Tag: Data Science

The NYC TLC Factbook is a public-facing PowerBI dashboard that showcases charts, maps, and key metrics on various data and policies, including trip counts, electric vehicles, driver pay, utilization rates, and driver demographics. The underlying data for the dashboard includes publicly available information, such as trip data, as well as more sensitive data that is kept confidential to protect driver privacy. The Data Analytics team, part of TLC’s Policy Division, invites members of the public to an interactive presentation that offers an in-depth look at the analysis behind the dashboard, as well as how it helps evaluate and monitor critical policies

In this presentation, we will introduce our recently developed urban heat portal for NYC. We will demonstrate how each layer in the heat portal is prepared. We used a variety of resources to prepare urban heat layers. They include:

  • Satellite data from Landsat 8 and 9
  • Weather Station Data from Visual Crossing
  • A variety of layers from City’s open data including Land Cover (Tree cover and permeable surface cover), NTA, Parks, buildings.

In this presentation, you will learn about the science of urban heat and the methods used for producing multiple layers that are publicly available for download. We will explain the workflow and the models that are developed to create Mean Radiant Temperature, Air Temperature, Heat Index, and an overall Outdoor Heat Exposure index.

This event will be hybrid.

For in-person attendance at Hunter College, please RSVP in advance using the “Going” button below, as front desk security will need a list of attendees in advance. Please arrive 15 minutes in advance to get a pass.

For virtual attendance, please RSVP using this link.

Have you ever tried working with the 311 dataset available on Open Data? Notice how it’s very, very big? Join us for our presentation, where we demonstrate how we use this dataset. Nisuka Williams, a recent graduate of Columbia University, will share how to create a webmap using Open Data APIs. Using HTML, CSS, and JavaScript, this presentation will demonstrate ways to filter the data in the front end to display the data. No prerequisites are required to attend, though knowledge of front-end coding is a plus. If you’d like to try this yourself, all the code is available on GitHub.

Character showing ways to reduce CO2 emission through carbon tax, credit and eco investing.

Join this interactive demonstration of DataKind’s Economic Opportunity Datascape (EO Datascape), a platform dedicated to enhancing financial well-being and economic opportunity through the power of data.

Leveraging nearly 10 public data sources, this session will showcase how the EO Datascape can help stakeholders, from Community Development Financial Institutions to nonprofits and policymakers, access comprehensive, geographically standardized, financial and economic data to make informed decisions and offer tailored services to better serve communities. The EO Datascape provides users with the ability to customize their experience by selecting key economic and financial indicators across diverse themes and public datasets—including socio-economic indicators, small business metrics, banking and investment data, and housing data—enabling them to preview and download a tailored dataset at the 2020 U.S Census tract boundaries.

During this event you’ll explore how this tool can support data-driven decision-making and unlock new avenues for inclusive economic opportunity across New York City.

Open Data Week 2025 - Open Data Lightning Talk Showcase, Friday March 28 6 to 7 pm, 2 Metrotech Center, Downtown Brooklyn

Come to the NYC Office of Technology & Innovation offices on Friday, March 28 at 6PM for a lightning talk showcase, featuring open data use cases about the human brain, the environment, web domains, trash cans, and film locations. Each of the presenters will have a few minutes to showcase their work, and this will be followed by an audience question-and-answer period.

The presentations:

Arianna Zuanazzi – Exploring Child and Adolescent Mental Health in NYC: Insights from the Healthy Brain Network Open Dataset
The Healthy Brain Network (HBN) is a large-scale open science initiative of the Child Mind Institute which releases multimodal datasets capturing a broad range of clinical psychopathology in children and adolescents based in NYC. For this event, we will briefly introduce the openly available phenotypic and neuroimaging HBN datasets and present data and visualizations that illustrate socio-economic status, neighborhood crime and safety, school risk, and mental health in NYC children and adolescents. We will then explore how the HBN dataset can be combined with datasets from NYC Open Data, such as air quality and pollution data.

Surbhi Agrawal – Using Open Data to Map Regional Resiliency Risk and Assets
Sasaki Associates has developed a data platform to empower communities in mapping and understanding regional risks from natural hazards and stressors, alongside identifying critical community assets. Using open datasets, this platform visualizes data such as expected losses to populations, infrastructure, and agriculture, enabling informed decision-making for resilience planning.

Frank Noirot – Mapping the trash can landscape in NYC with QGIS and Open Data
I wondered how far people had to walk to the nearest litter basket anywhere in NYC, and thanks to NYC Open Data I was able to make a map that does just that, even though I’m no data scientist! I wrote about my process in making the map. I want to encourage others who have questions about the environment they live in to take a search through NYC Open Data to see if there is a data set that fits their topic. They might be pleasantly surprised with what they find.

Bailey Kane – Enriching NYC Open Data for .nyc Websites
All .nyc domain registrations since the beginning of the program are logged in a NYC Open Data dataset. However, actual use of those registered domains is not tracked. I was curious how people are using .nyc domains, so I started AllOf.nyc to explore all registered .nyc websites by expanding upon the data offered in the NYC Open Data dataset.

Cory D. Reeves – Simulating Soundscapes: NYC Open Data for Amplified On-Site Film Location Selection
Filming in New York City presents unique challenges—permitting, logistics, and environmental sound control measures during production are some examples. Our award-winning prototype from Autodesk University 2024’s Design & Make Conference, Dynamo Day Hackathon leverages NYC Mayor’s Office of Media and Entertainment (MOME) structured film permit datasets within Autodesk Forma’s AI-powered noise analysis engine, creating real-time feasibility assessments to support film location selection. This solution enables production teams to evaluate potential filming sites more in-depth, and to-scale within dynamic, virtual 3D space before more costly on-location mobilization of film crews and production staff.

