Sign up or log in to bookmark your favorites and sync them to your phone or calendar.

Friday, December 1


Intro + logistics
avatar for Wenfei Xu

Wenfei Xu

Data Scientist, CARTO

Friday December 1, 2017 9:00am - 9:10am


Baking Data: Better Data and Better Decisions
In this talk we’ll discuss the most important dataset in America. You are in the data. The data has probably had an impact on your life. However, we’ll show you that this data is broken, explain why its broken, and we’ll discuss algorithms for fixing the data. We'll try to convince you that data its raw form is often problematic and “baking” data can be important part of data-driven decision making. Output from one of the algorithms we’ll discuss is available in Carto’s Data Observatory.

avatar for Seth Spielman

Seth Spielman

Associate Professor of Geograpahy, University of Colorado Boulder
Seth is an Associate Professor of Geography at the University of Colorado and a Senior Data Scientist/Manager at Apple Maps. He’s won numerous awards for scholarly work and innovation, including the Breheny Prize for work in Urban Analytics, a distinguished scholar award from American... Read More →

Friday December 1, 2017 9:10am - 9:50am


Geo at WeWork
How and why is location intelligence important at WeWork? A global provider of coworking space, WeWork is growing at an incredible pace. With 178 locations in 53 cities and 18 countries, and doubling each year, and taking on decade+ leases, it is crucial that we take site selection seriously. In this talk, we’ll cover our initial efforts to bring geospatial thinking, tooling, and predictive models to the organization. We’ll cover some use cases, models, as well as some of the challenges of tackling geocentric data science at global scale.

avatar for Carl Anderson

Carl Anderson

Senior Data Scientist, WeWork
Carl Anderson is a senior researcher and data scientist at WeWork's new market analytics (i.e. location intelligence) team. He is the author of the book “Creating a Data-Driven Organization” (O’Reilly, 2015) and previously headed up data, analytics, and data science at both... Read More →

Friday December 1, 2017 9:50am - 10:30am


Towards a Geographic Data Science that Works for Everyone
This talk will bring together highlights from the two keynote speeches. In doing so, we’ll discuss the rise of ubiquitous spatial data, the role computers play in, and how that creates a growing set of opportunities for a Data Science focused on location, geography and space. This discussion will highlight how several of these challenges and benefits are shared across industry and academia, and how both worlds can work together to exploit synergies. Several of these ideas will be illustrated by examples from the Geographic Data Science Lab at the University of Liverpool and the work done around building a Geographic Data Science.

avatar for Daniel Arribas-Bel

Daniel Arribas-Bel

Lecturer in Geographic Data Science, University of Liverpool
Dr. Dani Arribas-Bel is Lecturer in Geographic Data Science and member of the Geographic Data Science Lab at the University of Liverpool (UK). Dani is interested in computers, cities and data. In particular, his work focuses on the spatial dimension of cities, from their physical... Read More →

Friday December 1, 2017 10:30am - 10:50am


Coffee Break
Friday December 1, 2017 10:50am - 11:05am


Supercharging Geospatial Analytics with GPU
Todd will explore the topic of GPU-analytics & their role in geovisualization. In particular, attendees will hear about how complex visualizations with massive amounts of geospatial data are an ideal match for GPUs, unlocking extreme speeds for interactive data exploration and real-time insight generation. The ability to instantly interact with billions of rows of geospatial data can be used across industries such as ad tech, energy, financial services, government, retail and service providers allowing them to quickly find anomalies and drill-down into the individual level without pre-aggregating or downsampling.

avatar for Todd Mostak

Todd Mostak

CEO and Co-founder, MapD
Todd is the CEO and Co-founder of MapD Technologies. Todd built the original prototype of MapD after tiring of the inability of conventional tools to allow for interactive exploration of big datasets while conducting his Harvard graduate research on the role of Twitter in the Arab... Read More →

Friday December 1, 2017 11:05am - 11:30am


Scaling PostgreSQL and PostGIS
Spatial data analysis workloads come in all shapes and sizes, and many
of them can be met with appropriate use of vertical scaling and job
partitioning in PostgreSQL. We will cover some common use cases and
approaches, as well as discuss the horizontal scaling options that are
available now and coming down the pipeline.

