Newer posts are loading.
You are at the newest post.
Click here to check if anything new just came in.

March 06 2012

Why Uber's data fascinates a neuroscientist

Uber logoMatching cars for hire with people who want to get places may not be rocket science. But a background in neuroscience couldn't hurt. Where 2012 speaker Bradley Voytek (@bradleyvoytek) has taken his experience as a neuroscience researcher to buzzy car-service company Uber, where he sees similarities between the connections in an urban landscape and those in the brain. Voytek's role with Uber involves figuring out how to make sense of and how to apply the massive amounts of data that the car service and its customers generate. Wrangling that data can help Uber match up cars and passengers more quickly — and has some other promising possibilities, too.

What are you learning from Uber's real-time analytics?

Bradley Voytek: A lot of people think that Uber is just a car service, and that we figure out where to pick people up and where to take them. But as a cognitive neuroscientist, of course I'm interested in human behavior. To me, the coolest thing about what we can learn when we take a deeper look at Uber's data is how people move around a city. We get a little glimpse at how people flow, what neighborhoods are connected, where people go to party on weekend nights. It's fascinating.

What are some of the things you might do with that data?

Bradley Voytek: One of the great things about working for a startup like Uber is spit-balling ideas, talking about possibilities. While I can't talk specifically about what else we might be able to do for our users using their data in terms of the business, you could easily imagine a lot of possibilities. My personal favorite "out there" idea is to ask drivers if they'd be willing to have a multi-sensor attached to their car that sampled air quality, temperature, and other environmental factors. We could make it so our driver partners are involved in "citizen science" in a sense.

How do you make the connection between incoming data, analysis, and business response?

Bradley Voytek: Managing supply is a critical issue. If we have a lot of users wanting a car, but we don't have enough cars on the system, then our wait times increase and the chance of any one user getting a car decreases. This provides a less optimal user experience. So, if we start to see an unexpected increase in demand, we can have our ops team start calling to get more drivers on the system, for example. When we launch in a new city, we need to know where people want us. So, we take a look at where people have been checking us out and look for hotspots of anticipatory activity in a city to make sure we're addressing our eager riders.

Where Conference 2012 — O'Reilly's Where Conference, being held April 2-4 in San Francisco, is where the people working on and using location technologies explore emerging trends in software development, tools, business strategies and marketing.

Save 20% on registration with the code RADAR20

Have you opened up Uber's data or compared it with other geo databases to learn new things?

Bradley Voytek: We anonymized some of our data a few months ago for a data visualization competition to see what people could do with it, but so far we haven't shared our data too broadly. I've been working hard to mash up our data with other public data though, to see if I can uncover something cool. For example, a few months back I wanted to see if I could predict which neighborhoods in San Francisco had the most rides based on some demographic information. At first I thought the obvious answer would be population density, but what we see is that people don't always take a car from their home, they take it for business or pleasure, from one social location to another. So, I used public crime data as a surrogate measure for the amount of "activity" in a neighborhood, and that predicted rides much better than population density.

How do you think your neuroscience background shapes the way you do your data work at Uber?

Bradley VoytekBradley Voytek: It's a two-way street. My neuroscience background has influenced the way I think about and work with data: I come from an electrophysiological background. I work with time-series data, so I tend to think about our data in terms of how metrics change over time. I think about cities as a series of connected nodes in a city-wide network, which is analogous to how I think about the brain: a complex network of connected neuronal hubs.

But I've also taken some of the visualization and analytic techniques I learned at Uber back into my neuroscience research, and I've even begun looking at geolocation data in some of my side projects. Specifically, my wife and I created a website with some help from my friend and Uber's head of engineering, Curtis Chambers, called This paper is currently under peer review, but the main idea was to see if we could "map" relationships between neuroscientific topics spread across more than three million peer-reviewed publications. It's an incredibly complex field, spanning psychology, biology, chemistry, medicine, computer science and artificial intelligence, and so on. There's too much data. As I learned new tricks about data visualization and graph theory at Uber, I was able to go back to this project and improve on it. We're trying to do two things: First, aggregate all of these disparate scientific findings into something more digestible (which is at the heart of big data and data visualization), and second, see if we can't learn anything new from these data (again, a core part of big data). So, instead of just visualizing relationships between topics, we're looking at the statistical properties of those 500,000 connections to try and find places where (statistically) connections should exist, but do not. I'm calling this "semi-automated hypothesis generation."