Make a night of it! Before the event, consider checking out the Data Through Design exhibition at BRIC (647 Fulton St, Brooklyn), which is a 10-15 minute walk from this event. Afterwards, join us for a happy hour a few blocks away at Sound & Fury Brewery and Kitchen (141 Lawrence St, Brooklyn).

The Workforce Strategy Team in the Human Capital division of the Department of Citywide Administrative Services will present on the production of the Workforce Profile Report (WFPR). The WFPR is an annual summary of employee data reflecting the City of New York’s municipal workforce across 72 agencies. The team will give a broad overview of the collection of the roughly 4 million entries of city employee data across 10 years, the data processing, and the final production of our Workforce Profile Report Shiny App.

Presenting will be Ruchika Sah, Feba George, and Manny Merino from the Workforce Data Science team at the Department of Citywide Administrative Services. This event welcomes users at all levels of expertise. Anyone with an interest in large scale data projects, R programing or data processing is invited to attend. Familiarity with programing whether in R or another language such as Python is recommended. Participants will learn about the processes involved in taking this data into a final product and can ask questions involving the project or suggest improvements.

COVID-19 changed people’s lifestyles all over the world. This event will focus on analyzing resident housing property sales data in New York City from 2019 to 2023, before, in, and after COVID periods. By examining trends in sale prices, property characteristics, and neighborhood differences, this analysis aims to uncover key insights into the residential real estate market. Furthermore, machine learning techniques will be applied to predict property values and classify neighborhoods based on various factors such as location and building type. An end-to-end data pipeline process will be demonstrated in this talk (data collection, wrangling, visualization, feature engineering, machine learning modeling) via the python notebook.

Join this event to learn from NYC Emergency Management (NYCEM) about their role coordinating citywide emergency planning and response for all types and scales of emergencies, and how they use 311 data in both the response and recovery cycles of a disaster.
This virtual presentation will explore:
– The types of reporting products produced at NYCEM for different disaster cycles.
– A technical overview of our data collection process and data pipeline.
– The important role 311 data plays in different cycles of an emergency.

Reflective roof colors reduce roof temperatures, internal building temperatures, the Urban Heat Island Effect , and carbon emissions; improve air quality; and extend the lifespan of rooftops and HVAC equipment. This project, conducted by John Hocknell, a student at Hunter College, uses machine learning to detect these cool and warm rooftops, and use that information to assess potential energy savings.

This work is inspired by the NYC CoolRoofs Initiative to reduce NYC’s carbon footprint by painting rooftops white.

Open Data Week 2025 at Cornell Tech, featuring sessions on NYC Open Data and academic research from 5:00-7:30 PM on Wednesday, March 26

Join us for an exciting set of back-to-back presentations featuring Cornell Tech researchers and practitioners as they share their real-world applications of NYC Open Data. This session offers a unique opportunity to explore how open data is being leveraged to address urban challenges, improve decision-making, and drive innovation across a variety of fields. Participants will gain valuable insights from experts who are actively shaping the future of NYC through data-driven solutions.

This event is part of an Open Data Week series hosted by Cornell Tech— learn more below!

Presentations:
– The ABCs of a PiTech Fellow: Artificial Intelligence (AI) & Natural Language Processing (NLP), Block Party & Community Boards
Breanna Green, PhD Candidate, Information Science, Cornell Tech

– Data-driven analyses and optimization of 311 systems: Applications to NYC Parks
Zhi Liu, PhD Candidate, Operations Research and Information Engineering, Cornell Tech

– Data analysis and modeling of public building construction in New York City
Sara Venkatraman, Senior Research Associate in Statistics, Weill Cornell Medical College

– Democratizing Policy Counterfactuals with AI: A deep dive into Local Law 97, NYC’s groundbreaking law to cut carbon emissions in its largest buildings
Vianney Brandicourt, Urban Tech Fellow, Cornell Tech

– Analyzing the effects of congestion pricing using Open Data
Nikhil Garg, Assistant Professor, Cornell Tech

– Predictive Maintenance for NYC Subway Lines
Atmika Pai, MS Candidate, Information Systems, Jacobs Technion-Cornell
Bhoomika Mehta, MS Candidate, Information Systems, Jacobs Technion-Cornell

– SenTree: Leveraging NYC Open Data to predict urban tree health
Rishabh Surendran, MBA Candidate, Johnson Cornell Tech
Shubham Arya, MBA Candidate, Johnson Cornell Tech

– – 
This event is part of an Open Data Week series hosted by Cornell Tech on Wednesday, March 26 from 5-8pm. We’d love for you to join us for both sessions— though it is not required! We’ll kick off at 5:00 pm with a hands-on Discovering NYC Open Data class from the Open Data Ambassadors, where you’ll learn the fundamentals of NYC Open Data. Following that, at 6:30 pm, Cornell Tech researchers and experts will discuss their real-world applications of open data, during Open Data in Action: Driving Academic Research and Government Collaboration at Cornell Tech. Join us for a post-event happy hour next door at Anything at All!

There are many easy ways to get to Cornell Tech, located on Roosevelt Island. For maps and directions see here.