#127 Michal Klos, Using Snowflake To Grow Food

Summary
Michal Klos of Indigo explains how they use Snowflake to help grow food, improve agriculture and the protect environment.

Details
Who he is, what he does. Decommoditizing agriculture. What Snowflake is, it's in all the clouds. Difference between a data warehouse and a database; could Snowflake be used instead of a database. Michal’s first experience with Snowflake a few years ago; how he uses it now; where the data Indigo uses comes from. Copying the data to traditional dbs. Querying Snowflake. Example of how Indigo uses data from prototype to production. How big do you need to be to use Snowflake. How to get started; put an API in front of the warehouse. Tech stack at Indigo. They are hiring.

Links
Michal's LinkedIn

Download mp3 of podcast

#109 Joshua Sheppard, Data Science is Hard

Summary
Joshua Sheppard of Infinite Campus tells my about their data science and machine learning projects and how you can start your own.

Details
Who he is, what he does. What is data science, is a data scientist a role or a team, what skills are needed. Data vs big data. When does SQL + math become science, how to get started, Python, R and other languages; trying to follow software engineering principles when doing data science, testing, source control, etc. Azure and AWS machine learning, getting your data in to the cloud. Moving to production, scaling. Josh's data and insights into the school districts in Kentucky. Applying insights to other locations. Home baking your data science project vs leveraging the cloud platforms, it's all about access to data. Future of the field.

Links
Joshua's homepage
Joshua's Twitter

Download mp3 of podcast

#42 Eric Schles, Ending Slavery with Data

Summary
Eric Schles tells me that "slavery is the most extreme version of income inequality" and how he is using technology to end it.

Details
Who he is, how he became interested in human trafficking; Manhattan district attorney, technological deficiencies, Eric introduced databases, predictions not allowed by law; Demand Abolition, factors leading to trafficking, changing policies to fight trafficking; types of data analysis and how it helps, where the data comes from, scanning multiple sources, cross referencing with homeless databases; languages and technologies used; in the DA's office what comes first - the case or the data, once a case is closed the data is sealed; some of Eric's successes, reduced workload on DA, saving a woman from slavery; how you can help.

Eric's GitHub

Download mp3 of podcast

#30 Open Data Science Conference

Summary
Boston was host to the first ever Open Data Science Conference over the weekend of May 30th and 31st 2015. I spent the days wandering around talking to people with interesting stories.
I hope you enjoy this episode, it was fun making it.

My next podcast will be back to the normal interview format.

Download mp3 of podcast

Music Credits
Opening music – The Return, niese23

Closing and other – Bit Rio by Podington Bear