This is a guest blog by Sumant US from Marax AI.
Today, artificial intelligence is being used in many different ways, from the iPhone’s Siri to getting recommendations based on your shopping history on Amazon.
Artificial intelligence has been on the rise, especially this decade, and can do some interesting things, such as composing its own piece of music on the piano.
With technology giants like Amazon, Google and Tesla increasingly looking to push their resources into artificial intelligence, it’s about time we saw AI being used by dating companies.
First, let’s see how AI could help singles find the right match.
Gone are the days when online dating was laughed off. Today, young adults and professionals are taking time out of their busy lives to find their perfect match using dating websites and apps. Considering the many different dating apps in the market, a perfect differentiation between them would be how well they match the users.
But wait, how is machine learning going to help me get the best matches?
When you use a dating app, you are usually asked a lot of questions about who you are, what you want and your likes & interests. Your answers are cross referenced with people who gave similar answers and then these people are matched with you. These matches might be relevant if both you and your match answer these questions truthfully. But history has proven that’s often not the case.
What if the dating app could understand what you want? Let me rephrase that – what if it could learn what you want based on how you behave with your current matches and predict the type of matches you would want in the future.
For instance, let’s look at when the user is swiping through profiles. You may have said that you are only interested in people with a master’s degree, but it’s often the case that you make an exception for somebody because they had other characteristics which compensated for the lack of a master’s degree. This is where machine learning works its magic. Based on this behaviour, the recommender system also matches you with people with similar characteristics – no master’s degree but other highly-compensating characteristics. Gradually, the more you use the dating app, the more the machine knows about you and the better matches it gives you.
All is good and well when you get matches who you find attractive. But what is the point if it’s only one-sided, ie. he/she doesn’t find you attractive. You wouldn’t get a response if your match doesn’t find you attractive. So, to help you save time, the intelligent dating app analyses the response rate of the messages you sent to your matches and other features and then evaluates what kind of people find you attractive.
What is this attractiveness score?
Attractiveness score is a cross feature which is calculated based on a set of attributes such as confidence levels, matching likes, response rates etc. The features used to calculate this score will depend on the kind of data that can be extracted from a dating app.
This attractiveness score will help find the kind of people who would find you attractive and thereby increase your response rate.
Aside from this, there are many other relevant features that can be used to make the recommendation engine more efficient, but it would vary with different dating apps.
So, AI helps you decide the right match where you and only you decide how you get your match.
At Marax AI, we are currently helping dating apps & websites integrate artificial intelligence so that they show relevant matches and keep their customers happy.
Powered by Marax’s AI Engine, which uses a combination of advanced machine learning, deep learning, natural language processing and other proprietary algorithms, it can help dating apps recommend personalised and accurate matches for every single user.
(If you’re interested, you can check out our demo on how we integrate artificial intelligence into dating apps.)