— Notes —
New this week... follow Data Elixir on LinkedIn for additional content and announcements throughout the week. The newsletter will always have the main content but there's never enough room for everything so if you like what you get here and would like more, follow Data Elixir on your favorite social media channel:
— In the News —
This list of 50 promising AI companies covers a broad range of applications in industries like human resources, security, insurance, finance, healthcare, transportation, and infrastructure. Each entry includes a short description of the problems being solved, the tools being built, funding and who the founders are.
The phrase “earthquake prediction” is practically taboo in seismology but recent studies with machine learning suggest that prediction might be possible for some types of earthquakes.
— Tools and Techniques —
It's not uncommon to start with problem statements that are imprecise and unclear. In this post, Jeremy Jordan focuses on design principles and shows how to define requirements to make sure that you're solving the right problem.
It's that time of year again! If you're an NFL fan, now's the time to start thinking about fantasy football. In this post, Aaron Miles shows how to use the ffanalytics package to scrape projections from multiple sites and build your optimal lineup.
Tristan Handy’s latest post describes how Fishtown Analytics manages to accurately scope analytics engineering projects more than 95% of the time!
As a VC at Insight Partners and SignalFire, Jon Ma spent several years evaluating tools geared towards data scientists and data engineers. In this post, he offers an overview of the 2019 data tools landscape and includes ideas for founders and investors that are interested in this space.
Useful ideas in this thread about online data collection.
Thrive in the fast-growing world of analytics with the Global Master of Management Analytics from Smith School of Business. Earn your degree while you work from anywhere in the world.
— Resources —
In this free, interactive course on predictive modeling, Julie Silge guides you through four case studies where you'll practice skills ranging from exploratory data analysis through model evaluation.
— Data Viz —
Great collection of step-by-step examples that show how to make publication-quality figures using ggplot2. Covers how to choose and customize scales, how to theme plots, and when and how to use extension packages. This is a new site by Claus Wilke that goes along with his book, Fundamentals of Data Visualization.
The Pudding team's latest project uses machine learning to recognize and classify political issues in Congressional tweets. The tweets are then used to support interactive visualizations that make it easy to explore issues, trends, and the concerns of specific representatives. This is a live, ongoing project that's worth coming back to during the upcoming election cycle. Also, the methods used and linked references on the main page are worth exploring.
It's well known in the data visualization community that color palettes are key for making visualizations clear and easy to understand. This is a great walk-through of how poor color choices likely helped President Trump misinterpret maps from the recent Hurricane Dorian, which eventually led to "SharpieGate." Includes suggestions and diagrams that are clearly more intuitive.
— Conferences & Events —
- Free Webinar: Data-Driven Approaches to Forecasting - Join Metis for this live online workshop designed for business leaders, data science managers, and decision makers seeking to understand how data-driven approaches can improve forecasting and planning. We will discuss examples of forecasting applications, explore some of the methodologies available, and address effective implementation. Sept 26, 12:00pm ET
- Domino Data Science Popup - Chicago - Advance the state of data science within your organization, glean new ideas and technical best practices, and meet like-minded people at the Midwest Data Science Pop-up in Chicago. Don’t miss these practical talks and workshops for data science leaders and practitioners. October 8, 2019