You ran out of time during your Ignite presentation while you were discussing an idea about correlating reaction times (of a brain task, via your work with Lumosity) with automobile accidents. Can you tell us what you found?

Bradley Voytek: Okay, this is very preliminary, but obviously exciting. The data I'm looking at with Lumosity measures attention and cognitive control. They've shared tens of thousands of users' worth of data with me from all over the world. After learning geolocation at Uber, I began to think about what kinds of location-based questions I could answer with the Lumosity data. Given that we're looking at attention and cognitive control, I thought maybe less "attentive" states would have a slightly increased risk of car accidents.

And that's what I'm finding, but with the huge caveats that these data are preliminary, not peer-reviewed, and, of course, complex in that there are a lot of potential factors that may explain the apparent relationship between the Lumos attention measure and car accidents. As I've gathered more state-level data, you start to see interesting correlations among factors like state, age, income, health — all with the usual caveats about interpreting correlations as causation.

Voytek's Ignite presentation is available in the following video.

October 24 2011

Four short links: 24 October 2011

  1. Tangle -- open source Javascript library for creating slider-type widgets in web pages, with built-in updating of other web elements. This is fantastic for exploring "what-if" scenarios. Check out the demos.
  2. Location-Based Security -- The researchers have created a customized version of Android controlled by a “policy engine” on a server. The Android devices use Bluetooth and near-field communications infrastructure to determine the location of the user, and what level of access they have to what kind of information, as well as the level of functionality of their device. Security, however, is defined not by what you can do but by what the bad guys can't do, and this seems very dependent upon external triggers (wifi and bluetooth) which are readily faked.
  3. Google Puts a Price on Privacy -- I'd never realized before that https and referer information are only loosely compatible: Google has to go to efforts to restore referer information because browsers don't pass the referer tag on when going from https (e.g., to http (e.g., your web site).
  4. Rocketcharts -- open source Javascript financial charting library.

Sponsored post
Reposted bynesraitMrCoffetimmoemrocznakatiabananananabananananabanananana

September 09 2011

ePayments Week: Who will own your mobile wallet?

Here's what caught my attention in the payment space this week.

What's in your mobile wallet? (MMT) hosted a mobile payments conference in New York this week that brought together a diverse group of people from a few points along the value chain, including payment providers, credit card issuers, and consumer marketing services. With the mobile wallet at the center of the conversation, three questions recurred throughout the event:

  1. Who will control the mobile wallet?
  2. How do you get people to adopt it?
  3. What new features will a more intelligent wallet enable?

First, whose name will be on it? Google Wallet owns a tremendous amount of mind share given that virtually no one actually has it on their phone yet, and few people, even those in the conference's crowd, have any idea when it will reach wider distribution. David Schropfer of the Luciano Group, author of "The Smartphone Wallet — Understanding the Disruption Ahead," suggested that familiar brands will be key in helping consumers switch from a physical wallet to a digital one. "People don't like to make two significant changes at once — how they pay and what they pay with." If they're switching from plastic cards to their mobile phones to make payments, consumers will almost certainly want a brand they trust with their money involved, someone like Visa or MasterCard. But while credit cards are trusted, those companies so far have had little success in promoting their own digital wallet solutions. They're more likely to be an option on some other branded mobile wallet from Google, PayPal, Amazon, or even Isis.

How Google Wallet works

The second key question on everyone's mind was how to get people to use the services, whether that's how to get them to notice and download an app, how to get them to favor the app, or how to get them to respond to things the app wants them to do. Google again appears highly favored, given the number of times every day the average person interacts with the brand's services. PayPal or Amazon would seem to have a higher hurdle, given they have fewer touch points with consumers, but both have more than 100 million user accounts through which they could extend offers.

