RecSys 2021 15th ACM Conference on Recommender Systems

 

Amsterdam, Netherlands, 27th September-1st October 2021
https://recsys.acm.org/recsys21/accepted-contributions/#content-tab-1-5-tab

PAPER: RecSys Challenge 2018
https://onlinedatingsoundbarrier.blogspot.com/2018/10/paper-recsys-challenge-2018-playlist.html

best paper RecSys 2011 Conference
https://onlinedatingsoundbarrier.blogspot.com/2011/09/best-paper-recsys-2011-conference.html

 

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)
https://onlinedatingsoundbarrier.blogspot.com/2019/05/paper-beyond-personalization-research.html
 
That is the only way to improve recommender systems, to include the personality traits of their users.
http://onlinedatingsoundbarrier.blogspot.com.ar/2017/01/paper-comparative-study-of-people-to_14.html  

They need to calculate personality similarity between users but there are different formulas to calculate similarity.

In case you did not notice: Recommender systems are morphing to compatibility matching engines, as the same used in the Online Dating Industry for years, with low success rates until now because they mostly use the Big Five model to assess personality and the Pearson correlation coefficient to calculate similarity.
Please remember: Personality traits are highly stable in persons over 25 years old to 45 years old. 

The key to long-lasting romance: COMPATIBILITY is exactly STRICT PERSONALITY SIMILARITY and not "meet other people with similar interests or political views".  

Which is the RIGHT approach to innovate in the Personality Based Recommender Systems Arena? 
The same approach to innovate in the Online Dating Industry == 16PF6 test or similar to assess personality traits and a new method to calculate similarity between quantized patterns.
 
Online Dating sites have very big databases, in the range of 20,000,000 (twenty million) profiles, so the Big Five model or the HEXACO model are not enough for predictive purposes. That is why I suggest the 16PF6 test instead and another method to calculate similarity.

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!
High precision in matching algorithms is precisely the key to open the door and leave the infancy of compatibility testing.

Without offering the NORMATIVE 16PF6 (or similar test measuring exactly the 16 personality factors) for serious dating, it will be impossible to innovate and revolutionize the Online Dating Industry.   

PAPER: Personality Based E-Recruitment and CV Ranking System

 

[PDF] Personality Based E-Recruitment and CV Ranking System

Measuring Recommender System Effects with Simulated Users
https://onlinedatingsoundbarrier.blogspot.com/2021/01/measuring-recommender-system-effects.html

 

PAPER: How Are Personality States Associated with Smartphone Data? http://onlinedatingsoundbarrier.blogspot.com/2020/11/paper-how-are-personality-states.html 

Which is the RIGHT approach to innovate in the Personality Based Recommender Systems Arena? 
The same approach to innovate in the Online Dating Industry == 16PF6 test or similar to assess personality traits and a new method to calculate similarity between quantized patterns.
 

The key to long-lasting romance: COMPATIBILITY is exactly STRICT PERSONALITY SIMILARITY and not "meet other people with similar interests or political views".   
Online Dating sites have very big databases, in the range of 20,000,000 (twenty million) profiles, so the Big Five model or the HEXACO model are not enough for predictive purposes. That is why I suggest the 16PF6 test instead and another method to calculate similarity.

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!
High precision in matching algorithms is precisely the key to open the door and leave the infancy of compatibility testing.

Without offering the NORMATIVE 16PF6 (or similar test measuring exactly the 16 personality factors) for serious dating, it will be impossible to innovate and revolutionize the Online Dating Industry.

