Romantic Matchmaking By Machine?

By Chordboard - Self, from material in my possession., Public Domain, https://commons.wikimedia.org/w/index.php?curid=4310843

For Valentine’s Day: an analysis of the shortcomings of machine learning (for now) to gauge two people’s romantic attraction to each other.  The authors divide romantic attraction into three components. First, the overall tendency of someone to desire others (actor variance), the tendency of that someone to be desired by others (partner variance) and, finally, a third component (relationship variance) that captures desire not characterized by the other two components (one may term this, I guess, “the mysteries of love”).  While machine leaning can predict some fraction of actor and partner variances, it was unable to model the more elusive relationship variance using traits and preferences reported before dates.  So far, the fine details of human romantic interest cannot be fully captured by machine learning. However, that may change in time.  Abstract:

Matchmaking companies and theoretical perspectives on close relationships suggest that initial attraction is, to some extent, a product of two people's self-reported traits and preferences. We used machine learning to test how well such measures predict people's overall tendencies to romantically desire other people (actor variance) and to be desired by other people (partner variance), as well as people's desire for specific partners above and beyond actor and partner variance (relationship variance). In two speed-dating studies, romantically unattached individuals completed more than 100 self-report measures about traits and preferences that past researchers have identified as being relevant to mate selection. Each participant met each opposite-sex participant attending a speed-dating event for a 4-min speed date. Random forests models predicted 4% to 18% of actor variance and 7% to 27% of partner variance; crucially, however, they were unable to predict relationship variance using any combination of traits and preferences reported before the dates. These results suggest that compatibility elements of human mating are challenging to predict before two people meet.