Look to the recent past for signals of future growth.
A company’s store locations reflect its overall site selection strategy. If your strategy is similar, look to them.
Learn how to sample addresses from Open Addresses in Python with Hex.
I thought I wanted to be an engineer for a Formula One team (kind of ridiculous in retrospect), so at the time I majored in mechanical engineering. Long story short, I was programming every night instead of doing my mechanical engineering homework, so I eventually decided to leave to find a job building software.
Leverage spatial indices to make joining POI data simple.
Sure, the food is important but who doesn't want to pair good food with an epic view? OpenTable now lets you do so!
Fall is approaching. If you want to see the leaves change but can't get up to Vermont or NH (or even Upstate) to peep them, where should you head? In this tutorial we use data on NYC maple trees to identify potential neighborhood leaf-peeping spots. We cluster trees and then turn the clustered points into polygons.
By automatically including Supercharging stops along your driving route Tesla not only removes friction from the experience of driving one, but opens up the opportunity to capture even more of your money by defaulting drivers to Tesla-owned chargers. This is just the tip of the iceberg in terms of the potential for Tesla...
Maps on real estate sites like Realtor.com usually have great data layers. But the map is usually the only way to interact with the data.
Iggy's contextual data now covers 94% of the US population!
If your data kit doesn't include contextual data about a location, you are going to miss a lot of the important factors that impact price. You could be leaving money on the table, or taking too much off. Either way, there's alpha to be had.
Select a geographic area, choose the data points you want, and a world of data is yours to build with. It can go right into your stack and be used to build better products from models to programmatic SEO pages.
Zillow has a hard-to-find 'waterfront homes' filter. But it's not really accessible to home searchers.
My background is mixed. I was an English major originally, and pivoted to environmental science and biology later in college. In graduate school, I got interested in quantitative / computational ecology and testing ecological theory using historical observational data, experiments, and computer simulations. I worked as an applied ecologist at Northern Arizona University for a couple of years, before co-founding a company called Conservation Science Partners in 2012. We had a tremendous amount of success over the last 10 years, but I was feeling ready for a change in focus.
The first post in a series highlighting place data in the websites we use and love. This piece covers Airbnb's category search.
As I was finishing my PhD, I did Insight Data Science and got hired at Airbnb where I hoped to use geospatial data to work on host growth or something. I was working on the host team as a Data Scientist and I realized that we didn't have any concept of the “context” of our listings… we knew a lot about the listing and its specific characteristics but we didn't really have a way to understand what was nearby. That matters because if you know what’s nearby you can market listings differently (which is sort of what Airbnb is (finally) doing w Categories), you can price more accurately, and you can drastically improve search. That became really compelling to me. I tried to work on an internal project there, but it didn't get a lot of support. So eventually, I decided to leave Airbnb and start Iggy to solve this challenge.
I am an astronomer by background - I did a PhD in astronomy. I studied the evolution of the galaxy since the Big Bang. Very different from what I do today. My interest in astronomy was motivated by the discovery process. You get to discover something interesting that no one's ever discovered before. But as I was going through that, one thing that I realized - and it led to my transition to data science and ultimately to product - was that I liked working on these sorts of big questions, but I wanted to do so in a bit more of an applied way.
I started with a design degree from SF State, doing graphic and web design for a small agency. I did a bit of print work as well as creating different kinds of collateral marketing and conferences.
Getting geospatial data into ML models is hard. One reason for this is that there are few “canonical” sources for geospatial data at scale. Open Street Map (OSM) is understood as one such source for rideshare, but its potential in real estate use cases is widely unexplored. In this post we discuss some of the quality control/QC work we do to improve off-the-shelf OSM data and measure the impact of that work via a real estate pricing model benchmarking test.
Virtually all companies are in the same boat: it's way too hard to innovate their products when it comes to location data. The few who can leverage geospatial data can innovate in truly game-changing ways.
This is a part of a series of posts introducing team Iggy. Meet Alex Malokin, Data Scientist and transportation expert!
This is a part of a series of posts introducing team Iggy. Meet Annie Iezzi, Chief of Staff!
Iggy's vision is to make data about the world accessible so that our customers can build great products, models and analyses. But the world is constantly changing and there is no one single best source of all geographic information, so how do we do this? We consider checking and improving data quality a core part of our work.
Augmenting your data with understanding around a place leads to better analysis, models and products. But really understanding place at a granular level is tough. Iggy makes it simple so all you have to do is plug it into your data analysis, model, etc.
Iggy Open Data, a site that hosts various datasets our team’s found useful along with detailed documentation about the attributes, coverage, licensing, and source.
Tune in to hear from Anne about: Motivations for iggy, based on our CEO Lindsay's experience as a data scientist at Airbnb, How we build our core/canonical datasets,Lessons learned from ingesting massive datasets with complex geometries (I.e. FEMA flood data),How iggy can help w health outcomes, Navigating the pre-PMF journey, Why Anne thinks machine learning on geospatial data is particularly cool.
This is the first in a series of posts introducing team Iggy. Meet Anirudh Shah!
Our mission at Iggy is to make information about the world accessible. We’ve taken our first steps toward this over the last few months. Starting today you can query more than 175 geographic datasets using the Iggy API.
My version of better is founded on usability as a first principle. This means building a company from the ground up that is devoted to making geospatial data actually usable to the folks who are building the products and experiences that are shaping our lives: developers.
Iggy makes data about the world more accessible