Emmett is currently unavailable
Emmett Storts
Verified Expert in Engineering
Data Scientist and Developer
Littleton, CO, United States
Toptal member since July 6, 2026
Bio
Emmett is a senior data scientist focused on end-to-end analytics and machine learning solutions. With over eight years of experience, Emmett has shipped production ETL/ELT pipelines, built executive dashboards, performed deep dive statistical analysis, and released ML models. He's comfortable at both small startups and enterprise businesses and everything in between. Emmett excels at building tools that drive actionable insights for decision-makers.
Portfolio
The Daily Wire
Data Build Tool (dbt), Snowflake, Clustering, CI/CD Pipelines, Docker...
Freelance Clients
Fivetran, Large Language Models (LLMs), OpenAI API, Clustering, PCA, Tableau...
Product Hunt
SQL, Python, A/B Testing, Dashboards, Data Analysis, Data Visualization...
Experience
- Statistical Methods - 10 years
- Data Analysis - 10 years
- Data Engineering - 8 years
- Python - 8 years
- Machine Learning - 8 years
- ETL - 8 years
- SQL - 8 years
- Deep Learning - 7 years
Work Experience
Data Scientist
2025 - 2026
The Daily Wire
- Designed and deployed a complete overhaul of a core data model in dbt and Snowflake, which was then viewed in a daily dashboard by the entire executive team.
- Built and deployed 4 production models (regressions, clustering, natural language processing (NLP), and random forests).
- Built and maintained an end-to-end YouTube network analysis Streamlit app for the production team to better understand the YouTube algorithm and help with programming decisions.
- Designed and deployed a lifetime value (LTV) data model, which was then used by marketing for balancing win-back spending and finance for financial projections.
- Developed a Streamlit application for on-platform comment insights, integrating AI summarization and vector embeddings, which was used by the production team to find comments for audience engagement.
- Moved the team's modeling off local machines into a monitored CI/CD pipeline using dbt, Docker, and GitHub Actions so anyone could ship and retrain reliably.
Technologies: Data Build Tool (dbt), Snowflake, Clustering, CI/CD Pipelines, Docker, Streamlit, Machine Learning Operations (MLOps), Machine Learning, Generative Artificial Intelligence (GenAI), Regression, Scikit-learn, YouTube API, Cursor AI, Python, SQL, Google Cloud Platform (GCP), Segment, Causal Inference, Data Analysis, Data Visualization, Data Communication, Statistical Methods, OpenAI API, Embeddings from Language Models (ELMo), A/B Testing, Lifetime Value (LTV), Data Cleaning, Pandas, ETL, ELT, Data Warehousing, Database Management, Git, XGBoost, Neural Networks, Business Intelligence (BI), Data Analytics, Artificial Intelligence (AI), Star Schema, Data Science, Communication, Feature Engineering, Model Deployment, Model Development, Model Evaluation, Monitoring, Stakeholder Management, Bayesian Statistics, Linear Regression, BigQuery, Google Cloud Storage, Streaming
Founder and Data Scientist
2024 - 2025
Freelance Clients
- Served as the point person for all data requests on Medimap. Constructed 10+ Power BI dashboards for self-service analytics.
- Built automated retention reports and dashboards for client subscription services, eliminating manual reporting entirely and improving visibility into churn trends.
- Migrated from Fivetran to Hevo to save 50% on data engineering costs.
- Generated 50,000 pieces of SEO content with LLMs (OpenAI API) leading to a 5% increase in sitewide traffic.
- Applied clustering and PCA to build audience segmentation models for SEO and content personalization.
- Built and managed 5 Tableau dashboards for Charter Communications, including 1 specifically for upper management.
- Handled 20+ ad-hoc requests for Charter Communications. Ensured data quality and accuracy through robust validation processes across all requests and dashboards.
