Romain Mondon-Cancel

Data Scientist

Ubisoft – San Francisco

Developed a TensorFlow-based Recommender System model integrated in a game currently in production to personalize in-game content based on user behavior.

Designed, built, and deployed a back-end infrastructure on GCP to expose an API able to train our models and return predictions.

Co-designed the in-game tracked events to feed our Hadoop-based database.

Designed, trained, deployed and tested a logistic regression model based on player gaming data to improve CRM targeting by up to 5%.

CMK Data Scientist

Ubisoft – Paris area

Analyzed the behavior of players on multiple AAA and mobile games (+10 millions users) and created advanced user segmentations for customer knowledge, CRM targeting, and production prioritization.

Developed multiple data visualization tools to analyze specific kinds of data (d3-based Sankey diagrams, Importance-Satisfaction Matrices).

Animated different formations on Data Analysis, Statistics, Machine Learning and Python Programming.

Developed a Machine Learning model to describe a game based on the playing profiles of gamers.

Junior Data Scientist

Ubisoft – San Francisco

Analyzed the behavior of players on multiple AAA and mobile games (millions of users) and created user segmentations for customer knowledge and CRM targeting.

Developed a high-end framework based on R-Shiny to quickly deploy web applications combining typical data and statistical visualization and analyses.

Developed a TF-IDF based document clustering application to regroup documents around similar topics to facilitate declarative data analysis.

Research Engineer Intern

Argonne National Laboratory – Chicago area

Developed a Markov Chains-based algorithm based on that profile to generate realistic speed profiles on any itinerary, where previously simulations required to actually drive on the said itinerary.

Developed a Matlab GUI to support the Autonomie team in using this new feature, with a very flexible and user-friendly design displaying the generated speed profiles.

MITx

Graduate-level courses – EdX

18.6501x Fundamentals of Statistics: passed with 100%.

6.86x Machine Learning with Python – From Linear Models to Deep Learning: passed with 100%.

Mines ParisTech

M.S. Mechanical and Energy Engineering – Paris area

Designed a new chassis with wheels for a quad-copter to enable ground movement. The drone successfully moved in the air and on the ground at the end of the 3-weeks project.

École polytechnique

M.S. Engineering and Business Administration – Paris area

Minors in Mathematics, Energy, Applied Mathematics and Computer Science.

"Outstanding Investment award for investment in school and student life (2012)."

Built an autonomous robot to compete in the 2011 French Robotics Cup.