Benjamin J. Hammack

Lead Data Scientist & Software Developer

πŸ“ Chicago, IL | πŸ“ž (630) 746-1685 | πŸ“§ bjhammack@protonmail.com

LinkedIn | GitHub

Professional Overview

  • Extensive work leading, coordinating, and executing complex machine learning and data analytics projects
  • Proficient in the design, development, and testing of predictive models (transformers, neural networks, logistic/linear regression models, support vector machines, etc.) using multiple languages and data systems
  • Strong experience in multiple high-level programming languages, including, but not limited to: Python, R, and C++
  • Strong background in the cleaning, transformation, and analyzing of messy, un-coded, and raw data
  • Extensive experience at all levels of the ETL process
  • Strong understanding and experience working with RDMS including MS SQL Server, MySQL, PostgreSQL
  • Experience working on and with cloud technologies, including AWS, Hadoop, Google Cloud Services, and Microsoft Azure
  • Experience developing Spark drivers and executors for scalable predictive modeling pipelines

Education

Master of Science, Data Science

Lewis University, Romeoville, IL

July 2020

GPA: 3.70

Bachelor of Science, Computer Science

Ball State University, Muncie, IN

May 2017

Professional Experience

Lead Data Scientist

Nielsen, Chicago, IL

August 2021 – Present

As part of a team of talented data scientists and mathematicians, I built, evaluated, and maintained machine learning models. Developed advanced data pipelines that connected our models to our robust, cloud, data infrastructure.

  • Utilized Python, Spark, AWS, and Apache Airflow to develop a full-stack machine learning model to ingest data from S3, perform cleaning and analysis, model the data, output the results throughout our cloud infrastructure, and generate automated reports
  • Performed statistical analysis on a variety of models, presenting the results to the head of data science, with suggestions for model improvements
  • Helped establish best practices within the data science team for workflow, maintaining codebases, and development best practices
  • Provided mentorship to junior data scientists, providing both project support and guidance on data science problems
  • Lead inter-team projects aimed to develop cutting edge products for Nielsen’s clients
  • Worked with external auditing companies to communicate our modeling processes, provide requested datasets, and useful analytics to complete annual accreditations

Data Strategy Scientist

Volkswagen Credit, Libertyville, IL

August 2020 – August 2021

Working on a team of data scientists, analysts, and data governance experts, I analyzed, cleaned and distributed data. I established best practices for data usage and data consumption and helped transition Volkswagen from an on-premises data company to an agile, cloud-based company.

  • Converted large amounts of deprecated SAS programs to up-to-date and automated Python scripts for continued analysis and reporting
  • Utilized Python and Spark to convert type 2 database tables into transactional tables to be consumed by leadership team and machine learning models
  • Profiled critical database tables for business processes, identified danger areas and designed approaches for resolving issues
  • Developed new database tables based on business users' needs for analysis, reporting, and machine learning
  • Assisted in the transition of Volkswagen to cloud-based company in AWS, developed best practices for cloud processes, transitioned data into Redshift
  • Helped in the development of data governance strategies, mapping out areas of need and creating a "source of truth" for developing data

Data Services Manager

FarmLogix, Chicago, IL

October 2018 – July 2020

Working in a fast-paced environment as Data Visualization Lead and then Data Services Manager, created data visualizations for internal and client-side use, developed and maintained ETL processes, and led data projects for clients.

  • Used Python (Pandas, SciPy, etc.) to clean and load large datasets of food transaction invoices from public school districts, major food distributors, and local farms
  • Developed visualizations using PowerBI and Tableau and presented them internally and to clients
  • Maintained and updated legacy pipelines using AWS, GCP, MySQL, and Apache Airflow
  • Led a project coordinating with seven of the largest school districts in the United States to receive, clean, combine, upload, and analyze their transaction and nutrient data to the cloud
  • Developed the ETL process for the reception and uploading of transaction data for one of the largest food distribution companies in the United States

Cloud Developer

Perficient, Inc., Chicago, IL

May 2017 – May 2018

Worked on multiple client projects developing systems and data management tools using Java, SQL, Spring Boot, and HTML.

  • Blue Shield of California: Developed systems to facilitate member-doctor matching using Java and SQL/ESQL
  • Network Real Estate: Developed data management tools using Java, Spring Boot, and HTML with MVC framework
  • Developed SQL scripts to transfer, copy, delete, and create data with integrity validation
  • Created UNIX scripts to backup database tables ensuring data integrity throughout development

IT Intern

National Express, Warrenville, IL

May 2016 – August 2016

Worked on various projects developing SharePoint intranet sites with C#, ASP.NET, JavaScript, Microsoft SQL Server, and HTML.

  • Developed an interactive, intranet, news feed with SharePoint Lists and JavaScript
  • Created and managed an SQL Server database to store and sort submitted internal audits
  • Developed software to create, edit, search, comment on, and delete internal audits using C#/ASP.NET and SharePoint
  • Used Microsoft PowerShell to deploy and manage intranet SharePoint sites

Technical Skills

Programming Languages

Python, R, C#, Java, JavaScript, SQL, ASP.NET

Databases

SQL Server, MySQL, MongoDB, IBM DB2, PostgreSQL

Cloud Computing

AWS (S3, EC2, RDS), Hadoop, Apache Spark, Apache Hive, Google Cloud Platform, Microsoft Azure

Data Analysis Tools

NumPy, pandas, scikit-learn, SciPy, Keras, TensorFlow, PyTorch, Matplotlib, ggplot2, Tableau, PowerBI, PySpark

Operating Systems

Windows, Linux, OSX, VMWare, Virtual Box

Additional Skills

Data interpretation, Data cleaning, Statistical analysis, Data management, Client-facing communication