Technologies: Fivetran, Large Language Models (LLMs), OpenAI API, Clustering, PCA, Tableau, Amazon Web Services (AWS), Redshift, Amazon Athena, Amazon S3 (AWS S3), Microsoft Power BI, GitLab, Streamlit, Non-technical Communication, Dashboards, Data Cleaning, Data Engineering, ETL, ELT, Data Pipelines, Pandas, Scikit-learn, Data Warehousing, Git, XGBoost, Business Intelligence (BI), Data Analytics, DAX, Artificial Intelligence (AI), Data Science, Communication, Feature Engineering, Model Deployment, Stakeholder Management, Bayesian Statistics, Linear Regression
Data Analyst
2022 - 2023
Product Hunt
- Owned the full analytics function on a two-person team, from ad-hoc requests to experimentation, partnering directly with non-technical stakeholders.
- Applied causal inference and econometric methods (e.g., diff-in-diff, propensity scoring) in SQL and Python to evaluate product and marketing initiatives.
- Collaborated with marketing on newsletter attribution, resulting in a self-service dashboard for non-technical stakeholders.
- Led 23+ A/B experiments in collaboration with leadership, design, product, and engineering teams, which led to a product redesign that increased user engagement by 18%.
- Developed spam detection models that reduced customer time-to-action by 25%.
- Built ad impression forecasting models for the sales team to optimize outreach strategy and accurately project pipeline revenue.
Technologies: SQL, Python, A/B Testing, Dashboards, Data Analysis, Data Visualization, Causal Inference, Econometrics, Marketing Attribution, Marketing Analytics, Machine Learning, Forecasting, Sales Analysis, Product Analytics, Non-technical Communication, Data Cleaning, Pandas, ETL, Redshift, Data Warehousing, Data Engineering, Time Series, Neural Networks, Business Intelligence (BI), Data Analytics, Artificial Intelligence (AI), Star Schema, Data Science, Communication, Feature Engineering, Model Deployment, Demand Forecasting, Model Development, Model Evaluation, Monitoring, Stakeholder Management, Time Series Forecasting, Bayesian Statistics, Linear Regression, LSTM
Senior Analytics Specialist
2020 - 2022
WEC Energy Group
- Led anomaly detection of failed meters using deep learning and neural networks, allowing for early intervention.
- Developed predictive models for customer retention and payment agreements using gradient boosting and random forests, which increased customer satisfaction by 10%.
- Built electric outage categorization models using natural language processing and random forests to eliminate 5 hours of work across 3 people.
- Managed 3 student interns and 2 data science outreach projects.
Technologies: SQL, Python, Amazon Web Services (AWS), Machine Learning, Deep Learning, Gradient Boosting, Random Forests, Natural Language Processing (NLP), Data Cleaning, Data Analysis, Data Pipelines, ETL, XGBoost, Time Series, Neural Networks, Business Intelligence (BI), Data Analytics, DAX, Artificial Intelligence (AI), Data Science, Communication, Feature Engineering, Model Deployment, Model Development, Model Evaluation, Monitoring, Stakeholder Management, Bayesian Statistics, Linear Regression
Analytics Specialist
2018 - 2020
WEC Energy Group
- Optimized customer call center costs through a mix of full-time and seasonal hiring.
- Used SQL and Python to evaluate a company-wide program and concluded it had no statistically significant impact on customer satisfaction (the primary metric for the program), which led to the end of the program.
- Reduced manual metric reporting by 90% for the largest IT project in company history (Customer Service 2022) using Python and Power BI.
- Provided internal support via 10+ data-centric projects, applying econometric and causal inference to evaluate program effectiveness and inform operational decisions.
Technologies: SQL, Python, Microsoft Power BI, Dashboards, Data Analysis, Causal Inference, Econometrics, Cost Reduction & Optimization (Cost-down), Data Visualization, Data Communication, Non-technical Communication, Data Cleaning, Data Pipelines, ETL, Business Intelligence (BI), Data Analytics, DAX, Data Science, Communication
Project History
Destiny RAG System: Natural Language Library Search
I built a retrieval-augmented generation (RAG) system that lets middle school students search their library catalog with natural-language queries rather than keyword matching. A student can ask "books about dragons but not too scary" or "stories like Percy Jackson but about Norse mythology," and get relevant results from the catalog.