avatar for Paul Ramsey

Paul Ramsey

Solutions Engineer, CARTO
Paul Ramsey is a Solutions Engineer at Carto. He has been working with geospatial software for over 15 years: consulting to government and industry; building a geospatial software company; and programming on open source software. He co-founded the PostGIS spatial database project... Read More →

Friday December 1, 2017 11:30am - 11:55am


Painting with Data
Contrary to traditional mapping software that operates as a database paired with a map or a graphical representation, “Painting with Data’ allows users to directly manipulate the map itself instead of through abstract numbers and symbols. This creates a more intuitive way of understanding spatial data and creating spatial models, and redefines the way in which users explore and gain intuitions from spatial data.

avatar for Carlos Sandoval Olascoaga

Carlos Sandoval Olascoaga

PhD Candidate in Architecture Computation, MIT
Carlos Sandoval Olascoaga is a PhD student in the Design and Computation Group, specializing in urban computing, and data visualization. Previously, he was a research scientist at UC Berkeley, investigating the convergence of design, spatial information, data science, and social sciences... Read More →

Friday December 1, 2017 11:55am - 12:00pm


Developing Spatial Data from Free Form Text
A (quick) presentation about creating spatial data for Community Board Budget Requests.

avatar for Amanda Doyle

Amanda Doyle

Technical Product Manager, Department of City Planning
With a background in Geography and Applied Urban Science Amanda has experience with and is passionate about developing spatial data and conducting spatial analyses to inform real-world decisions. With the Capital Planning team at the NYC Dept of City Planning Amanda develops new and... Read More →

Friday December 1, 2017 12:00pm - 12:05pm


Spatial Data Science solution to Vision Zero
Discussing High Injury Network (HIN) as a powerful application of Spatial Data Science, so as to provide city officials with necessary data, maps and analysis that aids them with informed decision making. It also discusses what a few other cities are doing to develop their HIN.


Manushi Majumdar

Product Engineer, ArcGIS Hub
An NYU CUSP and Argolabs alum passionate about everything data, maps and cities, now working at Esri as a Data Science Product Engineer.

Friday December 1, 2017 12:05pm - 12:10pm


Mapping Into a Healthy and Equitable Future
Since Hurricane Maria hit the Caribbean, NYC has become a new home to evacuees, many of whom came without medicine or the means to find medical services in the city. As women of color passionate about social justice and health equity, we wanted to do something to help close this gap. As a Public Health Intern and Urban Fellow at the NYC Health Department, we don’t have a traditional GIS education - but we did have a vision of how this problem could be solved with a map. In this talk, we’ll tell you how learning to make a map empowered us to provide a quick and easy resource for our newest New Yorkers when they needed it most.


Rahani Green

Public Health Intern, NYC Department of Health and Mental Hygiene
Rahani Green is an MPA student at New York University studying Health Policy & MGMT. Through her internship on the Risk & Analytics unit at the NYC Health Dept. (DOHMH) she is helping the city better serve vulnerable populations during disasters. When not at DOHMH, Rahani is conducting... Read More →

Anali Valdez

NYC Urban Fellow, NYC Department of Health and Mental Hygiene
Originally from Bakersfield, CA, Anali Valdez recently graduated with a Bachelor of Science in Public Health from the University of California, San Diego. As a current Urban Fellow at the New York City Department of Health and Mental Hygiene, she works on creating genuine and sustainable... Read More →

Friday December 1, 2017 12:10pm - 12:15pm


Lunch Break
Friday December 1, 2017 12:15pm - 1:05pm


Geoinformatics at Internet Scale
Machine learning on spatial data is hard. This talk will look at some of the unique issues when working with this data, how Dstillery cleans and classifies this data in real time a quarter trillion times a day, and why we ended up building two parallel spatial featurizers to maximize the utility of geo data in our machine learning stack.

avatar for Peter Lenz

Peter Lenz

Senior Geospatial Analyst, Dstillery
Peter Lenz is a geographer and data scientist with Dstillery, a data insights company that builds behavioral profiles from billions of observations of human behavior every day using AI. Specializing in geographic big data and data storytelling, Peter can dive anywhere into the data... Read More →

