Stefano Meschiari, Ph.D.

Product Data Scientist, Civitas Learning

I am a data scientist and software developer with a background in astrophysics. I work with a wide range of data, from predicting students’ future persistence at higher-education institutions, to understanding complicated time series that reveal the existence of new planetary systems with Bayesian modeling, to summarizing millions of game plays and behavior tracked within my game that went viral. I am proficient at machine learning, data analysis, data visualization, and development of data science applications and tools.

I love collaborating with product teams to integrate data science into their vision to test out new ideas and concepts. I am experienced at creating functional user interfaces for data science-driven prototypes, and working with cross-functional teams to evolve products and platform to the next level.


2016-present, Civitas Learning Product Data Scientist

  • Create and improve on prototype machine learning tools and pipelines to model student outcomes.
  • Prototype new product ideas and internal tooling that employ machine learning, novel summary statistics and visualizations.
  • Maintain and improve the custom modeling platform. Reduced training and scoring running time (and cloud costs) by half.
  • Independently developed end-to-end components for Data Science projects:
    • Machine learning models (linear models, random forest, gradient boosted trees, and custom classification techniques using R, Spark/Scala and JavaScript)
    • Back-end (Node.JS/Express, API calls to internal services, and offering new APIs and services for internal consumption)
    • Front-end (React, HighCharts and custom-built components and visualizations).

2012-2016, University of Texas at Austin W. J. McDonald Postdoctoral Fellow

  • Led the data analysis effort for the Lick-Carnegie science collaboration (~20 scientists across the United States). Analyzed time series data using my Markov-Chain Monte Carlo code, Systemic. Systemic has been used to discover more than 40 new planetary systems.
  • Wrote high-performance, parallelized codes to solve ordinary and partial differential equations modeling planet formation.

2014-2016, University of Texas at Austin SAVE/Point, Principal Investigator

  • Principal Investigator of SAVE/Point, a collaboration of astronomers and educators creating cutting-edge edtech games, apps, and interactive touch kiosks, running on the latest Web technologies.
  • Developed Super Planet Crash, an HTML5/JS game that was played more than 15 million times and was covered by The Verge, IO9, Huffington Post, and others.
  • Developed Systemic Live, an HTML5/JS web app that teaches students about the process of data analysis and scientific discovery. It is used in MOOC classes in Coursera, and classes at Caltech, UF, UT, MIT, SJSU, UD, Yale, Columbia, UCSC, SFSU, and others.

2010-2011, VN7 Dynamic LP; 2013-2014, EFFEX Capital Research Analyst/Contractor

  • Led the development of a sophisticated desktop application to monitor the real-time performance of strategies on high-frequency stock trading.

Technical Skills

  • Machine Learning: Classification, regression, feature engineering, propensity score matching, building ML pipelines.
  • Statistical Methods and Numerical Algorithms: Hypothesis testing, bootstrapping, Markov-Chain Monte Carlo, numerical optimization using local and global methods, numerical simulations, integration of differential equations, time series analysis.
  • Programming Languages:
    • R (including dplyr, tidyr, ggplot2, RMarkdown, caret, glmnet, xgboost, and the h2o ML platform)
    • JavaScript (both backend and frontend, including Express, React, HighCharts)
    • Scala (including Spark and SparkML)
    • Java
    • C and C++
    • SQL
    • Others: Lua, Matlab. Basic knowledge of Python, Fortran, Objective-C.


  • 2012 – Doctor of Philosophy (Astronomy & Astrophysics), University of California at Santa Cruz
  • 2006 – Master of Science (Astronomy, with highest honors), University of Bologna
  • 2004 – Bachelor of Science (Astronomy, with highest honors), University of Bologna

Publications, Academic Honors and Awards

  • Published 8 first-author publications on time series analysis, numerical optimization, and Monte-Carlo simulations (cited a total of 224 times); a total of 17 refereed papers.
  • 2014 – Meschiari, S. (PI), Ludwig, R., Green, J., Interactive Education Tools in the Public Square (Award: $2,800, for purchasing iPad Air tablets and wall mounts)
  • 2014 – Meschiari, S. (PI), Green, J., Ludwig, R., Bringing the Tools of Research Direct to the UT Class- room: Systemic, a Virtual Lab for Students (Award: $87,710)
  • 2010 – Award for Excellence in Teaching
  • 2008 – Whitford Prize for graduate academic performance
  • 2006 – Regents’ Fellow, University of California