Artwork for podcast Collaborative Craft
It's a Process: More than Machine Learning with Hana Lee
Episode 42nd September 2021 • Collaborative Craft • 8th Light
00:00:00 00:48:17

Share Episode

Shownotes

"You can build an initial model, but you have to keep updating it. You have to continually operate it, doing things incrementally rather than trying to solve the whole problem in one go. One of the benefits is that we have a good framework for building things incrementally." - Hana Lee

Machine learning is only as good as the humans who create the program. Even machines have biases. Hana Lee is a Principal Software Crafter at 8th Light. Before joining the team, she was immersed in academia and has a unique take on tech.

In our conversation today, Hana discusses her life in academia, the case for creating cross-functional teams, and how to frame data problems for machine learning success. Listen to learn about her process.

  • 05:53 - Genomics to Software
  • 07:07 - 8th Light Apprenticeship Model
  • 08:01 - Reproducibility 
  • 09:40 - data analysis vs. data science vs. data engineering
  • 13:58 - Cross-Functional Teams 
  • 15:54 - Work Collaboratively from the Beginning 
  • 20:33 - Probing the Model
  • 23:56 - Machine Learning Features
  • 25:52 - Frame the Problem in a Realistic Way
  • 30:35 - Analysis Paralysis
  • 32:51 - Translating ML to Business Terms
  • 36:40 - Machine Learning Bias
  • 39:59 - Get in touch with Hana
  • 43:14 - Final Thoughts with Thomas and Jerome

Context Links: 

The Failure of Big Data

85% of Big Data Projects Fail

87% of Projects Never Make it into Production 

Hana Lee completed a postdoctoral fellowship at the University of Chicago, where she studied the genomics of host-pathogen interactions. She holds a Ph.D. in molecular biology at UC Berkeley, an AB from Harvard University in biochemical sciences, and an AWS certification as a Solutions Architect Associate.Now at 8th Light, Hana is a Principal Software Crafter where she’s currently leading data engineering work with a global reinsurance client to take prototype machine learning models that predict insurance risk and turn them into production-ready, scalable services. Her system is responsible for the automated data ingestion and feature engineering pipeline, delivering real-time predictions, continually validating the model’s performance, and generating reports with interactive visualizations so that non-technical stakeholders can make informed decisions about the model’s performance. Twitter: @lee_hn LinkedIn: hanalee07

Thomas Countz is a Senior Software Crafter at 8th Light where he works with a variety of ambitious teams on a variety of ambitious projects. A true curious nerd at heart, Thomas digs into everything from robotics and cider making to bouldering and Shakespeare’s comedies. To hear even more about Thomas, you can follow him on Twitter at @thomascountz and visit his blog at https://thomascountz.com.

Jerome Goodrich is an adoring husband, new dog dad, and all-around curious explorer. Through his work as a Principal Software Crafter at 8th Light, Jerome leads amazing software teams to design and develop thoughtful solutions to complex problems. He loves pairing strenuous hikes with deep conversations and is always trying to see things clearly and with an open heart. Jerome lives much of his life off of the internet, but he occasionally writes on his website: https://jeromegoodrich.com

8th Light partners with businesses and community groups to craft software that unlocks human potential and makes the world a better place. We’re passionate about designing for people, inspiring through education, and empowering the future. With teams spread across the globe—including Chicago, London, Los Angeles, New York, Austin, and Madison—we’re always eager to hear about ambitious new projects. Learn more about our team and reach out at https://8thlight.com

If you'd like to receive new episodes as they're published, please subscribe to Collaborative Craft in Apple Podcasts, Google Podcasts, Spotify or wherever you get your podcasts. If you enjoyed this episode, please consider leaving a review in Apple Podcasts. It really helps others find the show.

Podcast episode production by Dante32.