar interaction (a precursor to Apple's Siri) and deploying a people-to-people recommender system for online dating on one of Australia's largest dating sites. His recent research focuses on data science in humanitarian contexts and machine learning applications in official statistics, conducted in collaboration with BPS (Statistics Indonesia) and STIS (Politeknik Statistika, Indonesia). His publication record shows a consistent trajectory of impactful research, with recent work concentrating on poverty targeting, domain adaptation, natural language processing for recommender systems, and political opinion mining. Scientific Awards: Best Paper Nomination, 11th Workshop on Argument Mining (2024) UNSW Arc Postgraduate Research Supervisor Award (2017, 2018) AAAI Deployed AI Application Award, Twenty-Sixth Annual Conference on Innovative Applications of Artificial Intelligence (2014) Best application paper runner up, 17th Pacific-Asia Conference on Knowledge Discovery and Data Mining (2013) Dr. Wobcke has successfully supervised numerous research students, with Irwan Rahadi currently working on 'Causal Modelling and Machine Learning for Official Statistics'. His grant portfolio includes significant funding from the Australian Research Council and various Cooperative Research Centres, totaling over $3.7 million since 2003. He teaches COMP9414 Artificial Intelligence and COMP9727 Recommender Systems at UNSW.

• Artificial Intelligence
• Data Science
• Machine Learning
• +7 more

Dimitris Karlis is a Professor in the Department of Statistics at the Athens University of Economics and Business (AUEB), within the School of Information Sciences and Technology. He has been a key academic figure since earning his BSc and PhD in Statistics from AUEB in 1992 and 1999, respectively, and was promoted to Associate Professor in 2012 before advancing to full Professor. Education: BSc in Statistics, AUEB (1992) PhD in Applied Statistics, AUEB (1999) His research spans computational statistics, mixture models, EM algorithms, copulas, multivariate discrete data, and applications in sports, insurance, and seismicity. He has published extensively in top-tier statistical journals such as the Journal of the Royal Statistical Society and Statistics in Medicine . The 15 most recent publications reveal a strong focus on multivariate count data, integer-valued time series, model-based clustering using copulas, and applications in actuarial science and health. His work frequently involves mixture models, Bayesian inference, and innovative extensions of Poisson-based frameworks. Scientific Service and Recognition: Associate Editor: Metron, Communications in Statistics, IMA Journal of Management Mathematics, Stochastic Environmental Research and Risk Assessment Editor: Biometrics Bulletin of IBS Member: American Statistical Society, International Statistical Institute, International Association of Statistical Computing, Hellenic Statistical Institute Publicity Officer: Eastern Mediterranean Region, International Biometric Society Advising and Grants: He has supervised 4 completed PhDs and 18 Master’s theses, with several more in progress. He has led and participated in research projects funded by the European Union and EUROSTAT, particularly in official statistics. His advising spans methodological and applied topics in statistics. Labs and Teams: While no formal lab is named, he collaborates extensively with researchers in actuarial science, transportation, biostatistics, and environmental risk, often through joint projects and publications.

• Computational Statistics
• Mixture Models
• EM Algorithm
• +12 more

Dan Hedlin is a Professor of Statistics at Stockholm University's Department of Statistics, specializing in official statistics production. He holds a PhD in Statistics from the University of Southampton (2003) and maintains an office at Room A4625, Albanovägen 12, Building 4, floor 6. His contact information includes email dan.hedlin@stat.su.se and phone +46 8 16 2975. Hedlin's primary research focuses on survey methodology and official statistics, with expertise in sampling design and estimation, nonresponse issues, analysis of survey data, statistical editing, response burden, reporting delays, experiments embedded in surveys, cut-off sample designs, and opinion polls. His work bridges theoretical statistical methods with practical applications in government and public policy contexts. His publications and media contributions demonstrate a strong emphasis on statistical literacy and proper interpretation of survey data, particularly regarding opinion polls. Hedlin frequently engages with the public through Swedish media, addressing common misinterpretations of statistical data and promoting better understanding of survey methodology among journalists and the general public. Hedlin serves on the Scientific Councils of both the Swedish National Council for Crime Prevention and Transport Analysis, applying his statistical expertise to inform policy decisions. His teaching portfolio includes advanced courses in Machine Learning, Statistics and Data Analysis III, and supervising independent student work.

• Survey methodology
• Official statistics
• Sampling design
• +9 more