Anomaly Detection in The Opioid Files

New York User Group
Wed, Jun 24, 2020, 12:00 PM (EDT)

About this event

For the first virtual event of the New York Dataiku user group, Patrick Masi-Phelps (Lead Data Scientist at Dataiku) will present an anomaly detection project in Dataiku DSS, based on the data in The Washington Post’s The Opioid Files.

Anomaly detection is a step in data mining that identifies data points, events, and/or observations that deviate from a dataset's normal behavior. Anomalous data can indicate critical incidents, such as a technical glitch, or potential opportunities, for instance a change in consumer behavior.

This presentation will be followed by a discussion to share feedback and best practices on anomaly detection with DSS.

Join the New York user group to be informed of upcoming events and chat with New York based DSS users!

We're wondering:

1)What's your experience with Anomaly Detection?

2)Any best practices to share, or pitfalls to avoid?

3) What is the most interesting dataset you have ever worked with?

Answer here!

Please note: The dataset that is used in this presentation is the publicly available data presented by The Washington Post. 


  • Patrick Masi-Phelps

    Patrick Masi-Phelps


    Lead Data Scientist

    Patrick Masi-Phelps leads a team of NYC-based data scientists at Dataiku. He has worked closely with companies in aviation, banking, insurance and pharma - helping them use Dataiku DSS and develop data science projects. Before joining Dataiku, Patrick studied math and economics at Wesleyan University and was most recently a fellow at NYC Data Science Academy. Patrick is always keeping up wit...

    Read More
  • When

    Wednesday, Jun 24
    12:00 PM - 1:00 PM (EDT)


  • Community Manager

    View Profile
  • Tom Brown

    Tom Brown

    Director, Digital Projects & Analytics



    Head of Data & Actuarial Science

    View Profile