Ovuline's Smart Fertility tracker uses big data and machine learning to help women get pregnant faster.
Want to make a baby, like, today? The tried-and-true method -- meaning without algorithms and big data -- isn't the way to go if you're in a hurry. On average, it takes a woman 4 to 6 months to conceive, but Ovuline, a year-old startup based in Cambridge, Mass., crunches large amounts of data to speed things up.
Ovuline's data-intensive methodology includes wearable mobile devices, smartphone apps, and machine learning analytics. The company collects health information on its users (i.e., women hoping to get pregnant) via wearable quantified self (e.g., self-monitoring) Wi-Fi devices from FitBit and Withings. It can also gather data via its free Ovuline Smart Fertility app for iOS.
Of course, a quick search of the App Store shows that fertility apps are a dime a dozen. But what makes Ovuline unique is its big-data approach to the mechanics of baby-making. The company has recorded 4 million data points from more than 70,000 women, including health information on blood pressure, body weight, cervical fluids, menstrual cycles, body temperature, and even sexual intercourse.
"We use all of this information, in addition with clinical guidelines, to make very accurate predictions about when [women] are ovulating, and when intercourse will lead to conception," Ovuline CEO Paris Wallace told InformationWeek in a phone interview.
The Ovuline method may appeal to Type A couples, particularly those who wait until their 30s or 40s to have kids. "When they want to have a child, they want to get pregnant immediately," said Wallace. "And then when it doesn't work over the course of a few weeks or a few months, they turn to Ovuline to help them conceive."
Because, he said, big data makes babies faster. "One of the big reasons why women take, on average, 4 to 6 months to conceive is because they are not accurately predicting ovulation," said Wallace. "Of our users who have reported pregnancy, they're doing so in about 60 days, which is about 3 times faster than the national average. So our algorithm and prediction engine seems to be working."
Ovuline's service is currently free to consumers, an incentive that allows the company to quickly amass valuable health data. "We really want to have as many consumers as possible sign up for our service and use it, obviously, because the more data we get, the better our service becomes, and the better our predictions are using our machine learning algorithms," Wallace noted.
The data science behind Ovuline was the brainchild of Alex Barron, the company's chief technical officer, who developed the ovulation-prediction technology while he and his wife were trying to conceive their first child.
"I already had a Ph.D. in computer science, and I was working on my masters in statistics at that time," Barron told InformationWeek. "While I was building the algorithm, we decided to try and see whether it was working, and it worked for us. So we have a beta baby, Michael, who is 7 months old."
Ovuline is developing more health-related applications as well. "In the fall we'll be launching a pregnancy tracker, which uses the same backend database," said Wallace. "Women will enter information, and we'll also collect (data) on the quantified self devices."
The company's future may bring other health-monitoring and diagnostic tools too. "We're building an incredibly flexible platform with a machine learning analytics layer that could be applied to a variety of health states," Wallace said.
To understand how to secure big data, you have to understand what it is -- and what it isn't. In the Security Implications Of Big Data Strategies report, we show you how to alter your security strategy to accommodate big data -- and when not to. (Free registration required.)
6 Tools to Protect Big DataMost IT teams have their conventional databases covered in terms of security and business continuity. But as we enter the era of big data, Hadoop, and NoSQL, protection schemes need to evolve. In fact, big data could drive the next big security strategy shift.
Big Data Brings Big Security ProblemsWhy should big data be more difficult to secure? In a word, variety. But the business won’t wait to use it to predict customer behavior, find correlations across disparate data sources, predict fraud or financial risk, and more.