The system indexes 10,000+ books from the school's catalog using OpenAI's text-embedding-3-large model, stores the embeddings in Pinecone for fast semantic retrieval, and uses the OpenAI API to handle query understanding and result generation. The pipeline covers data ingestion from the catalog, embedding generation, vector storage, and a query interface designed for the end users. It was demoed to school staff with a full build-out in progress.
The system indexes 10,000+ books from the school's catalog using OpenAI's text-embedding-3-large model, stores the embeddings in Pinecone for fast semantic retrieval, and uses the OpenAI API to handle query understanding and result generation. The pipeline covers data ingestion from the catalog, embedding generation, vector storage, and a query interface designed for the end users. It was demoed to school staff with a full build-out in progress.
Local Catholic Business Directory: Community Streamlit App
I designed and deployed a Streamlit dashboard for a local church business networking group, providing members with a searchable, interactive directory of community businesses. The app features 100+ business listings with categorical filtering and a clean interface built for non-technical end users.
The project covered the full lifecycle: data ingestion, cleaning, schema design, application development, and deployment. It's a working example of taking a community need and delivering a functional data product end-to-end with a lightweight stack.
The project covered the full lifecycle: data ingestion, cleaning, schema design, application development, and deployment. It's a working example of taking a community need and delivering a functional data product end-to-end with a lightweight stack.
Education
2017 - 2017
Master's Degree in Economics
The University of North Carolina at Greensboro - Greensboro, NC, USA
2016 - 2016
Bachelor's Degree in Economics
The University of Wisconsin at Whitewater - Whitewater, WI, USA
Skills
Libraries/APIs
Pandas, Scikit-learn, OpenAI API, XGBoost, YouTube API, LSTM
Tools
Tableau, Git, Microsoft Power BI, GitHub, Amazon Athena, GitLab, BigQuery
Languages
SQL, Python, Snowflake
Paradigms
ETL, Business Intelligence (BI)
Storage
Data Pipelines, Redshift, Amazon S3 (AWS S3), Database Management, Google Cloud Storage
Platforms
Amazon Web Services (AWS), Docker, Google Cloud Platform (GCP)
Frameworks
Streamlit
Other
Causal Inference, Regression, Statistical Methods, Data Analysis, Data Visualization, Data Communication, Machine Learning, Dashboards, Econometrics, Non-technical Communication, Data Cleaning, Data Engineering, ELT, Data Analytics, Data Science, Communication, Stakeholder Management, Linear Regression, Random Forests, Neural Networks, Vector Embeddings, Client Communication, Generative Artificial Intelligence (GenAI), Cursor AI, Segment, A/B Testing, Marketing Analytics, Forecasting, Product Analytics, Deep Learning, Natural Language Processing (NLP), APIs, Data Warehousing, DAX, Artificial Intelligence (AI), Feature Engineering, Model Deployment, Model Development, Model Evaluation, Data Build Tool (dbt), Clustering, CI/CD Pipelines, Fivetran, Large Language Models (LLMs), PCA, Gradient Boosting, Time Series, Retrieval-augmented Generation (RAG), Machine Learning Operations (MLOps), Business Management, Embeddings from Language Models (ELMo), Lifetime Value (LTV), Marketing Attribution, Sales Analysis, Cost Reduction & Optimization (Cost-down), Pinecone, Star Schema, Demand Forecasting, Monitoring, Time Series Forecasting, Bayesian Statistics, Streaming
Collaboration That Works
How to Work with Toptal
Toptal matches you directly with global industry experts from our network in hours—not weeks or months.
1
Share your needs
Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2
Choose your talent
Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3
Start your risk-free talent trial
Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.
Top talent is in high demand.
Start hiring