Colin Catlin
Principal Data Science Architect
Minnesota, United States
Summary
🤩
Rockstar🎓
Top SchoolColin Catlin is a Principal Data Science Architect with eight years of experience building production forecasting and ML infrastructure, currently leading forecasting innovation at Lovelytics. He has pioneered automated, high-accuracy ensembled time series methods—contributing to open-source forecasting projects and winning competitions—while making models up to 100x faster and more explainable for non-technical users. Colin has deep hands-on DevOps and data engineering experience, having run Airflow CI/CD pipelines, large-scale BigQuery ingestion, and cost-saving infrastructure migrations at UnitedHealth. His background spans industry and research-driven roles where he delivered measurable ROI applications (from retail forecasting to healthcare risk models) and built enterprise data lakes and CI/CD for analytics. Based in Minnesota, he brings an unusual combination of classical archaeology and neuroscience training that informs a meticulous, multidisciplinary approach to data problems.
8 years of coding experience
3 years of employment as a software developer
Bachelor of Science (BS) Neuroscience, Bachelor of Science (BS) Neuroscience at University of MinnesotaHigh School Diploma, High School Diploma at Mounds View High SchoolMasters of Business Analytics Data Science, Masters of Business Analytics Data Science at UMN Carlson School of Management
English, Latin
Stackoverflow
153reputation
53kreached
4answers
0questions
Github Skills (16)
forecasting10
machine-learning10
forecast10
time-series-forecasting10
python10
deeplearning-ai9
deep-learning9
pandas6
datetime6
type-conversion6
parallel-processing6
trigger6
azure-functions6
azure-container-instances6
random-forest6
Programming languages (2)
Github contributions (5)
winedarksea/AutoTS
Nov 2019 - Jan 2023
Automated Time Series Forecasting
Role in this project:
Data Scientist & Machine Learning Engineer
Data Scientist & Machine Learning EngineerContributions:62 releases, 429 commits, 149 PRs in 3 years 2 months
Contributions summary:Colin's commits primarily involved building and refining time series forecasting models. They implemented and iterated on various models, likely using libraries for time series analysis and machine learning. Their work included experimenting with diverse algorithms and techniques.
forecastingpythontime-series-analysisdeep-learningseries-forecasting
conda-forge/autots-feedstock
Feb 2022 - Mar 2025
A conda-smithy repository for autots.
Contributions:18 reviews, 33 PRs, 29 pushes in 3 years 1 month
pythonautotscondasmithy
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.