Data and Predictive Analytics Center


"Big data" and the ability to discover patterns and make predictions from large amounts of data is revolutionizing almost every other scientific and technical field. The Data and Predictive Analytics Center (DPAC) creates and applies new, cutting-edge techniques to collect, transform, model, and visualize data. Analysis techniques are drawn from mathematics and statistics, computer and information science, machine learning, and several other areas. DPAC provides instruction, training sessions and internships for students and those already in the workforce, and supports the Data Analytics and Simulation of Complex Systems application domain of RIT's Ph.D. in Mathematical Modeling. Additionally, DPAC encourages and assists new ventures and innovation in Data and Predictive Analytics.

Research and Consulting

Eric Hittinger, Assistant Professor
Dr. Eric Hittinger studies the operation, economics, and policy of electricity systems, focusing particularly on the adoption on emerging technologies, like wind, solar, and energy storage.

Eric Williams, Associate Professor
Dr. Eric Williams is a researcher and educator specializing in how to assess and use technology for sustainability. Dr. Williams has studied technologies like include renewable energy (photovoltaic, wind), fuel cells, mobility (alternative fuels, electric vehicles), information technology (hardware production, electronic waste, telecommuting, smart grids - electric and water) and the methods he has used include Life Cycle Assessment (LCA), material flow analysis (MFA), risk analysis, benefit-cost analysis, experience curve modeling, and fuzzy logic decision simulation.

Joseph Voelkel, Professor
Dr. Joseph Voelkel’s research topics include experimental design, Reliability, Multivariate Analysis, Non-standard industrial problems.

Anthony Harkin, Associate Professor
Dr. Anthony Harkins works to create real-time, interactive visualizations of a variety of government data sets at the federal, state and local levels so that everyone can become more informed on civic issues and policies that matter to them. The challenge he is addressing is how to make vast amounts of open government data visually interesting and understandable by everyone. Doing this requires applying techniques of advanced visualization, data mining, machine learning, social network theory and much more. 

Linlin Chen, Associate Professor
Dr. Linlin Chen’s research focuses in biostatistics and big data analytics. She conducts research in statistical analyses in high-dimensional data, genetic data, cancer-related data, and other medical data. Her research interests also include machine learning, computational statistics, microarray gene expression data analysis, survival analysis, and related topics in data science.

Nathan D. Cahill, Associate Professor
Dr. Nathan Cahill's areas of research include medical image analysis and computer vision.

Elizabeth M. Cherry, Associate Professor
Dr. Elizabeth Cherry’s research focuses on Mathematical Biology, Nonlinear Dynamics, Cardiac Electrophysiology, Mathematical Modeling, Scientific Computing and Bioinformatics. 

Bernadette Lanciaux, Lecturer
Bernadette Lanciaux’s work focuses on Curriculum Development for Statistics and Data Science for the General Curriculum. Introductory Statistics is the only class on data that most students take and as such, needs to prepare them to understand the data they will encounter in the real world. The developments in data acquisition, storage and analysis fundamentally need to fundamentally change the teaching of introductory statistics. It is no longer enough to teach students the fundamentals of inferential statistics. Modern courses need to contextualize traditional introduction to statistics in the appropriate historical context in addition to some of the new tools that have been developed for deriving meaning from the masses of data.

We need to introduce data science concepts at the introductory level and teach today’s students to do Exploratory Data Analysis on real data (including Big Data) from a wide variety of sources using modern statistical methods and modern statistical software. Her work focus on developing teaching and learning modules to make this a reality.

Carol Marchetti, Professor

Ernest Fokoué, Associate Professor

Dr. Ernest Fokoué focuses on Statistical Machine Learning, Bayesian Statistics, Computational Statistics, and Statistical Data Mining research.

Matthew Hoffman, Associate Professor
Dr. Matthew Hoffman is the Data Analyst for the RIT Men’s Ice Hockey Team and the organizer for RIT Hockey Analytics Conference. His research areas also include oceanic and atmospheric dynamics, data assimilation, remote sensing, vehicle tracking, and cardiac electrical dynamics.

