Going Spatial:How to handle a Spatial DS project&Building an Amazon.com for Data

Agenda:
6:30pm - 7:00pm - ODSC Intro, Food & Refreshments.
7:00pm - 7:40pm - Speaker One and Q&A
7:40 - 8:20 - Speaker Two and Q&A
8:20 - 8:40 - Networking

IMPORTANT: Please bring your photo ID and sign in at the front desk.

Speaker One: Dongjie Fan - Data scientist at CARTO
https://www.linkedin.com/in/dongjie-fan/

Topic:
Going Spatial - How to handle a Spatial Data Science project

Bio:
Dongjie Fan is a data scientist in CARTO. His background is Statistics and Urban Informatics. And His work focuses on large size geospatial data processing as well as applying statistical learning methods to solve prediction, inference and optimization problems in spatial data science field.

Abstract:
In this talk, Dongjie will talk you through how to scope a spatial data science project and share some obstacles when his team handle analytical geospatial problems in practice.

The talk will start with a project sharing including data enrichment, large geospatial data processing, statistical learning methods in spatial data science field. Also he will introduce some relevant tools for data processing and visualization and other spatial data science projects that his team has been working on.

Speaker Two: Julia Ingrid Lane, Professor at NYU’s Wagner School of Public Service
https://wagner.nyu.edu/community/faculty/julia-lane

Topic:
Building an Amazon.com for Data: Interacting with a New Data Tool

Bio:
Julia Ingrid Lane, Professor at NYU’s Wagner School of Public Service, runs the Administrative Data Research Facility, where she pushes the boundaries of cutting-edge data science for the benefit of governments and researchers everywhere.

Abstract:
Researchers and analysts who want to use data for evidence and policy cannot easily find out who else worked with the data, on what topics and with what results. As a result, good research is underused, great data go undiscovered and are undervalued, and time and resources are wasted redoing empirical work. Our vision is to build an Amazon.com for data. We invited data science teams to compete against each other to develop an algorithm capable of detecting mentions of datasets in publication text and associate further information with these mentions. We are now challenging the data science community to validate the results of the competition. The interactive presentation will demo the results and ask the audience to provide feedback. Going forward, algorithms like these will help link data to research both retrospectively – past publications without documented relationships to datasets – and prospectively – suggesting to researchers uploading their papers that they link to documented datasets that seem to be mentioned in their manuscript.

ODSC Links:
• Get free access to more talks like this at LearnAI:
https://learnai.odsc.com/
• Facebook: https://www.facebook.com/OPENDATASCI/
• Twitter: https://twitter.com/odsc & @odsc
• LinkedIn: https://www.linkedin.com/company/open-data-science/
• East Conference Apr 30 - May 3: https://odsc.com/boston