Mark Brooks from OnlinePersonalsWatch had interviewed the CEO of IntroAnalytics.
Their core product is a Behavioural Recommender System.
"What does Intro Analytics do?
It’s a data intelligence matching company designed for dating sites and social media. We look at the behavior people have online and we match them based on that."
Behavioural Matching recommends people based on the type of person you have sent emails to, replied to, clicked on in search results and gone on dates with, but .... persons/people often report/select partner preferences that are not compatible with their choices in real life, that is why Behavioural Recommender Systems / Recommendation Engines perform so bad.
Some time ago I posted about punches to Behavioural Recommender Systems / Recommendation Engines for Online Dating sites like IntroAnalytics, VisualDNA, the one used at PlentyOfFish or other system that learns your preferences:
NEW and FRESH paper, punch to Behavioural Recommenders.
a big punch to Behavioural Recommender Systems.
Two papers debunking speeddating for serious dating
Personality Based Recommender Systems are the next generation of recommender systems because they perform FAR better than Behavioural ones (past actions and pattern of personal preferences)
That is the only way to improve recommender systems, to include the personality traits of their users.
Have you seen they need to calculate personality similarity between users?
Have you seen there are different formulas to calculate similarity?
In case you did not notice, recommender systems are morphing to .......... compatibility matching engines!!!
They mostly use the Big5 to assess personality and the Pearson correlation coefficient to calculate similarity.
Researchers in the Personality Based Recommender Systems arena are also testing different / novel formulas to calculate similarity, useless at all because they use the Big5 to assess personality of users.
Online Dating Sites like eHarmony, Parship, Be2, MeeticAffinity, PlentyOfFish Chemistry Predictor and others had been calculating personality similarity between prospective users since several years ago with low successful rates, with a low effectiveness/efficiency level of their matching algorithms (less than 10%) because they use the normative Big5 or ipsative proprietary models instead -like Chemistry or PerfectMatch- to measure personality traits.
No one is using the 16PF5 to assess personality of members.
No one calculates similarity with a quantized pattern comparison method.
No one can show Compatibility Distribution Curves to each and every of its members.