You + Your Data The Small Data Lab @ CornellTech develops new personal data APIs and applications for individuals to harvest the small data traces they generate daily

What is Small Data?

Every day, each of us leave millions of individual digital traces. We leave these traces as a long continuous trail of data spanning our mobile phone communications, the location and mobility patterns pinged out from our smartphones, our purchases at the local grocery store and online at our favorite e-commerce portals, our emails and instant messages, our search engine histories, and our latest posts to friends and peers on social media.

All of these breadcrumbs of data are the result of our interactions with online and mobile platforms that increasingly shape our daily lives. Even though they often empower us with access to information about the vast world around us, they very rarely provide access to us on the fundamental information about ourselves.

The Small Data Lab at Cornell Tech is working to change that with a new generation of personal data APIs, applications and email and browser plugins that provide not just access to the small data of your life but, more importantly, the big insights and meaning this small data contains within.

Our Work

  • Mobile Sensing

    Mobile Sensing

    Building on close to 5 years of application and platform development, Ohmage is an advanced open-source participatory sensing platform for passively collecting your location and activity sensor data along with regular inquiry-driven surveys requiring your active input. Ohmage leverages the two datastreams in tandem to build sensemaking and prediction capabilities for any number of behaviors and conditions of interest. Particularly our work has concentrated on using this small data for healthcare but over the course of 2014 we are incrementally expanding our focus to other problem areas.

    mhEALTH, Smartphone Sensors, Location and Activity Sensemaking

  • Smart Email Inboxes

    Email is one of our oldest communication mediums on the Web and still encompasses a stunning amount of the small data we generate daily. The Small Data Lab is actively developing new email plugins and services to not only organize and analyze what your emails can say about your health, mood and engagement with the world but to also securely scrape and recapture key personal data such as your online purchases, which is informative on a myriad of interests and activities - for instance, in the case of online groceries, what you are cooking and eating at home.

    Email, Natural Language Processing, Content Scraping

    Web app UI screenshot
  • iPhone app UI screenshot

    Personal Data APIs

    Working closely with corporate, civic and non-profit partners the Lab is in the early stages of identifying, designing and developing new personal data APIs to provide Beta personal data access back to individuals. We are activiely looking for new partners - particularly in the area of consumer transactions and line-item purchase records.

    APIs, Access Control, Personal Data APIs, Consumer Transaction Data

TEDMED 2013: Small Data
Can Show Big Health Changes


Wells RileyDeborah Estrin, Professor of Computer Science, Cornell Tech, NYC; Professor, Public Health, Weill Cornell Medical College; Co-founder, Open mHealth