 
If Match Group MTCH plans to enter the Job Recruiting Industry also?
http://onlinedatingsoundbarrier.blogspot.com.ar/2017/12/if-match-group-mtch-plans-to-enter-job.html

eHarmony failed in the jobs industry with Elevated Careers and sold it to CandidateGuru
http://onlinedatingsoundbarrier.blogspot.com.ar/2017/12/candidateguru-and-elevated-careers.html

LinkedIn's career advice app vs. dating app Bumble's version / major flaws with both
http://onlinedatingsoundbarrier.blogspot.com.ar/2017/12/linkedins-career-advice-app-vs-dating.html

FT articles: Bank hiring: Wall St turns to machines to find better-behaved bankers & Making the grade at Deutsche Bank
http://onlinedatingsoundbarrier.blogspot.com.ar/2016/09/ft-articles-bank-hiring-wall-st-turns.html

Compare to WayUp
http://onlinedatingsoundbarrier.blogspot.com.ar/2017/04/wayup-same-road-as-elevatedcareers.html

 

 

PAPER: How Are Personality States Associated with Smartphone Data?

 

https://www.alexandria.unisg.ch/261212/1/Ruuegger%20et%20al%202020%20Personality%20States%20Smartphone%20Data.pdf

PAPER: Twitter User Personality Prediction 2017
https://onlinedatingsoundbarrier.blogspot.com/2017/04/paper-twitter-user-personality.html

PAPER: A Modified Similarity Measure for Improving Accuracy
https://onlinedatingsoundbarrier.blogspot.com/2018/06/paper-modified-similarity-measure-for.html

PAPER: A Recommender System based on the analysis of personality traits in Telegram social network
https://onlinedatingsoundbarrier.blogspot.com/2020/10/paper-recommender-system-based-on.html

The key to long-lasting romance: COMPATIBILITY is exactly STRICT PERSONALITY SIMILARITY and not "meet other people with similar interests or political views".  

Which is the RIGHT approach to innovate in the Personality Based Recommender Systems Arena? 
The same approach to innovate in the Online Dating Industry == 16PF6 test or similar to assess personality traits and a new method to calculate similarity between quantized patterns.
 
Online Dating sites have very big databases, in the range of 20,000,000 (twenty million) profiles, so the Big Five model or the HEXACO model are not enough for predictive purposes. That is why I suggest the 16PF6 test instead and another method to calculate similarity.

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!
High precision in matching algorithms is precisely the key to open the door and leave the infancy of compatibility testing.

Without offering the NORMATIVE 16PF6 (or similar test measuring exactly the 16 personality factors) for serious dating, it will be impossible to innovate and revolutionize the Online Dating Industry.

Compatibility IS REALLY No. 1 Ingredient To Satisfying Relationship, Study Says

"The researchers studied 2,500 heterosexual couples who have been married for about 20 years and discovered that shared interests weren’t the No. 1 element to a satisfying relationship despite what many people – and dating apps – believe."

https://philadelphia.cbslocal.com/2019/07/06/compatibility-isnt-no-1-ingredient-to-satisfying-relationship-study-says/

https://www.sciencedirect.com/science/article/pii/S0092656618301508


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 like 16PF6.
*similarity: there are different ways / formulas to calculate similarity, it depends on how mathematically is defined.

Three words in compatibility matching methods.
https://onlinedatingsoundbarrier.blogspot.com/2010/03/three-words-in-compatibility-matching.html
Big summary about matching algorithms
https://onlinedatingsoundbarrier.blogspot.com/2011/11/big-summary-about-matching-algorithms.html


Facebook dating Australia soon. (July 2019 Winter in South Hemisphere)
https://onlinedatingsoundbarrier.blogspot.com/2019/07/facebook-dating-australia-soon-july.html

Great paper "Couple Similarity on Personality, Moral Identity and Spirituality Predict Life Satisfaction of Spouses and Their Offspring"
https://onlinedatingsoundbarrier.blogspot.com/2019/04/great-paper-couple-similarity-on.html

FUNNY: IDEA's Project 0d8 Helps Dating Services Improve
https://onlinedatingsoundbarrier.blogspot.com/2019/07/funny-ideas-project-0d8-helps-dating.html
Improvement is not innovation!


