Benjamin Leinwand, Vice President, NYC Chapter
In March 2013, New York City passed the Open Data Law, mandating that all public data be made freely available on a single web portal. Since 2017, the NYC Open Data team at the Office of Technology and Innovation has coordinated Open Data Week, a festival of community-driven workshops, seminars, and art exhibits celebrating publicly available data sets across the city over one week.
March 2026 marked the 10th annual Open Data Week. To celebrate, the New York City Chapter hosted a public event, “A Treasure Hunt Through NYC Open Data,” at Google’s Chelsea office, with assistance from the Open Data team.
The session featured a series of data-driven prompts that guided attendees through unique statistical signatures in NYC Open Data, covering taxis, bicycles, schools, and complaints. Participants solved progressively difficult analytical questions, from simple lookups to cross-referencing across data sets. After each question, a panel of Google and New York City Chapter experts presented a bite-sized lesson on related statistical concepts: distributional thinking; outlier detection; hypothesis testing; nonlinearity; and difference-in-differences. The session culminated in a final puzzle—identifying the hidden theme connecting all questions and answers.
About 35 people participated, including attendees from as far away as Chicago. Several remarked that answering such questions would have been difficult just a few years ago, but large language models now enable them to leverage diverse tools for complex analyses across disparate data sets. The experience prompted thoughtful questions: “Does this result support the idea that statistics can tell us anything?” and “Where do we draw the line between careful analysis and p-hacking?”
Though the secret theme proved challenging initially, attendees ultimately solved it through discussion.
Participants reported that the program encouraged them to think deeply about how data is generated and collected, and how context and domain expertise influence analysis beyond rote calculations.
We see this format as a promising pathway to engage the broader public in data science and expose them to statistical concepts motivated by topics in their daily lives. NYC is hardly alone in hosting an open data platform; all 10 largest US cities maintain open data portals, and even smaller cities like Albuquerque and Winston-Salem offer publicly available data. This approach gives a wider audience—including those skeptical of data science—practice with new, accessible tools while demonstrating how careful thinking about a problem leads to deeper understanding.
If your organization would like to adapt this event template, email Benjamin Leinwand.
Data Portals Throughout the US
Leave a Reply