Dating website data mining

All that data, ripe for the picking

Now, let's discuss how this applies in some of your research Q - Your recent work on developing a "Netflix style" algorithm for dating sites has received a lot of press coverage A - We try to address user recommendation for the unique situation of reciprocal and bipartite social networks e. The idea is to recommend dating partners who a user will like and will like the user back.

In other words, a recommended partner should match a user's taste, as well as attractiveness. Q - How did Machine Learning help?

A - In short, we extended the classic collaborative filtering technique commonly used in item recommendation for Amazon. A - People's behaviors in approaching and responding to others can provide valuable information about their taste, attractiveness, and unattractiveness. Our method can capture these characteristics in selecting dating partners and make better recommendations. Editor Note - If you are interested in more detail behind the approach, both Forbes' recent article and a feature in the MIT Technology Review are very insightful.

Here are a few highlights:. Recommendation Engine from MIT Tech Review - These guys have built a recommendation engine that not only assesses your tastes but also measures your attractiveness. It then uses this information to recommend potential dates most likely to reply, should you initiate contact. The dating equivalent [of the Netflix model] is to analyze the partners you have chosen to send messages to, then to find other boys or girls with a similar taste and recommend potential dates that they've contacted but who you haven't.

In other words, the recommendations are of the form: The problem with this approach is that it takes no account of your attractiveness. If the people you contact never reply, then these recommendations are of little use. So Zhao and co add another dimension to their recommendation engine.

more on this story

They also analyze the replies you receive and use this to evaluate your attractiveness or unattractiveness. Obviously boys and girls who receive more replies are more attractive. When it takes this into account, it can recommend potential dates who not only match your taste but ones who are more likely to think you attractive and therefore to reply. Machine Learning from Forbes - "Your actions reflect your taste and attractiveness in a way that could be more accurate than what you include in your profile," Zhao says.

The research team's algorithm will eventually "learn" that while a man says he likes tall women, he keeps contacting short women, and will unilaterally change its dating recommendations to him without notice, much in the same way that Netflix's algorithm learns that you're really a closet drama devotee even though you claim to love action and sci-fi. Finally, for more technical details, the full paper can be found here. A - We want to further improve the method with different datasets from either dating or other reciprocal and bipartite social networks, such as job seeking and college admission.

How to effectively integrate users' personal profiles into recommendation to avoid cold start problems without hurting the method's generalizability is also an interesting question we want to address in future research. That all sounds great - good luck with the next steps! So why does Tinder need all that information on you?

Unfortunately when asked how those matches are personalised using my information, and which kinds of profiles I will be shown as a result, Tinder was less than forthcoming. The trouble is these pages of my most intimate data are actually just the tip of the iceberg.

Data Mining for Dates

Eventually, your whole existence will be affected. As a typical millennial constantly glued to my phone, my virtual life has fully merged with my real life. There is no difference any more. Tinder is how I meet people, so this is my reality. It is a reality that is constantly being shaped by others — but good luck trying to find out how. This article contains affiliate links, which means we may earn a small commission if a reader clicks through and makes a purchase.

All our journalism is independent and is in no way influenced by any advertiser or commercial initiative. The links are powered by Skimlinks. The biggest challenge that online dating websites face is to make sure you are matched with people that you like.

I asked Tinder for my data. It sent me 800 pages of my deepest, darkest secrets

Even in the early days of online dating, the sites used questionnaires and profile information to try and find you the perfect date. However, before the Big Data boom it was often quite a manual process and could sometimes leave you disappointed by the end of a date. Sarah Holmlund via Shutterstock. The questions have become more specific, with definitive answers.

How Machine Learning Can Transform Online Dating: Kang Zhao Interview | Data Science Weekly

At the same time, the amount of users across the sites has increased, creating a huge pool of data. By developing machine learning algorithms 4 Machine Learning Algorithms That Shape Your Life 4 Machine Learning Algorithms That Shape Your Life You may not realize it but machine learning is already all around you, and it can exert a surprising degree of influence over your life. You might be surprised. Read More , the online dating platforms hope to be able to predict, with greater certainty, matches that brighten your day. The site differentiates itself from the competition by billing themselves as a relationship, rather than dating, website.

As the company is privately owned it has no obligation to share its data and statistics with the general public. They have previously mentioned that over , couples have got married after meeting on the site, with over two thirds finding this match within their first year. But try eHarmony if you want to improve your chances for a long term relationship. Read More that aims to dig a deep into who you are, and what you may like in a partner.

At questions, and taking almost 18 hours to complete, it is a lot of effort. I give it a try. The basis of the site is a collection of fun personality quizzes using a variation of the infamous Myers-Briggs Type Indicator. They combine your answers with how you would like your match to answer them, along with how important each question is to you.

But if online dating is where you're at right now, OkCupid is the best service, free or paid, available on the market today. Read More and plugged into their algorithm to find you a match, complete with a percentage compatibility rating. Since , OKCupid has written a blog where they detail some of the more interesting and surprising things they learn from the data they analyze. Read More that they used some of this data to experiment on their users. While sites like eHarmony and OKCupid have found success mining data for matches, some have taken a different approach.

Probably the most popular among the competition is Tinder. So Tinder is employing Smart Photos to help you get more right swipes. In just a few short years, Tinder managed to become the most popular online dating service with over 50 million users as of Collectively those users make 1.

This high volume of matches far exceeds OKCupid, eHarmony, or any other traditional data-based dating site. Tinder does still use data like location, number of mutual friends, and common interests to suggest matches.