In terms of getting users to make transactions, it's clear that the mobile wallet of the future will have a lot more "pull" to it, as opposed to the "push" nature of our physical wallets. I wrote recently about Placecast, which uses geofenced locations to trigger alerts when opted-in subscribers enter a particular zone. I was interested to hear from Placecast's Blair Swedeen at the MMT conference that of the consumers who took action on offers, only 27% did so that day, with another 35% responding up to three days later — a longer shelf life than one might have expected for location-triggered offers.

Opinions differed as to whether or not mobile payments would replace cash. Tom Meredith of P2PCash suggested it wouldn't replace simple cash transactions, and Schropfer showed data indicating that while debit card usage had replace plenty of credit card usage, cash purchases remained fairly steady in the US. The story may be different in other countries. Schropfer also presented a slide showing a dramatic rise in the volume of Safaricom's M-PESA text-message payments in Kenya from 2007-2010, while cash usage in the country dwindled significantly. This suggests that the M-PESA payments have indeed replaced cash payments when available for small, simple transactions like taxis and bus rides.

There is no shortage of answers to the third question — what features will a more intelligent wallet enable? Certainly, those features will include the ability to set limits on payments (where and how much), better ways to prevent fraud (since phones offer a variety of ways to confirm identity), and obvious marketing tools like location-smart marketing and automated rewards and loyalty programs. Schropfer suggested another feature: retailers steering customers to their preferred method of accepting payment. In the physical world, retailers are pretty much at the mercy of consumers' payment options. But in a smart-wallet purchase, merchants will have a greater ability to dynamically offer discounts based on a consumer's choice of payment. A company might offer a bigger discount if you pay with, for example, PayPal, if the merchant can redistribute that value within the PayPal system without paying any fees. The retailer might offer a smaller discount with Visa and none at all with American Express since those options cost the merchant more. And, of course, those conditions might vary from day to day as different payment providers offer different incentives.

In short, there will be far more options and capabilities with a mobile wallet. But it also seems clear that, as often happens, a technology that enters the scene promising to make life simpler winds up making it more complicated.

Android Open, being held October 9-11 in San Francisco, is a big-tent meeting ground for app and game developers, carriers, chip manufacturers, content creators, OEMs, researchers, entrepreneurs, VCs, and business leaders.

Save 20% on registration with the code AN11RAD

Pew survey: One quarter of US adults use location services

About a quarter of Americans use the location-smart capabilities of their mobile phones to get directions or recommendations; far fewer use them to share where they are with friends and contacts. That's one conclusion from a Pew Research Center survey based on phone interviews with 2,277 U.S. adults last spring. The percentages are higher for smart phone owners. Only 4% owned up to checking in on services like Foursquare or Gowalla, while a slightly higher number had set up their social media services (Facebook, LinkedIn, Twitter) to show their locations when posting. (I have to wonder if that number has jumped higher since Facebook changed its posting settings to make location-aware posts easier.) The Knight Digital Media Center for digital journalism picked up on the Pew results to urge news media publishers to geotag their content.

Got news?

News tips and suggestions are always welcome, so please send them along.

If you're interested in learning more about the payment development space, check out PayPal X DevZone, a collaboration between O'Reilly and PayPal.


November 05 2010

Four short links: 5 November 2010

  1. S4 -- S4 is a general-purpose, distributed, scalable, partially fault-tolerant, pluggable platform that allows programmers to easily develop applications for processing continuous unbounded streams of data. Open-sourced (Apache license) by Yahoo!.
  2. RDF and Semantic Web: Can We Reach Escape Velocity? (PDF) -- spot-on presentation from the linked data advisor. It nails, clearly and in only 12 slides, why there's still resistance to linked data uptake and what should happen to change this. Amen! (via Simon St Laurent)
  3. Pew Internet Report on Location-based Services -- 10% of online Hispanics use these services - significantly more than online whites (3%) or online blacks (5%).
  4. Slate -- Python library for extracting text from PDFs easily.

Older posts are this way If this message doesn't go away, click anywhere on the page to continue loading posts.
Could not load more posts
Maybe Soup is currently being updated? I'll try again automatically in a few seconds...
Just a second, loading more posts...
You've reached the end.
No Soup for you

Don't be the product, buy the product!

YES, I want to SOUP ●UP for ...