Jana Dodson, Developer in South Lake Tahoe, CA, United States
Jana is available for hire
Hire Jana

Jana Dodson

Verified Expert  in Engineering

Data Scientist and Developer

Location
South Lake Tahoe, CA, United States
Toptal Member Since
May 20, 2022

In her more than eight years of experience, Jana has worked at both small and large companies and has been through many stages of growth. She has also collaborated with people across the tech industry, including executives, designers, product managers, engineers, business leaders, and marketers. Jana's job is to take loosely defined problems, design robust solutions, and find the quickest path to implementation while ensuring the solution is never a "black box" for the client.

Portfolio

Shift
Python, Amazon SageMaker, SQL, Apache Airflow, AWS Lambda...
Nielsen
Python, SQL, Bitbucket, Oracle, Hadoop, Zeppelin, Databricks, Tableau...
Acumen
SAS, SQL, Data Science, Supervised Learning, Machine Learning, Modeling, ETL...

Experience

Availability

Part-time

Preferred Environment

Python, SQL, Amazon SageMaker, Apache Airflow, Jupyter Notebook, Pandas

The most amazing...

...initiative I've led was revamping the pricing algorithm at an online car retailer by introducing new ML techniques and automating model training and deployment.

Work Experience

Lead Data Scientist

2018 - 2022
Shift
  • Designed, built, tested, and iterated on machine learning (ML) algorithms across the business. Used techniques such as regularization, ensembling, gradient boosting, cross-validation, and dimensionality reduction.
  • Found and validated external and internal data sources to support models.
  • Increased organizational trust by building data visualizations to explain “black box” models. These models are sufficiently complex that they are not straightforwardly interpretable to humans.
  • Worked with business stakeholders to identify key areas of opportunity related to the accuracy and scalability of pricing algorithms to optimize for business metrics such as GPU, revenue, and sales volume.
  • Collaborated with the data engineering team to establish requirements for and build the first ML model training and deployment system using Amazon Sagemaker for live inferences and Apache Airflow for batch inferences.
  • Built out monitoring systems for production models to track input and output over time and catch degradations in quality.
  • Ran technical screens for data science team candidates. Onboarded and mentored more than five new data scientists.
  • Acted as the interim data science manager during a three-month gap in leadership.
Technologies: Python, Amazon SageMaker, SQL, Apache Airflow, AWS Lambda, Amazon Web Services (AWS), GitHub, Docker, Amazon EC2, Redshift, PostgreSQL, Amazon S3 (AWS S3), Git, Jupyter Notebook, Sisense, Regression, Gradient Boosted Trees, Random Forests, Data Science, Supervised Learning, Unsupervised Learning, Pandas, Machine Learning, Modeling, ETL, Data Analysis, Data Visualization, Forecasting, Statistical Analysis, Model Development, Microsoft Excel, Web Scraping, Data Queries, Algorithms, Artificial Intelligence (AI), Testing, NumPy, Spark, Databases, Data Reporting, Data Analytics

Senior Data Scientist

2016 - 2018
Nielsen
  • Supported a product suite that produced a continuous stream of data related to wireless network usage and performance from over 100,000 mobile devices.
  • Built out algorithms for data anomaly detection, predictive modeling of customer satisfaction based on network performance, and data pipeline management.
  • Collaborated cross-functionally to productionize these algorithms.
  • Hired as the first full-time data scientist on the product suite. Helped expand the team by interviewing and training four new data scientists.
  • Established the tool set, coding standards, and best practices for the team.
Technologies: Python, SQL, Bitbucket, Oracle, Hadoop, Zeppelin, Databricks, Tableau, Data Science, Supervised Learning, Unsupervised Learning, Pandas, Machine Learning, Modeling, ETL, Data Analysis, Data Visualization, Statistical Analysis, Model Development, Generative Pre-trained Transformers (GPT), GPT, Natural Language Processing (NLP), Microsoft Excel, Web Scraping, Data Queries, Algorithms, Artificial Intelligence (AI), Testing, NumPy, Spark, Databases, Data Reporting, Data Analytics

Data Analyst | Statistical Programmer

2014 - 2016
Acumen
  • Developed, optimized, and documented SAS programs for ETL and analysis of large Medicare and Medicaid claims datasets to support government healthcare research projects.
  • Created and implemented risk models to identify healthcare providers who systematically over-utilize Medicare resources or have patients with poor health outcomes.
  • Led SAS and SQL training classes for new programmers and managed interns.
Technologies: SAS, SQL, Data Science, Supervised Learning, Machine Learning, Modeling, ETL, Data Analysis, Data Visualization, Statistical Analysis, Model Development, R, Microsoft Excel, Data Queries, Algorithms, Databases, Data Reporting, Data Analytics, Healthcare IT

Auto Loan Pre-qualification Tool

I have built a model to reverse the terms of car loans, i.e., whether or not someone will get approved for a loan, the annual percentage rate (APR), the minimum required down payment, and the term length. This model was then used to help shoppers find vehicles within their budget, given their particular debts, income, and credit score.

Languages

Python, SQL, SAS, R

Libraries/APIs

Pandas, NumPy

Tools

Sisense, Tableau, Microsoft Excel, Amazon SageMaker, Apache Airflow, GitHub, Git, Bitbucket

Paradigms

Data Science, ETL, Testing

Platforms

Jupyter Notebook, Oracle, AWS Lambda, Amazon Web Services (AWS), Docker, Amazon EC2, Zeppelin, Databricks

Storage

PostgreSQL, Databases, Redshift, Amazon S3 (AWS S3)

Other

Regression, Data Analysis, Data Visualization, Statistical Analysis, Model Development, Web Scraping, Data Queries, Algorithms, Artificial Intelligence (AI), Data Reporting, Data Analytics, Big Data, Machine Learning, Statistics, Gradient Boosted Trees, Random Forests, Supervised Learning, Unsupervised Learning, Modeling, Forecasting, Natural Language Processing (NLP), GPT, Generative Pre-trained Transformers (GPT), Research, Healthcare IT

Frameworks

Hadoop, Spark

2010 - 2014

Bachelor's Degree in Mathematics and Physics

Georgetown University - Washington, DC, United States

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