Chief Data Scientist & Learning Engineer
Current
Gandhinagar, Gujarat, India
I lead the data science team at Playpower Labs. We are one of the most dynamic groups of educational data experts in the world, open to helping wonderful learning companies. We currently work with some of the biggest education organizations in the world.My team and I work with many different types of educational data. Examples include event data, assessment data, intelligent tutor data, user behavior data, web analytics data, license and entitlement data, roster data, eText data, item response data, time-series data, panel data, hierarchical data, skill and standard data, assignment data, knowledge structure data, school demographic data, reading passage data, student handwriting data (images), speech data, and more. We have developed expertise in analyzing and modeling these different types of data.For learning analytics, we primarily use data transformation and visualization to find useful insights from the data. Our focus is always on getting actionable pieces of information from the data. We also use various statistical models (regression, SEM, hierarchical models) and computational models to get more value out of the data. We know how to work with text data using NLP methods, we have computer vision capability to work with all types of image data, and our recent work also includes neural network speech models. Our special expertise is around Process Analysis of educational data, where we work to uncover hidden learning teaching processes in the data.Our work has won multiple awards. - We won #2 place in the international NAEP data mining challenge co-sponsored by ETS against 89 global teams in 2020 - Our research in Curriculum Analytics field won us the best-short-paper award at the Intelligent Tutoring Systems Conference in 2018We believe in doing research that directly impacts human problems, and we continue to do rigorous research that is practical and valuable.Google Scholar: https://scholar.google.com/citations?user=TIsCIPUAAAAJ&hl=en