Peter Bajorski, Professor
Dr. Peter Bajorski has taught undergraduate and graduate courses in fundamentals of probability and statistics, multivariate analysis, regression analysis, and experimental design. He has also developed and taught a specialized course on multivariate statistics for imaging science. His research areas include imaging science, network communication, biomedical applications and high-dimensional data.

John Klofas, Professor
Dr. John M. Klofas, Ph.D., is Professor of Criminal Justice, and Founder and Director of the Center for Public Safety Initiatives (CPSI) at RIT. He is also the past chairperson of the Department of Criminal Justice. Dr. Klofas has taught a wide range of undergraduate and graduate courses. His current areas of focus include community level crime and justice issues including violence, management in criminal justice and strategies and practices in policing. He has received external funding and published widely in these areas.

His most recent book collaboration is an examination of changes in criminal justice at the community level entitled, “The New Criminal Justice.” Professor Klofas continues to serve as a research partner with local criminal justice agencies, on the State’s police training commission and on several national projects addressing community violence. He also works with several police departments across the country on issues of risk management as part of reform focused consent decrees in the Federal Courts.

John McCluskey, Professor
Dr. John McCluskey is the chairperson of the Department of Criminal Justice. He earned his BA, MA, and PhD from the University at Albany. His primary teaching areas include Criminal Justice Theory and Criminal Justice and Public Policy. His most recent research has included the study of body camera adoption in two divisions of LAPD with Justice and Security Strategies as well as a large-scale data collection effort to measure prevalence, causes, and consequences of teacher victimization in San Antonio, Texas with Dr. Byongook Moon.

Richard O’Shaughnessey, Assistant Professor

John Whelan, Associate Professor

Robert Parody, Associate Professor
Dr. Robert Parody’s research focuses on Experimental Design Response, Surface Methods, Mixture Experiments simulation, Quality Control and Improvement. 

Mihail Barbosu, Professor
Dr. Mihail Barbosu heads DPAC and is the primary advisor for SPEX (Space Exploration) at RIT.

At DPAC, one of his projects involved using data science to monitor machine health and to predict machine health failure. The equipment health monitor records parameters like device vibrations, temperatures etc. and data analytic methods are used to analyze the raw data files, to determine alarm signatures and trend vibrations, to diagnose machine faults and to predict future machine failures.

At SPEX, one of the projects involves the collection of telemetry from their High-Altitude Balloon testing program. The solution to this problem is twofold; transmit the telemetry in real time to a ground station and analyze and store the data in real time. The scope of this project is concerned with the collection of telemetry data from a radio base station, and its subsequent transmission and display in real time.


  • Promote RIT as a leader in the Data and Predictive Analytics (DaPA) community
  • Respond to the enormous demand in industry for highly-trained data analysts by serving as a cross-campus multidisciplinary hub for faculty
  • Foster research, training, and funding opportunities
  • Advance basic and applied research in techniques for DaPA
  • Foster partnerships with other universities, government, and industry
  • Support the Data Analytics and Simulation of Complex Systems application domain of RIT's Ph.D. program in mathematical modeling
  • DPAC promotes cross-disciplinary and multidisciplinary projects that are supported with collaborations between our academic and research programs and our industrial partners.
  • DPAC draws faculty from more than one academic unit in the College of Science and other RIT colleges.
  • DPAC facilitates collaborations and access to DaPA resources, organize seminars, workshops, and other activities where DPAC members are able to share their expertise in various application areas involving comples data gathering and interpretation.
  • Gifts from corporate partners and RIT alumni will primarily be used for supporting DPAC projexts involving students and faculty, summer research experiences, capstone projects, internships, and attending conferences to present student and faculty projects.
  • The DPAC director provides support, coordination, management, and advocacy, and develops strategies aimed at creating, sustaining, and promoting RIT activities and initiatives pertaining to DaPA.
  • DPAC runs various focused labs. Each has a director or coordinator who, in collaboration with the DPAC director, manages the lab.

Affiliate Faculty

Peter Bajorski
Mihail Barbosu
Nathan Cahill
Linlin Chen
Associate Professor
Ernest Fokoue
Tony Harkin
Associate Professor
Matthew Hoffman
Carol Marchetti
Richard O'Shaughnessy
Associate Professor
Robert Parody
Associate Professor
John Whelan