In the opening keynote at SSIR‘s February 2016 Data on Purpose conference, Jake Porway shares best practices for data storytellers and shows why knowing what the data is or is not saying is critical to creating ethical and accurate visualizations. Among other things, he explains the pitfalls of pie charts, why you should be wary of word clouds, and why good data storytelling ultimately means good statistics. He also argues that the real power of data storytelling lies not just in reporting on past activity, but in making decisions that drive decision-making in the future.

Porway is the founder and executive director of DataKind, a nonprofit that uses data science in the service of humanity. He previously worked at the New York Times R&D Lab, Google, and Bell Labs, and has spoken at IBM, Microsoft, and the White House. He holds a bachelor’s degree in computer science from Columbia University and a master’s degree and a doctorate in statistics from the University of California, Los Angeles.

If desired, you can follow along with the slideshow that accompanied Porway’s presentation here.