Does Machine Learning allow opposites to attract?
Most online dating sites use 'Netflix-style' recommendations which match people based on their shared interests and likes. What about those matches that work so well because people are so different - here is my example.
In 1958, the Monotones asked, “Who Wrote the Book of Love?”. If we fast forward 58 years to the present day, would the ‘Algorithm of Love’ be a more accurate title? It is certainly a valid question; such is the popularity of the modern online dating website. Users can forego the inevitable awkwardness of blind or speed dating altogether, having found out every last detail about their date before they ever have to meet them in person.
Most dating websites utilise some form of collaborative filtering or a ‘Netflix style’ recommendation algorithm that matches people with their potential partners based on shared interests and hobbies or mutual likes and dislikes. Joseph Essas, former CEO of EHarmony, wrote in 2011 that his site’s user compatibility matches are based on three distinct areas: psychological compatibility, interpersonal chemistry and physical attraction.
Given that the cornerstone of how online dating websites work is to match people with similar interests and personality traits. Here’s my question - what about the relationships that exist and function beautifully because people are so different? I recently got engaged and feel extremely lucky. However, I’m confident that no online dating website would have matched me to my fiancée. I love sport, she finds it boring. She doesn’t like wine, I love it. I read lots, she’s a movie addict. Our music tastes are completely different. I love walking, she’d prefer to cycle. She loves shopping, I don’t. Spaghetti Bolognese is the best thing in the world, she disagrees. She’s 5ft, I’m 6ft2. You can see what I’m getting at…. Can Machine Learning help identify the non-matches that in reality are a perfect fit? Is it capable of understanding that opposites often attract? Are online dating websites keeping you from the love of your life because you’ve not followed the same question path?
Just as a disclaimer; I’m not suggesting for a moment that these websites don’t help people find love. Match.com’s recent stats are staggering, having apparently been responsible for 500,000 relationships, 92,000 marriages and over a million babies. I don’t have an overriding conclusion on this subject, just a thought that it would be a great shame if the spontaneity of meeting someone whilst having a coffee or bumping into someone in the park was lost, because people were too busy swiping left and right on their phones to notice their ideal partner walking past them. It is Valentine’s Day this Sunday, and many of those who will be celebrating will have met through dating websites, and many will have met because they were just in the right place at the right time. My point is that the wrong person according to an algorithm could be the right person according to your heart.