Totte Harinen
Senior Data Scientist
San Diego, California, United States
Summary
🤩
Rockstar🎓
Top SchoolTotte Harinen is a Senior Data Scientist based in San Diego with eight years of experience applying causal inference and experimental design to real-world problems. Currently at Airbnb, he blends rigorous academic training—a PhD in Philosophy from King’s College London and social sciences degrees from University of Helsinki—with practical machine learning engineering. He contributes to open-source causal ML tooling (notably examples and tests for the well-regarded uber/causalml repo), emphasizing uplift modeling, meta-learners, and counterfactual optimization. Totte’s background gives him a distinctive strength in clearly formulating assumptions and interpreting causal claims alongside building scalable models. He excels at translating complex experimental questions into robust, testable algorithms that drive product decisions. Colleagues rely on him for combining analytical depth with pragmatic engineering to deliver measurable business impact.
7 years of coding experience
MSocSci, Social Sciences, First, MSocSci, Social Sciences, First at University of HelsinkiDoctor of Philosophy (Ph.D.), Philosophy, Doctor of Philosophy (Ph.D.), Philosophy at King's College LondonVisiting student, SOCIAL SCIENCES, Visiting student, SOCIAL SCIENCES at University of Glasgow
English, Finnish, Swedish, German
Github Skills (11)
scikit10
lift10
pandas10
machine-learning10
lifting10
python10
modeling10
causal-inference10
scikit-learn10
logistic-regression9
xgboost9
Programming languages (3)
Github contributions (5)
uber/causalml
Jul 2019 - Mar 2022
Uplift modeling and causal inference with machine learning algorithms
Role in this project:
Data Scientist & ML Engineer
Data Scientist & ML EngineerContributions:14 reviews, 42 commits, 29 PRs in 2 years 8 months
Contributions summary:Totte primarily contributed to example code demonstrating uplift modeling techniques using the CausalML library. Their commits showcase the application of tree-based algorithms and meta-learners for uplift modeling with synthetic datasets. The user implemented functionalities for including binary outcome options to meta-learners and added tests for validating the different classification meta-learners. They also introduced and tested a counterfactual value optimization method within the framework.
fairness-mldeep-learningmachine-learning-algorithmscausalinference
t-tte/causality-papers
Jun 2018 - Jan 2019
Contributions:10 pushes, 1 branch in 7 months
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.