Tuesday, May 17, 2011

ASoundMatch and Behavioural Recommender Systems

Last January 2008 I had tested ASoundMatch and posted a comment at OnlineDatingInsider
saying "…..
matches with a high likelihood of compatibility because they have a similar music lifestyle and also similar personality traits.
How it can be proved?
Also profiling by voice analysis, image analysis, music/video preferences, handwriting analysis, color preferences and other == lack of precision by distortion!"

I had also posted about punches to Behavioural Recommender Systems / Recommendation Engines for Online Dating sites:
NEW and FRESH paper, punch to Behavioural Recommenders.
a big punch to Behavioural Recommender Systems
Two papers debunking speeddating for serious dating
Someone told me "People need to improve their mate-hunting skills." in a private email.

I strongly agree with the paper:
"Perceptions of Ideal and Former Partners' Personality and Similarity"
Pieternel Dijkstra / Dick P. H. Barelds / University of Groningen, The Netherlands
..... Our findings may help understand why so many relationships end in divorce due to mismatches in personality.
Our findings strongly support the 'similarity-attraction' hypothesis: Individuals clearly desire a potential partner with a similar personality.
In addition to finding a mate with a similar personality, our study showed that individuals seek a mate who is slightly 'better' than they are: They prefer a mate who is somewhat less neurotic, more agreeable, more conscientious, more open and more extraverted than they are themselves.
.... mismatches in personality are a frequently mentioned cause for relationship break-up. If former partners indeed have dissimilar personalities, our findings underline how difficult it is for many people to select a mate with a similar personality, or, alternatively, how little value individuals put on finding a similar partner in terms of personality.
The present study's results, as well as the results found in previous studies (e.g., Eastwick & Finkel, 2008), may be used to educate people, especially singles, about what really matters in long-term relationships, for instance, similarity in personality, instead of complementarity.


In compatibility matching methods there are 2 steps:
1) to objectively measure personality traits or other human variables (with the 16PF5 test).
2) to calculate compatibility between prospective mates.

Breaking "the online dating sound barrier" is to achieve far better precision than searching on one's own or mutual filtering.

Actual Online Dating sites are fully intoxicated with different versions of the FFI five factor inventory / Big5 or other proprietary models instead (like Chemistry or PerfectMatch), to measure personality traits, and all of those tests are more simplified versions than the 16PF5 normative personality test.

Breaking "the online dating sound barrier" is to achieve at least:
3 most compatible persons in a 100,000 persons database.
12 most compatible persons in a 1,000,000 persons database.
48 most compatible persons in a 10,000,000 persons database.
100 times better than Compatibility Matching Algorithms used by actual online dating sites!

The only way to achieve that is:
- using the 16PF5 normative personality test, available in different languages to assess personality of members, or a proprietary test with exactly the same traits of the 16PF5. The ensemble of the 16PF5 is: 10E16, big number as All World Population is nearly 6.7 * 10E9
- expressing compatibility with eight decimals, like The pattern is 92.55033557%  +/- 0.00000001% similar to the pattern
Using a quantized pattern comparison method (part of pattern recognition by cross-correlation) to calculate similarity between prospective mates.

That is the only way to revolutionize the Online Dating Industry.

All other proposals are .............. NOISE

No comments:

Post a Comment