About

Dean Abbott

Introduction

Dean Abbott is President of Abbott Analytics andcurrently is the Bodily Bicentennial Professor in Analytics at UVA DardenSchool of Business. He is an internationally recognized thought leader and innovatorin data science and predictive analytics with more than three decades ofexperience solving problems in customer analytics, fraud detection, riskmodeling, text mining, survey analysis and is frequently included in lists of thetop pioneering and influential data scientists in the world. He formerly co-founded and was Chief Data Scientist of SmarterHQ.

Mr. Abbott is the author of Applied Predictive Analytics (Wiley, 2014, 2^nd Edition forthcoming) and coauthor of The IBM SPSS Modeler Cookbook (Packt Publishing,2013). He is a popular keynote speaker and bootcamp/workshop instructor at conferences worldwide and serves on advisory boards for the UC/Irvine Predictive Analytics and UC/San Diego Data Science Certificate programs. Mr.Abbott holds a bachelor’s degree in computational mathematics from Rensselaer Polytechnic Institute and a master’s degree in applied mathematics from the University of Virginia.

Professional Experience

March 1999 to Present

Abbott Analytics

Abbott Analytics leads organizations through the process of applying and integrating leading-edge data mining and machine learning methods to marketing, research and business endeavors. Abbott Analytics has been dedicated to improving efficiency, ROI, and regulatory compliance through machine learning.

Abbott Analytics also provides bootcamp, training, mentoring and advisory services in machine learning and data science.

May 2023 – May 2024

Bodily Bicentennial Professor of Analytics
University of Virginia, Darden School of Business

In 2022, Darden initiated the Bodily Bicentennial Professorship in Analytics to advance faculty research in the field. The position was created in honor of the contributions of Sam Bodily, the John Tyler Professor Emeritus of Business Administration to the field of decision analysis. Each year, this visiting professor will offer new insights and possibilities for collaboration with Darden faculty and students.In 2022, Darden initiated the Bodily Bicentennial Professorship in Analytics to advance faculty research in the field. The position was created in honor of the contributions of Sam Bodily, the John Tyler Professor Emeritus of Business Administration to the field of decision analysis. Each year, this visiting professor will offer new insights and possibilities for collaboration with Darden faculty and students.

2020 - 2023

Chief Data Scientist, Wunderkind

Wunderkind and SmarterHQ merge in November 2020. Remain Chief Data Scientist.

2009 - 2020

Chief Data Scientist, SmarterHQ

Actual start date was mid-2009, but I went from part-time involvement to full-time involvement on April 1, 2014.

Co-Founded SmarterHQ, bringing analytics and machine learning to retail email marketing in a SaaS context. Designed and built process to automate building of models for 100+ clients, rebuilding models as needed, either daily, weekly, or monthly. Analytics backend instrumental in obtaining the first $7M round of venture funding and future rounds.
Served as CTO of SmarterHQ for 3 years, hiring and managing the Software Development, DevOps, and Data Science teams (more than 20). Succeeded in migrating the entire backend infrastructure from SQL Server + MongoDB to Redshift + S3 + AWS microservices

1996 – 1999

Senior Research Scientist, Elder Research

Data mining consulting; financial services portfolio optimization. During this time, co-presented with John Elder KDD-98 workshop on data mining software tools; remains largest workshop attendance in KDD history.

1994 – 1996

Senior Member Technical Staff, PAR Government Systems Corp.

Data mining and pattern recognition in signal and image processing (ASW, radar, flourescence imaging); Development of software for commercial data mining software; Optical sensor simulation and testing.

1991 – 1994

Algorithm Designer, Martin Marietta Corp.

Built neural networks and polynomial neural networks for postal bar code reader, optical character recognition, image identification.

Radar cross-section analysis and classification (tanks, trucks, aircraft) using neural networks, including X-band, K-band, etc. Building neural networks and polynomial neural networks for postal bar code reader, optical character recognition, image identification. Radar cross-section analysis and classification (tanks, trucks, aircraft) using neural networks, including X-band, K-band, etc.

1987-1991

Research Scientist, Barron Associates, Inc.

Development of "Optimum Path-to-Go" guidance laws for missiles and glide bombs(combining polynomial neural networks with variational calculus optimum solutions)

Development of 3DOF and 6DOF simulations for guidance and control.

Development of classification models for passive ASW using polynomial neural networks

AWARD WINNING PROFESSIONAL

Advisory Boards

University of California Irvine Data Science Certificate Program

University of California Irvine Predictive Analytics Certificate Program

University of California Irvine Data Analytics for Business Certificate Program

University of California San Diego Data Mining for Advanced Analytics Certificate Program

CompEdge™ company: Pay Transparency in Real Time

2012 KDD Conference Industrial Track Program Committee

2014 KDD Conference Industrial Track Program Committee

Consulted for top companies

Partners

Clients

Partner: Seer Analytics; Survey analysis, likelihood to renew, recommend to a friend, satisfaction

Department of Treasury: IRS (LMSB, now LB&I)

Partner: The Modeling Agency;

Noncompliance for large corporate tax returns: S-Corps (F1120S), Partnerships (F1065), C-Corps

Center for SEAL and SWCC (Navy Special Warfare Command)

Partner: Elder Research and IBM; Predict candidates who will continue Phase I training through Hell Week; Optimize candidate selection for Chief Petty Officer review.

Partner: The Modeling Agency; Ensemble modeling for upsell modeling, subscription modeling

Parter: Elite Analytics; Predict tax owed by non-filer, age and recovery potential of tax debt

Partner: Intelligent Automation Corporation; Predict LD50 toxicity likelihood for compounds based on chemical structure.

Partner: Orincon; Predict likelihood of future severe failure of engines

Partner: Elder Research; Identify invoices likely to be suspicious/improper; Identify government credit card misuse

Partner: Elder Research; “Optimal IT”; model IT support bottlenecks and optimize prioritization of tickets

Partner: The Modeling Agency; Likelihood to respond to contact; customer segmentation

Cross-sell and churn modeling; data scientist hiring process/test

Partner: The Modeling Agency; Medicare customer acquisition.

Partner: The Modeling Agency; Predict new subscriptions, renewed subscriptions; subscription forecasting

Partner: Elite Analytics; Predict age and recovery potential of tax debt

Partner: The Modeling Agency; On-time likelihood models

Partner: The Modeling Agency; Metadata analysis to determine if Ragweed is resistant to Roundup (presented at Southern Weed Society conference)

Abbott Insights

Get Insights to Case Studies, Resources, and Latest Blogs

Case Study

November 28, 2023

Large, National Health Club

A national fitness club created a survey to assess and understand how well it was meeting its core objectives by satisfying the desires and

Insight

November 26, 2023

What if Generative AI turns out to be a dud?

"Everybody in industry would probably like you to believe that AGI is imminent. It stokes their narrative of inevitability, and it drives

Case Study

November 26, 2023

Invoice Fraud Detection

The Defense Finance and Accounting Service (DFAS) is responsible for disbursing nearly all of the Department of Defense (DoD) funds.

Get more insights