The Online Dating Industry needs INNOVATIONS, not more bells and whistles.
http://onlinedatingsoundbarrier.blogspot.com.ar/2018/01/mistakes-at-behavioral-economics-of.html

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 3 milestone discoveries of the 2001 - 2010 decade for Theories of Romantic Relationships Development are:

I) Several studies showing contraceptive pills users make different mate choices, on average, compared to non-users.
"Only short-term but not long-term partner preferences tend to vary with the menstrual cycle"

II) People often report partner preferences that are not compatible with their choices in real life. (Behavioural recommender systems or other system that learns your preferences are useless)

III) What is important in attracting people to one another may not be important in making couples happy. The key to long-lasting romance: COMPATIBILITY is exactly STRICT PERSONALITY SIMILARITY and not "meet other people with similar interests or political views".  

PAPER "Only the congruent survive - Personality similarities in couples. Personality and Individual Differences"
http://onlinedatingsoundbarrier.blogspot.com.ar/2013/04/paper-partnership-longevity-and.html 
PAPER "Partnership longevity and personality congruence in couples"
http://onlinedatingsoundbarrier.blogspot.com.ar/2010/04/only-congruent-survive-personality.html
 
At the paper  "Perceptions of Ideal and Former Partners' Personality and Similarity" 
The authors had written
".... 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."
http://onlinedatingsoundbarrier.blogspot.com.ar/2011/05/big-punch-to-behavioural-recommender.html
http://onlinedatingsoundbarrier.blogspot.com.ar/2012/07/two-papers-debunking-behavioural.html

Online Dating sites have very big databases, in the range of 20,000,000 (twenty million) profiles, so the Big Five model or the HEXACO model are not enough for predictive purposes. That is why I suggest the 16PF6 test instead and another method to calculate similarity.

High precision in matching algorithms is precisely the key to open the door and leave the infancy of compatibility testing.
Without offering the NORMATIVE 16PF6 (or similar test measuring exactly the 16 personality factors) for serious dating, it will be impossible to innovate and revolutionize the Online Dating Industry.
 
The 8 tips to innovate in the Online Dating Industry!
http://onlinedatingsoundbarrier.blogspot.com.ar/2013/12/the-8-tips-to-innovate-in-online-dating.html 

 

PAPER: Measuring Executive Personality using Machine-Learning Algorithms:

A New Approach and Validity Tests

https://faculty-research.esmt.berlin/sites/faculty/files/2019-05/Hrazdil%2C%20Novak%2C%20Rogo%2C%20Wiedman%20%26%20Zhang.pdf

Watson IBM and Amazon AI solutions, pitfalls.
https://onlinedatingsoundbarrier.blogspot.com/2018/07/watson-ibm-and-amazon-ai-solutions.html
https://onlinedatingsoundbarrier.blogspot.com/2018/01/violaai-but-match-failed-with-amazon.html
 
Finally the perfect dating algorithm? Of course NOT, Big Five test is
OBSOLETE. http://onlinedatingsoundbarrier.blogspot.com.ar/2017/02/finally-perfect-dating-algorithm-of.html
*BIG HOAX, SAME AS Watson IBM* http://onlinedatingsoundbarrier.blogspot.com.ar/2016/01/artificial-intelligence-can-watson-save.html
Our apps are an extension of our personalities, new research reveals
https://onlinedatingsoundbarrier.blogspot.com/2019/05/our-apps-are-extension-of-our.html
 
PAPER: EVALUATING RECOMMENDER SYSTEMS FOR AI-DRIVEN DATA SCIENCE
https://onlinedatingsoundbarrier.blogspot.com/2019/05/paper-evaluating-recommender-systems.html
 
The Big Five normative personality test, had been proven/revealed as an incomplete and incorrect model to assess/measure personality of persons.  It is a HOAX, a FRAUD to use the Big Five normative test in year 2019.     
For Online Dating purposes: Online Dating sites have very big databases, in the range of 20,000,000 (twenty million) profiles, so the Big Five model or the HEXACO model are not enough for predictive purposes.   That is why I suggest the 16PF6 test instead and another method to calculate similarity.
I *calculate similarity in personality patterns* with (a proprietary) pattern recognition by correlation method. It takes into account the score and the trend to score of any pattern.
Also it takes into account women under hormonal treatment because several studies showed contraceptive pills users make different mate choices, on average, compared to non-users. "Only short-term but not long-term partner preferences tend to vary with the menstrual cycle".

