Peter Smits Email and Phone Number
Peter Smits work email
- Valid
- Valid
- Valid
Peter Smits personal email
Data Scientist with a PhD in Evolutionary Biology. I have experience in shipping data, health care real-world data, display advertising, and academic research.I am an expert in Bayesian data analysis with extensive experience in generalized linear models, hierarchical/multilevel models, survival analysis, longitudinal data analysis, and discrete time series analysis.
-
Principal Business AnalystWizards Of The CoastSeattle, Wa, Us
-
Data Science Technical Program Management ConsultantShippo Jan 2024 - Aug 2024San Francisco, California, Us -
Principal Applied ScientistTruveta May 2022 - Jul 2023Seattle Area, Washington, Us -
Senior Applied ScientistTruveta Jun 2021 - May 2022Seattle Area, Washington, UsResearch and Product. I design, develop, and implement reproducible statistical analysis workflows for medical research.
-
Data Scientist IiAmazon Jan 2020 - Jun 2021Seattle, Wa, UsAmazon Advertising.Performance tools, reporting, and recommendations for Display advertising campaigns. -
Data Science FellowInsight Data Science Sep 2019 - Dec 2019San Francisco, Ca, Us– Designed Copyprism, a web application for generating draft product descriptions from an image.– Implemented web scraper for collecting IKEA product descriptions in python using beautifulsoup.– Fine-tuned GPT-2 natural language deep learning model on IKEA catalog in python using Google Colab, whose generated text was indistinguishable from human text 26% of the time.– Deployed Copyprism web application on AWS using flask. -
Postdoctoral ResearcherUniversity Of California, Berkeley Sep 2017 - Jul 2019Berkeley, Ca, Us– Designed multilevel discrete-time survival model using Stan to predict species extinction which identified species at risk of extinction within 1-million years with an AUC of 0.78.– Created multievel Bayesian time series model in Stan for predicting when rare extinction events were likely to be clustered in time based on geological information sourced from multiple databases.– Wrote nine chapters of online book on the analysis of paleontological and macroecological data using R, tidyverse, and brms. -
Graduate ResearcherThe University Of Chicago Sep 2012 - Jun 2017Chicago, Il, Us– Identified how differences in mammal species ecologies affected their survival rates over the last 65 million years using a multilevel Bayesian survival model implemented in Stan and R applied to a database of fossil occurrences (approx. 40k rows) accessed via web API.– Created hidden Markov birth-death model for incompletely observed longitudinal data in Stan where transition probabilities were modeled as multilevel regressions in order to identify how speciation and extinction rates varied over time by species ecology and environmental state.– Developed ensemble framework for identifying species based on 2D shape information using R and caret where average of multinomial logistic regression, neural network, and random forest models correctly differentiated seven closely related turtle species with an AUC over 0.98.– Mentored and taught graduate and undergraduate students in R, statistics, Stan, and pedagogy.
Peter Smits Education Details
-
University Of ChicagoEvolutionary Biology -
Monash UniversityGeneral
-
Macquarie UniversityPaleobiology Database Intensive Workshop In Analytical Palaeobiology
-
University Of WashingtonEcology And Evolutionary Biology
Frequently Asked Questions about Peter Smits
What company does Peter Smits work for?
Peter Smits works for Wizards Of The Coast
What is Peter Smits's role at the current company?
Peter Smits's current role is Principal Business Analyst.
What is Peter Smits's email address?
Peter Smits's email address is pe****@****eta.com
What schools did Peter Smits attend?
Peter Smits attended University Of Chicago, Monash University, Macquarie University, University Of Washington.
Free Chrome Extension
Find emails, phones & company data instantly
Aero Online
Your AI prospecting assistant
Select data to include:
0 records × $0.02 per record
Download 750 million emails and 100 million phone numbers
Access emails and phone numbers of over 750 million business users. Instantly download verified profiles using 20+ filters, including location, job title, company, function, and industry.
Start your free trial