FIGARODIGITAL.CO.UK
ESSAYS
ince few things in life are less logical than love, you’d be forgiven for thinking that data has a limited role to play in matchmaking. In fact, says Samir El-Alami, Online Marketing Director at
Lovestruck.com, successful online dating is all about having a fi rm grasp of users’ vital statistics. The challenge, familiar to anyone who’s ever been on a blind date, lies in understanding users’ intentions and responding sensitively. So how does
Lovestruck.com, which has a membership of over 100,000 digitally- savvy singletons in London and the south east, approach the vast amount of data at its disposal? “It starts with hard data,” says El-Alami. “From there it goes to contextual and then behavioural.” Hard data, he explains, is the personal information supplied by users when they sign up to Lovestruck. “Since we’re a dating site, people naturally want to tell us where they live, where they work and what their interests are. They’ll also indicate the sort of person they’re looking for. They may specify what sort of career they want that person to have, what age range they’re looking for. All of that is hard data which people are very happy to provide.”
So, unlike plenty of ecommerce
sites,
Lovestruck.com users have a vested interest in providing as much detailed, accurate information about themselves as possible since that increases their chances of a successful match.
“That’s right,” says El-Alami. “If
you’re asking people for data, you have to make it worth their while. The quicker and easier it is to fi ll in the form, the better. But you can’t ask for too much data, and you have to incentivise people. It’s also worth bearing in mind that, in
42 issue 20 january 2014
WITH DATA
MAKING A DATE
Samir El-Alami, Online Marketing Director at
Lovestruck.com, tells us about the dating site’s relationship with data
our experience at Lovestruck, people may tell you what they think they’re looking for, but that’s not necessarily what they actually want.” So, hard data provides a useful sketch
of users’ interests. “It’s a great place to start,” says El-Alami. “But just because two people both like ‘Twilight’ and work near each other, that doesn’t automatically mean they’re a great match. You need more than that. And that’s where behavioural data comes in.”
YOU GET OUT WHAT YOU PUT IN This, for El-Alami, is the most important element in
Lovestruck.com’s data equation. “I might tell you I’m looking for X, Y or Z, but in reality I could be looking at completely different profi les. We need to look at who members are ‘winking’ at, who they’re sending messages to. These are simple bits of data which really tell me what kind of person you’re looking for. As well as our own in-house algorithm, we have a second one which looks at
hard data and behavioural
data together. In a perfect world, what people do and what they say they do would be the same thing, but as we all know life isn’t quite like that. But by taking these strands together, the site is able to start making really good suggestions based on actual user behaviour.” The next step in refi ning user
data is contextual. “This is where something even more interesting happens,” says El-Alami. “So, you’ve said you like this person - or this type of person - but in reality, you’re more interested in speaking to these types of people. What we can do is fi nd users who are similar to those, and make sure you see more of them. That enables us to provide a list of potential candidates based on what you’ve actually done.”
☞ ARTICLE JON FORTGANG
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42 |
Page 43 |
Page 44 |
Page 45 |
Page 46 |
Page 47 |
Page 48 |
Page 49 |
Page 50 |
Page 51 |
Page 52 |
Page 53 |
Page 54 |
Page 55 |
Page 56 |
Page 57 |
Page 58 |
Page 59 |
Page 60 |
Page 61 |
Page 62 |
Page 63 |
Page 64 |
Page 65 |
Page 66 |
Page 67 |
Page 68
