Cofounder and Chief Data Scientist at Feature Labs.

Besides data science and machine learning, I’m into Zen Buddhism, pole vaulting, mobility, music, skiing, and generally making a fool of myself through art.


Feature Labs is a venture-backed startup enabling enterprises to conduct and productize data science without hiring additional data scientists. We automate and abstract away the complexities of the entire data science process so that business executives, domain experts, and software engineers can focus on solving business problems instead of optimizing complex algorithms or building large data processing systems.


My research at MIT focused on data science automation, and specifically, on automatically generated and solving meaningful prediction problems given arbitrary relational data. This work culminated in my master’s thesis as well as a paper in IEEE/ACM DSAA 2016 titled What would a data scientist ask? Automatically formulating and solving prediction problems.

Before working on automating prediction problem definitions, I built a system to augment human project managers of large scale software projects, requiring automated data transforms of extremely messy data, automated feature engineering, natural language processing of textual comments, and quick configurable selection of various prediction problems. Parts of this system are now in use at one of the largest software consulting firms in the world. Check out the source here

I also helped develop an end-to-end data science foundry for MOOCs that enabled a systematic way of going from raw data to predictive models. This work was published in IEEE/ACM DSAA 2015 (link).

More fun projects include an implementation of near-optimal online matrix-completion algorithms (which had previously only existed in math form), multiplexed robotic scheduling for liquid-handling robots, recipe modification using recurrent neural networks, and scene detection using a combination of convolutional and recurrent neural networks.

Current Projects and Experiments

Lil Neuron

Human-generated rap is so 20th century. Who’s to say Lil Neuron can’t be the illest rapper alive without being “alive”?

Lil Neuron is an AI rapper using recurrent neural networks. See Lil Neuron Takes His First Breaths for my first blog about it, and the source on Github. Please let me know if you want to contribute!

BSS For Fitness

I took a year-long break from calendar sales to focus on my master’s thesis, and the time seems right to rekindle the Ben Schreck Shits brand. My goals this time are twofold: 1) Branch out of calendar sales into one-off merchandise like mugs and t-shirts 2) Promote local fitness and other wellness-focused clubs through toilet art.

Intermittent Fasting

After hearing enough about this I decided it’s weird enough for me to try. The idea is to eat the same amount of food I would normally eat, but only for an 8 hour period every day, fasting the other 16 hours. Sort of following this guide I found after a quick Google search.

Predicting Body and Mental States

Attempting to predict how tired I’ll feel, how much energy I’ll have, how sick I’ll be, and the locations and times I do things using both passive phone and watch data as well as active recording of the food I eat both as it enters and exits my body and the way I feel throughout the day.

Past Projects and Experiments

Online Matrix Prediction


Scenic Recursion

Learning Musical Style

Ben Schreck Shits Calendars

Gesture-Controlled Drone

Hacking Hackathons


subscribe via RSS