Saturday, July 30, 2011

Behavioural Recommender Systems RUBBISH

Behavioural Recommender Systems RUBBISH

It is really funny how those "important persons" from big Online Dating Sites can waste precious time with Behavioural Recommender Systems, improving them, "refining" those Behavioural Matching Algorithms, which are all rubbish.
The effectiveness/efficiency level of those Behavioural Matching Algorithms are less than 10%!!!

Free online dating sites like PlentyOfFish and OkCupid can not be successful because they are only marketing tools to send users to paid online dating sites. To be profitable, they need the commissions paid bay those paid online dating sites

Paid online dating sites like eHarmony, Meetic, Match, Chemistry, etc, can not be successful because they have high acquisition costs, they can not abandon the attracting, converting and retaining marketing stages; the automatic renewal of their members's subscriptions with dirty credit-card billing trickery.

Big online dating sites DO NOT WANT TO INNOVATE.

The entire Online Dating Industry for serious daters in 1st World Countries is a HOAX, performing as a Big Online Casino, with a low effectiveness/efficiency level of their matching algorithms (less than 10%) There is a range convergence phenomenon between the 3 mains tools online dating sites offer now: Searching by your own, Recommendation Engines and Compatibility Matching Methods based on proprietary models or the Big5. Any member receives on average 3 to 4 prospective mates as selected / recommended / compatible for dating purposes per 1,000 members screened in the database.
They all 3 are performing the same for serious daters, with a high percentage of false positives, like gun machines firing flowers.

See these infographics from a white label service

Would  you be flying with an airline that had a 80% failure rate?

The Online Dating Industry needs innovations but they will come from only one source: the latest discoveries in theories of romantic relationships development with commitment.
I) Several studies showing contraceptive pills users make different mate choices, on average, compared to non-users.
II) People often report partner preferences that are not compatible with their choices in real life.
III) Compatibility is all about a high level on personality* similarity* between prospective mates for long term mating with commitment.
*personality measured with a normative test.
*similarity: there are different ways to calculate similarity, it depends on how mathematically is defined.

Also 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 and they need to calculate personality similarity between them.

WorldWide, there are over 5,000 online dating sites
but no one is using the 16PF5 (or similar test) to assess personality of its members.
Without offering the 16PF5 (or similar test measuring exactly the 16 personality factors) for serious dating, it will be impossible to innovate and revolutionize the Online Dating Industry.

No comments:

Post a Comment