And that’s a wrap! Yesterday was the third and final day of AnacondaCON 2018, and what a ride it’s been. Read some highlights from what you missed, and stay tuned for our comprehensive AnacondaCON 2018 recap, coming soon!


Improving Your Anaconda Distribution User Experience

Anaconda Product Manager Crystal Soja presented a roadmap of upcoming plans and release cadences for each aspect of the Anaconda Distribution: the Anaconda and miniconda installers, repo.anaconda.com, anaconda.org, Anaconda Navigator, conda, and conda-build. One exciting change on the horizon? An improved conda/pip user experience!

Setting Data on Fire

Research Engineer Craig Weinschenk introduced us to the Fire Community Assessment/Response Evaluation System (FireCARES), which provides fire departments the ability to add a technical basis to what historically has been an anecdotal discussion regarding community hazards and risks, as well as the impact of changes to fire department resource levels. He also demonstrated the National Fire Operations Reporting System (NFORS), a real-time data analysis tool for overcoming the obstacles of flawed fire incident data.

Testing Together


Krissy Tripp of Evolytics talked to us about how to maximize insights and the business impacts of A/B testing through advanced statistical methods. She showed us how collaboration between A/B testing and data science teams can deliver amazing customer experiences, uncover novel consumer insights, and scale the process to enterprise levels.

Approaching Causal Inference

Jenny Lin, a data scientist at Yelp, talked to a packed house about how to conscientiously approach causal inference in large, messy data sets in the absence of an experiment (or when experimental setup was not ideal). Jenny walked us through a stylized example of a causal inference problem she ran into at Yelp, and demonstrated how easily one can arrive at very misleading conclusions when not correcting for certain issues.


Accessing Data from Disparate Sources

Dremio CTO & Co-Founder Jacques Nadeau provided an overview of Dremio and Arrow, and how projects like Pandas are leveraging Arrow to achieve high performance data processing and interoperability across systems. He also showed us how companies can use Arrow to access and analyze data across disparate data sources without having to physically consolidate it into a centralized data repository.

Closing Keynote: David Yeager

After three days filled with data science and machine learning, we concluded our program with human learning! David Yeager, Assistant Prof. of Developmental Psychology at University of Texas, Austin, is a renowned expert on grit and how growth mindsets can motivate people to achieve excellence. He shared with us how it is more important than ever to be a “learner”—that is, to be able to teach ourselves new skills. David showed us how to create an environment that fosters the grit needed to be a learner, so that we can adapt our skills and knowledge to the quickly changing economy.

Congratulating our Winner

Congratulations to Shelley Chang of PCCI, who won our drawing for an NVIDIA TITAN V GPU! We hear demand for these is so high right now, AnacondaCON 2018 is the only place you can get one. Enjoy, Shelley!

Feeling Gratitude

Thanks again to all of our awesome sponsors for helping to make AnacondaCON 2018 such a great success: DataCamp, Dremio, NVIDIA, Full Spectrum Analytics, NumFOCUS, Intel, General Assembly, and Microsoft. We never could have done it without you!

And finally, thank you to all the passionate, curious, and inspiring members of our data science community who attended AnacondaCON this year. We can’t wait to see you again in 2019!