Svetlana Vinogradova

Senior Data Scientist

Nuna

Biography

Currently, I am a Senior Data Scientist at Nuna, developing ML-based trend algorithms and surfacing insights for users and healthcare providers.

Prior to Nuna, I worked at Zwift building recommendation models designed to offer personalized training and route suggestions for users, drawing from their historical time-series data.

Before that, I worked at InsideTracker where I focused on integrating blood biomarkers and DNA data with physiological data from activity trackers to improve lifestyle recommendations and discovering new patterns and optimal zones in sleep, heart rate, and blood biomarkers.

I have always been passionate about teaching and explaining complex concepts in simple terms. During my PhD, I developed and taught a course “R and its application in bioinformatics”. In 2013, this course was the first R course taught in Russia and was very popular among students. Since then, I taught R to students and professionals, in groups and individually. I am an RStudio Certified Instructor in tidyverse and teach at posit Academy.

Interests

Machine Learning
Teaching
Storytelling with Data

Education

PhD in Mathematical Biology and Bioinformatics, 2016
Lomonosov Moscow State University
BSc and Msc in Bioengineering and Bioinformatics, 2010
Lomonosov Moscow State University

Experience

Senior Data Scientist

Nuna

Jul 2024 – Present Remote

Leading the development of the new ML-based trend algorithms and surfacing insights for users and healthcare providers

Lead Data Scientist

Zwift

Sep 2022 – Mar 2024 Remote

• Led the development and deployment of customer-facing product features, including introducing the racing score as part of a company-wide initiative for a personalized recommendation system. Conducted initial research, statistical modeling, and implemented the machine learning model in production, resulting in significantly enhanced user engagement. Collaborated with engineers and product teams, leading the data science aspect of the project.

• Developed a machine learning model for customer segmentation, leveraging behavior data from 1 million users on a virtual cycling gaming platform, aiding the business in expanding its recreational cycling enthusiast audience.

• Enhanced data integrity across multiple data streams by initiating and establishing a comprehensive data quality and governance review process, covering data validation, anomaly detection, and consistency checks

Lead Data Scientist

Inside Tracker

Aug 2019 – Sep 2022 Cambridge, MA

Led the Data Science team to integrate a unique dataset of blood biomarkers and genomic data with physiological data from wearable sensors (including sleep, RHR, HRV), performed end-to-end analyses, and built new product features. Built core Data Engineering infrastructure supporting the data science function, and set up internal consulting service supporting the Marketing, Product, and Executive teams.

Research Fellow

Harvard Medical School / Dana-Farber Cancer Insitute

Aug 2016 – Jul 2019 Boston, MA

Performed bioinformatics analysis of NGS data produced in the lab (RNA-seq, ChIP-seq), and developed algorithms and pipelines to address various biological questions: analysis of allelic imbalances in gene expression, chromatin marks signatures analysis using machine learning approaches and NGS experimental design.

PhD candidate and senior lecturer

Lomonosov Moscow State University

Aug 2010 – Jul 2016 Moscow, Russia

As a part of Mironov lab, I developed a computational approach to incorporate RNA probing data into RNA secondary structure prediction and genome-wide search for structured RNAs. Published 3 papers in peer-reviewed journals, and published a web-server. Additionally, I developed and/or taught the following courses: algorithms; algorithms in computational biology; bioinformatics; R language.

Researcher

Institute for Systems Biology

Jul 2010 – Apr 2013 Moscow, Russia

During time in the company, I got industry experience in PK/PD modeling and clinical pharmacology. I was a part of several projects closely interacting with colleagues from pharmaceutical companies and published a paper in a peer-reviewed journal.