By Andi Gillentine (Co-Founder & COO, Whit.li)
Have you ever had the experience of reading a review online – for a book, a hotel or a restaurant – and wanted to know if you were “like” the reviewer? Not if you lived in the same place, were the same age, or bought the same gift for someone else, but if you were really alike, deep down. Me too, and so have all of the founders of Whit.li. This was our inspiration moment.
The four of us all worked together at a previous startup that, after 10 years, split into two companies. That previous company had developed a sophisticated matching algorithm to match large data sets to help enterprises in IT Outsourcing, Financial Services and Healthcare perform services like bill their clients, evaluate the quality of stock fills, or find fraudulent doctors, respectively.
My founders and I thought about our frustrations using the Web and the concept of what it means to be “like” someone. We were pretty certain that there had to be a way to use our expertise in algorithms and matching to solve this problem. At the time that we started doing this, there were a couple of companies working on personalization on the web, like Hunch. And there were more than a few companies matching people for romantic reasons, like eHarmony. The common theme with these companies is that the user had to answer a lot of questions to get to the value of being matched.
We wanted it to be easier than that. With the help of a Yale trained PhD in Psychology, we found our path. Personality, like the big five personality traits, can be extracted from user-generated content (like Facebook posts) based on the kinds of words they use. And there it was — the answer to the problem. So we got started.
It took nearly a year to get the core technology built and tested. We initially focused on Facebook data as a source. To gather our first data to test our algorithms, we used a Facebook app where we provided a personality analysis based on a user answering a Big 5 personality inventory and authenticating that we could look at their posts. We used that data, anonymously, to refine our algorithms to provide personality, demographic and interest analysis.
In keeping with our original inspiration, we released the technology via API so that companies could build it into their sites directly. We launched our API at SXSW 2012. Initially, we thought that collaborative consumption companies would be very heavy users of this technology. At, SXSW we learned that brands – big, enterprise brands – were even more interested in it. That was an eye-opening experience for us.
Only two of our four founders had experience with consumer market research at the time so we reached out through our network and found advisors in that industry. Over the next several months, we worked with big brands to better understand their needs and produced an MVP Segmentation application that uses the core personality technology to address their needs.
It’s been 8 months since SXSW. We have nearly 200 hundred companies registered for the API, and another nearly 200 hundred waiting for the next version of our Segmentation application. When one of our advisors wanted to pay us to finish the MVP of the Segmentation application – we knew we were on the right track.
When we found out we had been selected as a PITCH NYC Finalist at Women 2.0, it was a great day. When you create a new technology, most days are long and hard. And getting people to try your technology is often difficult. But every piece of validation, like being a Women 2.0 finalist, is a huge lift.
Women 2.0 readers: Will you be joining us for PITCH NYC Conference & Competition? Let us know in the comments.
About the guest blogger: Andi Gillentine is Co-Founder and COO of Whit.Li. Andi combines her experience implementing technology solutions for enterprise clients with her Mathematics background to lead the development of Whit.li’s natural language processing technology that provides businesses understanding of the personality and interests of their fans and followers. Andi holds a degree in Mathematics from Bryn Mawr College and a Masters Degree in Epidemiology from the University of Texas.