What comes after the Social Networking wave?
The Next Big Investment Opportunity on the Internet will be .... Personalization!
Personality Based Recommender Systems and Strict Personality Based Compatibility Matching Engines for serious Online Dating with the normative 16PF6 personality test. http://onlinedatingsoundbarrier.blogspot.com.ar/2013/06/the-next-wave-of-innovation.html

PAPER: Machine learning meets partner matching:

Predicting the future relationship quality based on personality traits

https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0213569&type=printable

PAPER: A Study on the Accuracy of Prediction in Recommendation System Based on Similarity Measures
http://onlinedatingsoundbarrier.blogspot.com/2019/03/paper-study-on-accuracy-of-prediction.html
PAPER: Aspirational pursuit of mates in online dating markets
https://onlinedatingsoundbarrier.blogspot.com/2018/08/paper-aspirational-pursuit-of-mates-in.html
 
Online Dating sites have very big databases, in the range of 20,000,000 (twenty million) profiles, so the Big Five model or the HEXACO model are not enough for predictive purposes. That is why I suggest the 16PF6 test instead and another method to calculate similarity.

The key to long-lasting romance: COMPATIBILITY is exactly STRICT PERSONALITY SIMILARITY and not "meet other people with similar interests or political views".  

Contradictory information from eHarmony and PROOF of FRAUD from the papers they had published using the OBSOLETE NORMATIVE PERSONALITY TEST BIG FIVE.
BIG FIVE NORMATIVE TEST WAS REVEALED AS INCORRECT AND INCOMPLETE MODEL OF PERSONALITY !!!
http://onlinedatingsoundbarrier.blogspot.com.ar/2017/08/contradictory-information-from-eharmony.html

High precision in matching algorithms is precisely the key to open the door and leave the infancy of compatibility testing.
Without offering the NORMATIVE 16PF6 (or similar test measuring exactly the 16 personality factors) for serious dating, it will be impossible to innovate and revolutionize the Online Dating Industry.

The 8 tips to innovate in the Online Dating Industry!
http://onlinedatingsoundbarrier.blogspot.com.ar/2013/12/the-8-tips-to-innovate-in-online-dating.html 

Paper: EFFECTS OF SIX PERSONALITY FACTORS OF CEOs

AT SMALL AND MEDIUM-SIZED ENTERPRISES ON PERFORMANCE IN BUSINESS MANAGEMENT: FOCUSING ON LEARNING AND GROWTH

http://web.usm.my/aamj/22022017/aamj22022017_4.pdf

For matching job seekers with employers, the best predictor of job performance is always: personality!!!

Ripple, a Tinder spinoff backed by Match Group, launches app for professional networking ?
http://onlinedatingsoundbarrier.blogspot.com.ar/2018/01/ripple-tinder-spinoff-backed-by-match.html

--------------------

For Serious Online Dating Purposes:
Online Dating sites have very big databases, in the range of 20,000,000 (twenty million) profiles, so the Big Five model or the HEXACO model are not enough for predictive purposes. That is why I suggest the 16PF5 test instead and another method to calculate similarity.

High precision in matching algorithms is precisely the key to open the door and leave the infancy of compatibility testing.
Without offering the NORMATIVE 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..
http://onlinedatingsoundbarrier.blogspot.com.ar/2017/04/article-how-successful-is-digital.html
  Finally the perfect dating algorithm? Of course NOT, Big Five test is OBSOLETE.
http://onlinedatingsoundbarrier.blogspot.com.ar/2017/02/finally-perfect-dating-algorithm-of.html

The 8 tips to innovate in the Online Dating Industry!
http://onlinedatingsoundbarrier.blogspot.com.ar/2013/12/the-8-tips-to-innovate-in-online-dating.html

article and PAPER: Effects of personality on postdivorce partnership trajectories

http://journals.sagepub.com/doi/abs/10.1177/0265407516665250
http://www.bbc.com/future/story/20161205-how-break-ups-change-your-personality


Please notice the research was done using the Big Five (Big 5) normative test that was revealed as incomplete, incorrect and obsolete personality test. It was replaced by the Big Six a.k.a HEXACO test. 
The Big Five (Big5) normative personality test is the biggest mistake Psychologists made since several years ago. The Big Five is also known as the Five Factor Model theory of personality traits, a psychological model based on research by Paul Costa and Robert McCrae.    

