Data Science + Learning Science
Providing you with the most meaningful insights about your learning context requires more than just data science. Our Learning Team understands which signals to measure and how to interpret them, allowing ALP to provide optimal results with lower requirements for data and computational resources.

ALP combines cutting-edge machine-learning technology with the training and expert vision of world-class learning scientists to produce richer, more varied, and more accurate insights.
ALP's learning-relevant capabilities include:
Skill Measurement
Understanding which skills each activity supports is critical for evaluating learner progress. Drawing upon our extensive experience developing and analyzing learning contexts that range from games to test preparation, we designed ALP to handle complex skill mapping and fine-grained measurement.
Behavior Identification
Insight into specific learner behaviors offers a richer picture than just scores alone. We have developed models for identifying behaviors such as guessing, re-checking work, working too quickly or too slowly, and more. ALP uses these models to provide insights about trends, changes in behavior, and comparisons with other learners.
Performance Prediction
We have developed highly accurate predictive models based on learner and peer performance on individual items to provide information such as the learner's next score, the expected difficulty of certain items for the learner, and estimates of working speed.
Recommendations
ALP's content recommendation models go beyond typical demographic and ratings-based information to include learning-relevant factors such as the learner's and population's skills, interests, and curricular focus.
Meet Our Learning Scientists
"We built ALP because we believe that personalized learning should start with a holistic picture of the learner. ALP's most basic goal is to help parents, teachers, tutors, and creators of educational products understand each learner deeply enough to effectively support that learner's progress."
Dylan Arena, Ph.D.
Co-Founder & Chief Learning Scientist
Learn More About Dylan
"Helping partners make the most meaningful use of their learning data and see new opportunities to support learners and those who care about their development is exciting, challenging, and deeply rewarding."
David Hatfield, Ph.D.
Director of Assessment & Product
Learn More About David
"As education moves online and large quantities of educational data become available, we work on the frontier of knowledge in the fields of psychometrics and educational data science to develop models that go beyond prediction of outcomes and give meaningful insights to support learners in their online educational journey."
Josine Verhagen, Ph.D.
Director of Psychometrics
Learn More About Josine
"I believe that nature is the best teacher, and what we learn from nature comes through both what we can see and what we cannot see. We have discovered so much that we had not known before, yet there is more to be found by those who are asking the right questions."
Young Park, Ph.D.
Senior Psychometrician
Learn More About Young
"In today's educational landscape, we can collect large amounts of data as learners interact with educational products. With intelligent models we can adapt to each learner and reach the whole spectrum of learners. We can help level the playing field and bring learning excellence within reach of all learners."
Uma Vijh, Ph.D.
Data Scientist
Learn More About Uma
"True learning involves both studying and thinking. The learner profile built by ALP tells if a learner has studied, thought, and a lot more."
Ji An
Data Scientist
Learn More About Ji
Dylan Arena, Ph.D.
Co-Founder & Chief Learning Scientist
Dylan is a learning scientist with a background in cognitive science, philosophy, and statistics. He has studied, presented, and written extensively about game-based learning and next-generation assessment. Dylan started out as a software developer at Oracle, but after a few years he returned to graduate school at Stanford, where he spent several years as a MacArthur Emerging Scholar in Digital Media and Learning. Dylan has also been a Gordon Commission Science and Technology Fellow, a Stanford Graduate Fellow in Science and Engineering, a Gerald J. Lieberman Fellow, a FrameWorks Fellow, and a United States Presidential Scholar. Dylan has earned a bachelor's degree in Symbolic Systems, a master's in Philosophy and a master's in Statistics, and a Ph.D. in Learning Sciences and Technology Design (in the program for Developmental and Psychological Sciences), all from Stanford University. Dylan has two sons, ages 9 and 5.
David Hatfield, Ph.D.
Director of Assessment & Product
David is a learning scientist with a background in science education, video game design, and assessment. His Ph.D. research focused on developing and testing innovative performance-based assessment models for measuring complex thinking and designing simulated professional practicum experiences for young people. Prior to joining Kidaptive, David was a research scientist with the Epistemic Games research lab and the Games, Learning and Society center, both at the University of Wisconsin. David also has a bachelor's degree in Biology from Virginia Tech, and studied English Literature at North Carolina State University. David has a son and daughter, ages 10 and 8.
Josine Verhagen, Ph.D.
Director of Psychometrics
Josine is a psychometrician with a background in Bayesian statistics, educational testing, and psychology. She has studied the application of Bayesian statistics to cross-national and longitudinal comparisons of tests and questionnaires, hypothesis testing and adaptive educational tests. Josine graduated from Leiden University in the Netherlands with Msc.'s in both Social Psychology and Methodology and Statistics. She started working on non-response in surveys at the Netherlands Institute for Social Research (SCP). After 2 years, she moved on to obtain a PhD. in psychometrics at the University of Twente, conducting research on Bayesian psychometrics with Jean Paul Fox and Cees Glas. Josine did postdoctoral research on Bayesian hypothesis testing and adaptive educational tests at the University of Amsterdam, where she was subsequently hired as an Assistant Professor of Psychological Methods before joining Kidaptive.
Young Park, Ph.D.
Senior Psychometrician
Young (영선) Park is a psychometrician with a background in Item Response Theory (IRT), Computerized Adaptive Testing (CAT), and mathematics/statistics education in K-12. Young earned his bachelor's and master's degrees in electrical engineering from Hanyang University in Seoul, South Korea and the University of Texas at Austin, respectively. Upon graduation, he worked as a microprocessor designer for Motorola/Freescale in Austin for nine years before returning to the University of Texas at Austin for a Ph.D. in educational psychology. Prior to joining Kidaptive, Young taught intermediate and advanced psychometrics/statistics courses as an assistant professor at Wayne State University in Michigan. In his free time, he loves to spend time in nature with his son, age 6.
Uma Vijh, Ph.D.
Data Scientist
Uma is a data scientist with a background in astrophysics. She has led several NSF/NASA projects and published extensively about the nature of interstellar dust. She has a bachelor's in Physics from St. Xavier's College in Bombay and a master's in Physics from the Indian Institute of Technology in Bombay (IITB). Uma worked briefly at Infoysys Technologies before earning another master's and a Ph.D. in Physics from the University of Toledo in Ohio. Uma's doctoral work explored photoluminescence from interstellar dust. After a post-doctoral stint at the Space Telescope Science Institute in Baltimore, she returned to the University of Toledo as a Research Professor. Before joining Kidaptive, Uma worked as a Data Scientist for California's Department of Justice, analyzing juvenile data to help guide juvenile justice reform. Uma has a daughter and a son, ages 8 and 2.
Ji An
Data Scientist
Ji is a data scientist with a pending Ph.D. in Measurement, Statistics, and Evaluation from University of Maryland (expected conferral autumn 2018). Ji's background is in teaching: She earned a bachelor's degree in Teaching Chinese as a Second Language from Nanjing University in China and a master's degree in Teaching & Curriculum from Michigan State University, and she taught in a public school in Michigan for two years. Ji's research at the University of Maryland addressed education, social sciences, and public health. Her work included analyzing large-scale data with complex sampling structures; implementing experiments and making causal inferences from experimental/quasi-experimental designs; deriving actionable insights; and presenting her findings in a storytelling style. Ji has a daughter, age 7 months.