Friday December 1, 2017 1:05pm - 1:30pm


Inferring Human Mobility Patterns from Mobile Phone Data
In this talk, Dr. Shan Jiang will discuss geo-computing, modeling and visualization methods to extract from massive and passive spatiotemporal mobile phone data to advance understanding of human mobility in urban environments. She will provide a range of examples from Boston to Singapore, to demonstrate the usage of big data for travel behavior modeling and analysis, which will allow cities to monitor and forecast travel timely and efficiently, and make informed decisions on sustainable infrastructure planning and investment.

avatar for Shan Jiang

Shan Jiang

Postdoctoral Associate, MIT DUSP
Dr. Shan Jiang is a Postdoctoral Associate in DUSP at MIT, where she received her PhD from the Urban Information Systems group and Masters in Transportation and City Planning. Her research interests lie in the fields of Big Data Analytics, GIScience, Computational Social Science... Read More →

Friday December 1, 2017 1:30pm - 1:55pm


Measuring Spatial Associations – with Applications to Health Geography
The nuances of statistical regression modelling with spatial data will be discussed, and solutions through “spatial” regression modelling options will be summarized. A particular solution for a public health issue will then be illustrated.

avatar for Glen Johnson

Glen Johnson

Associate Professor, City University of New York School of Public Health
Dr. Johnson is an Associate Professor in the Department of Environmental, Occupational and Geospatial Health Sciences at the City University of New York (CUNY) School of Public Health. He has a Ph.D. in Quantitative Ecology, a M.A. in statistics and a M.S. in Ecology, all from Penn... Read More →

Friday December 1, 2017 1:55pm - 2:20pm


Data, Density and Technology – Perspectives on Last-Mile Logistics
As cities grow in size, density, and complexity, companies need to re-think their distribution strategies to operate profitably in these constrained environments. In this talk, I will discuss how our team at the MIT Megacity Logistics Lab is leveraging different sources of data, including geo-spatial datasets, to better inform strategic and planning decisions in urban logistics. At its core, logistics is about moving goods between different locations. Thus, geo-spatial data plays a key role in enabling better decision-making. I will present several case studies to illustrate the combined use of logistics planning methods, data science algorithms and varied sources of data to support decisions in last-mile logistics.

avatar for Daniel Merchán

Daniel Merchán

Ph.D. Candidate, MIT
Daniel Merchán is a Ph.D. Candidate in Engineering Systems at the Massachusetts Institute of Technology. His research focuses on logistics operations in large urban areas. Specifically, Daniel explores how varied data sources can be leveraged to inform last-mile strategies and operational... Read More →

Friday December 1, 2017 2:20pm - 2:45pm


Coffee Break
Friday December 1, 2017 2:45pm - 3:05pm


Identifying and categorizing business districts using Census LODES data
Both practitioners and academic researchers have a keen interest in understanding how employment is spatially distributed throughout metropolitan areas. In this paper I use high-resolution Census LODES data to document regularities in the spatial distribution of jobs and residents. I show that unlike residents, who form a continuous surface covering most parts of each MSA, jobs have a bimodal spatial distribution. Most Census blocks contain no jobs whatsoever, while a small number have extremely high employment densities. I then introduce an algorithm to identify and classify contiguous business districts based on the densities of employment and population in each block.

avatar for Robert Manduca

Robert Manduca

PhD Candidate in Sociology and Social Policy, Harvard
Robert is a PhD student in Sociology and Social Policy at Harvard University. His research focuses on local and regional economic development, trying to understand why some cities and neighborhoods prosper while others are left behind. Prior to beginning his PhD he received a Master's... Read More →

Friday December 1, 2017 3:05pm - 3:25pm


Addressing city-scale optimization problems of ride and vehicle-sharing
In this presentation, I will show how analyzing data of millions of NYC taxi trips led us to create a powerful network-based optimization approach for an optimal management of a fleet of vehicles serving a city's mobility demand.

avatar for Mohammed Vazifeh

Mohammed Vazifeh

Lead data scientist, MIT Senseable City Lab
Moe Vazifeh is a postdoctoral associate/lead data scientist at MIT Senseable City Lab. He is also a cofounder of a Vancouver-based startup, Q.I. Leap Analytics. His interests are centered around mining and modeling complex patterns in large-scale spatio-temporal urban data as well... Read More →