As some of the subdomains of the main domains of the HEXACO model are different from the subdomains of the main domains of the Big Five model, it can not be simple added the scale of the Honesty-Humility factor to the Big Five model to upgrade the personality test to the HEXACO model.
".. the Big Five's Agreeableness and HEXACO's Agreeableness are not identical. The Big Five factors do not include an Honesty-Humility factor, but some of the characteristics belonging to Honesty-Humility are incorporated into the Big Five's Agreeableness factor. Although earlier investigations found only the Big Five factors, more recent studies conducted in various languages (including English) with larger sets of adjectives recovered six factors. "
 
I need to hammer your head and drill holes in your brain to make you understand Online Dating sites have very big databases, in the range of 20,000,000 (twenty million) profiles, so the Big Five model or the HEXACO model are not enough for predictive purposes. That is why I suggest the 16PF5 test instead and another method to calculate similarity.
Also take into account women under hormonal treatment because several studies showed contraceptive pills users make different mate choices, on average, compared to non-users. "Only short-term but not long-term partner preferences tend to vary with the menstrual cycle". 
 
Please remember: Personality traits are highly stable in persons over 25 years old to 45 years old (the group of persons who could be most interested in serious online dating) They have only minor changes in personality (less than 1 interval in a normative test) and the 16PF5 test will not "see" them because the output of the 16PF5 test are 16 variables STens (Standard Tens) taking integer values from 1 to 10. STens divide the score scale into ten units. STens have the advantage that they enable results to be thought of in terms of bands of scores, rather than absolute raw scores. These bands are narrow enough to distinguish statistically significant differences between candidates, but wide enough not to over emphasize minor differences between candidates.

 

Interesting and Controversial Chinese AI software judges

whether Chinese men aged 18-55 could be criminals based on facial features

Xiaolin Wu and Xi Zhang, researchers from Shanghai Jiao Tong University, released their paper on arXiv, an online open-sourced pre-print journal – but it has not yet been peer-reviewed or published officially.

The researchers singled out three features that they suggest can tell whether someone will be a criminal or not – lip curvature, eye inner corner distance, and the angle from the tip of the nose to the corners of the mouth.

http://www.dailymail.co.uk/sciencetech/article-3956826/Do-face-criminal-Controversial-AI-judges-law-abiding-based-look-like.html

PAPER "Too hot to trust:
http://onlinedatingsoundbarrier.blogspot.com.ar/2016/11/paper-too-hot-to-trust.html

PAPER: "Telling facial metrics: facial width is associated with testosterone levels in men"
http://onlinedatingsoundbarrier.blogspot.com.ar/2013/05/paper-telling-facial-metrics-facial.html

How facial features drive our first impressions
http://onlinedatingsoundbarrier.blogspot.com.ar/2014/07/how-facial-features-drive-our-first.html

article about Tinder at La Nación Newspaper
http://onlinedatingsoundbarrier.blogspot.com.ar/2014/11/article-about-tinder-at-la-nacion.html

about article "Bot Selects Tinder Dates For You"
http://onlinedatingsoundbarrier.blogspot.com.ar/2015/02/about-article-bot-selects-tinder-dates.html

