DR. KOBI ABAYOMI

Statistician, Probabilist, Professor


CURRICULUM VITAE

SHU Page


Biography

Dr. Kobi Abayomi is a professional statistician with widely cited publications in top journals for methodological and applied research work. His specialty in developing models from first principles - tailored particularly to each research or business application - has yielded measurable lift in business impact and results, documented by his wide publication record.

His methodological work is on statistical dependency:

  • Machine Learning algorithms
  • Constrained sum measures
  • Non-Gaussian data
  • Multivariate dimension reduction

He has completed and published innovative work for clients such as the World Bank, United Nations, the Government of Ecuador, and the Innocence Project. He has over 15 years of experience discovering, consulting, publishing, and teaching Probability and Statistics with a focus on measures of dependency, environmental sustainability, social networks, social inequality and justice.

Dr. Abayomi is the Head of Science for Gumbel Demand Acceleration - a Software as a Service (SaaS) company for digital media. Dr. Abayomi was the first and founding SVP of Data Science at Warner Music Group (WMG). He has also served as a Professor of Industrial Engineering, Probability, and Statistics & Environmental Science at Georgia Tech, Universidad de Cuenca, and Binghamton University. He holds a Ph.D. in Probability and Statistics from Columbia University and Post-Doctorates from Duke and Stanford Universities. 

Dr. Abayomi serves on the Data Science Advisory Council at Seton Hall University, where he holds an appointment in the Mathematics & Computer Science Department. He serves on the Advisory Council at the Ivan Allen College at the Georgia Institute of Technology, the Faculty Council at Barnes & Noble Education, the advisory council for Modal Education, and he is a chapter advisor for AI 2030.

Papers

  1. Modeling and Optimization for Streaming Listening Demand

  2. Open Set Recognition For Music Genre Classification

  3. The Design, Data Flow Architecture, and Method- ologies for a Newly Researched Comprehensive Hybrid Model for the Detection of DDoS Attacks on Cloud Computing Environment

  4. Using Conditional Lorenz Curves to Examine Consolidation in New Zealand Commercial Fishing

  5. Probabilistic 'Best Set' Sorting Algorithms for Multivariate (Prognostic) Data

  6. On Inequality

  7. Copula Based Multistate Hazard Model: An Inferential Methodology for Innocence Project

  8. Statistical Evaluation of the Effect of Ethanol in US Corn Production: A Flexible Test for Independence on a Constrained Sum

  9. Statistics for Re-identification in Network Models

  10. Quantifying Sustainability: Methodology for and Determinants of an Environmental Sustainability Index

  11. Monitoring the United Nations Millennium Development Goals: A Straighforward (Bayesian) Methodology for a Cross-National Index

  12. Statistics for Re-identification in Social Networks

  13. Bayesian Multivariate Markov Processes for a Network Flow Optimization Problem

  14. Probabilistic Heuristic Search Using (Multivariate) Order Statistics. Illustrated On A Network Flow Problem In Two Dimensions

  15. A Friendly Amendment of the Theil Index and Consequent Test for Across and Within Theil Inequality

  16. Monitoring Human Development Goals: A Straightforward (Bayesian) Methodology for Cross-National Indices

  17. Statistical Evaluation of Biofuel Role in Land Use Change

  18. Relationships among blood pressure, triglycerides and verbal learning in African Americans

  19. Diagnostics for multivariate imputations

  20. Copula based independent component analysis

  21. El Niño and drought in southern Africa

  22. Statistical Evaluation of Effect of Bioenergy on Crops and Land Use

  23. Quantifying Sustainability: Methodology for and Determinants of an Environmental Sustainability Index

Slides

  1. What is [sic] Data? Columbia University Student Seminar, (October 2020)

  2. Ranking using Multivariate Prognostic Data, (2014)

  3. Statistical Issues for Re-Identification in Network Data

  4. Multivariate Extreme Value Thresholding (for Environmental Hazards), (2012)

  5. Statistical Methdology For Innocence Project Data ASC, (November 2012)

  6. Statistical Approaches for Constrained/Limited Sums:Environmental Economics, (January 2012)

  7. Social Determinants of Health Disparities, (August 2011)

  8. Statistics on Innocence Project Data JSM, (August 2011)

  9. Bayesian Multivariate Extreme Value Thresholding for
    Environmental Hazards
    , (2010)

  10. A Friendly Amendment of the Theil Index, (November 2010)

  11. A Friendly Amendment of the Theil Index, (March 2010)

  12. Copulas for Tunable Markov Processes, (January 2010)

  13. A Friendly Amendment of the Theil Index, (October 2009)

  14. Dependency/Competition in Corn Yield: A Proxy for Land Use Change, (October 2009)

  15. Copula Based Independent Component Analysis, (October 2008)

  16. CAARMS Talk, (July 2008)

  17. Copula Based Independent Component Analysis, (April 2008)

  18. Joe, Harry. Multivariate Models and Dependence Concepts, (2007-2008)

  19. Thresholding MEVD-Multiple Environmental Hazard, (2007-2008)

  20. Expedient Methods in Environmental Indexing
    2002 ESI, 2004 UNDP Hotspots Report
    , (October 2004)

Projects

  • Predicting the UNDP Millennium Development Goals, (October 2014)

  • Xenia

    Xenia's YouTube