Theorem uses Data Science to invest in the best Marketplace Lending loans

LOCATION San Francisco, CA

COMPANY SIZE Between 5 and 10

# OF ENGINEERS Less than 5




TAGS Big Data, Finance, Machine Learning, YC Winter 2014

What do we do?

We are a cross-disciplinary team applying machine learning and rigorous scientific investigation to revamp the lending and securitization space. This is one of finance’s least sexy areas, but is a multi-trillion dollar market- and it’s where the financial crisis started. Bad technology was a major cause, and even after almost 10 years, no one has fixed it.

Why join us?

1) We are a full-stack startup, not just another vendor; we make tools so that we can use them.
2) We have capital commitments of over $100mn dollars from a set of institutions and individuals.
3) Current team brings together experience from Google and Morgan Stanley

Technical challenges

1) Begin rigorous about investigations - we need to prove our hypothesis actually work rather than just getting a p-value of 0.5
2) We’re not just applying algorithms from existing libraries, we want a machine learning savant who can understand our business problems and contribute to our analysis on a deeper level.
3) We use feature engineering and mine external data to help boost model performance
4) We value correctness, maintainability, elegance, and testability of code
5) Experience in writing fast, performant code (especially numerical code) is a big plus

Our Founders

Abeer Agrawal


Hugh Edmundson


Our tech stack

  • Pandas
  • Scikit Learn
  • Python
  • Statistics
  • Fast Code
  • Numpy
  • Data Science
  • C++
  • Machine Learning

Our investors

  • SV Angel
  • Max Levchin
  • Two Sigma
  • Data Collective