Friday December 1, 2017 3:25pm - 3:50pm


Open Mobility with Valhalla
Valhalla provide open source routing software. It includes routing and navigation software with a design tailored to make it flexible and extensible. Costing is dynamic and computed at run-time allowing many different routing options and modes. Valhalla also includes tools for analysis like time-distance matrix, route optimization, and isochrones - each using the dynamic costing methods. In addition, recent work has been done to create persistent road segment identifiers (called OSMLR) that can be used along with map-matching to associate custom data to roads. This paves the way for custom costing methods to integrate user data into routing and mobility applications.

avatar for David Nesbitt

David Nesbitt

Software Director, Mapzen
Dave is technical lead of the Mobility Team and lead developer of Valhalla routing and navigation software. Prior to joining Mapzen in 2015, he was Chief Architect for MapQuest's' transportation systems: supporting routing, navigation, and traffic. At MapQuest, he designed, developed... Read More →

Friday December 1, 2017 3:50pm - 4:15pm


Geosilhouettes: putting the "Geo" back in Geodemographics
Community detection and analysis is a fundamental concern of spatial data science. But, many of the metrics we use to characterize how well an observation fits into a cluster do not consider spatial information about the observation and its context. Instead, I suggest a new family of measures that are simple in concept and powerful in application. I'll show an application of these new measures: together, we'll examine how some neighborhoods can be strongly distinct even when they're right next to one another, and some can flow seamlessly into one another.

avatar for Levi Wolf

Levi Wolf

Lecturer in Quantitative Human Geography, University of Bristol
My name is Levi John Wolf. I am a lecturer in Quantitative Human Geography at the University of Bristol’s Spatial Modeling Group. My dissertation focused on the spatial dimensions of electoral change, improving measures and models that can be used to detect gerrymandering. Now... Read More →

Friday December 1, 2017 4:15pm - 4:40pm


Un-Conference Session
Friday December 1, 2017 4:40pm - 5:15pm


Visualizing Transit Frequency
Transit frequency matters -- so how do we talk about it? This talk will explore a existent strategies for communicating about transit frequency and will introduce TransitFlow, a new experimental, open-source software tool for generating animated transit maps from GTFS data.

avatar for Will Geary

Will Geary

Masters of Science Student, Columbia University
Will is a second-year graduate student pursuing an M.S. in Data Science from Columbia University. He currently consults for the United Nations Department of Peacekeeping on spatial analysis and geo-visualization. Previously, Will interned on the mobility team at Mapzen, where he developed... Read More →

Friday December 1, 2017 5:15pm - 5:20pm


Spatial-Data Cupcakes: A Discussion On Responsibility
A discussion on responsibility for those creating and presenting spatial data in the age of mass information consumption.


Phillip Martin

VP Data, SumAll
Data Scientist, Geophysicist, R-user, Maker of Things

Friday December 1, 2017 5:20pm - 5:25pm


cartoframes: A Python interface for CARTO
cartoframes is a new Python package for integrating CARTO into data science workflows. It allows you to build CARTO maps, read/write/query datasets, perform spatial operations, and augment data from Data Observatory. It also easily ties into the Python ecosystem because it speaks the language of the de facto data science standards pandas, Jupyter, matplotlib, and SQL/PostGIS.

avatar for Andy Eschbacher

Andy Eschbacher

Data Scientist, CARTO
Andy is a Data Scientist at CARTO, where he builds new tools and analyses into CARTO's platform, helps clients solve data science problems, and explores new problems in open spatial data science. He lives in New York with his wife and son.

Friday December 1, 2017 5:25pm - 5:30pm


Beyond Our Silos: Towards Spatial Data Science
In this closing keynote, Julia Koschinsky and Stuart Lynn are poking fun at our tendency to work in silos and conclude with projects that integrate spatial analytics and data science. We invite you to join our forums to extend the exchange between these two communities.

avatar for Julia Koschinsky

Julia Koschinsky

Research Director, Center for Spatial Data Science, University of Chicago
Julia Koschinsky is the Research Director of the Center for Spatial Data Science at the University of Chicago and has been part of GeoDa team for over ten years. She has been conducting and managing research funded through federal awards of over $8 million to gain insights from the... Read More →
avatar for Stuart Lynn

Stuart Lynn

Head of Research and Data,, CARTO

Friday December 1, 2017 5:30pm - 6:00pm