NEW BOOK: Persönlichkeit – Auf der Suche nach unserer Individualität

http://link.springer.com/book/10.1007/978-3-662-48895-9

"BIG SIX statt BIG FIVE? Das Hexaco-Modell der Persönlichkeit"
http://onlinedatingsoundbarrier.blogspot.com.ar/2014/03/big-six-statt-big-five-das-hexaco.html
PAPER: A sixth personality domain that is independent of the Big Five domains:
http://onlinedatingsoundbarrier.blogspot.com.ar/2014/03/paper-sixth-personality-domain-that-is.html
The normative BIG5 model (a.k.a. Big Five, FFI, FFM, Five Factor Model, OCEAN model) used at many online dating sites with questionnaires to measure personality of daters had been proven/revealed as an incomplete and incorrect model to assess personality of persons. Now it was replaced by HEXACO test, a.k.a Big Six test.
The BIG5 normative personality test is the biggest mistake Psychologists made since several years ago.
The BIG5 is also known as the Five Factor Model theory of personality traits, a psychological model based on research by Paul Costa and Robert McCrae.
 
Online Dating sites have very big databases, in the range of 20,000,000 (twenty million) profiles, so the BIG 5 model or the HEXACO model are not enough for predictive purposes. That is why I suggest the 16PF5 test instead and another method to calculate similarity. I calculate similarity in personality patterns with (a proprietary) pattern recognition by correlation method. It takes into account the score and the trend to score of any pattern. Also it takes into account women under hormonal treatment because several studies showed contraceptive pills users make different mate choices, on average, compared to non-users. "Only short-term but not long-term partner preferences tend to vary with the menstrual cycle". 
Please remember: Personality traits are highly stable in persons over 25 years old to 45 years old (the group of persons who could be most interested in serious online dating) They have only minor changes in personality (less than 1 interval in a normative test) and the 16PF5 test will not "see" them because the output of the 16PF5 test are 16 variables STens (Standard Tens) taking integer values from 1 to 10. STens divide the score scale into ten units. STens have the advantage that they enable results to be thought of in terms of bands of scores, rather than absolute raw scores. These bands are narrow enough to distinguish statistically significant differences between candidates, but wide enough not to over emphasize minor differences between candidates.
http://onlinedatingsoundbarrier.blogspot.com.ar/2011/06/stability-and-change-of-personality.html
http://onlinedatingsoundbarrier.blogspot.com.ar/2010/09/personality-traits-are-highly-stable.html
http://onlinedatingsoundbarrier.blogspot.com.ar/2014/05/paper-personality-resilience-following.html
http://onlinedatingsoundbarrier.blogspot.com.ar/2014/05/examining-relationship-between-changes.html

Personality traits are highly stable in persons over 25 years old to 45 years old.
http://onlinedatingsoundbarrier.blogspot.com.ar/2010/04/personality-traits-are-highly-stable-in.html

The key to long-lasting romance is STRICT PERSONALITY SIMILARITY

But many online dating sites like eHarmony and its copycats like eDarling / EliteSingles, TeAmoRU, MiMediaManzana, eSynchrony and other are HOAXES.  
Another eHarmony style copycat: eSynchrony  http://onlinedatingsoundbarrier.blogspot.com.ar/2016/02/another-eharmony-style-copycat_18.html Another eHarmony style copycat: MiMediaManzana (from Peru)
http://onlinedatingsoundbarrier.blogspot.com.ar/2016/02/another-eharmony-style-copycat.html
Another eHarmony style copycat: TeAmoRU (from Russia)
http://onlinedatingsoundbarrier.blogspot.com.ar/2016/02/another-eharmony-style-copycat-teamoru.html
eDarling/EliteSingles are only copycats of eHarmony.
http://onlinedatingsoundbarrier.blogspot.com.ar/2016/02/edarling-german-version-homepage.html 
eHarmony Spanish version / ready / 3 months free
http://onlinedatingsoundbarrier.blogspot.com.ar/2016/02/eharmony-spanish-version-ready-3-months.html    
eHarmony, is a 15+++++ years old obsolete site and a HOAX, based on a big scientific fraud, only sustained by big marketing budget.  eHarmony is using the Big Five (Big5) normative test that was revealed as incomplete, incorrect and obsolete personality test. It was replaced by the Big Six a.k.a HEXACO test.
 
Also eHarmony has no Scientific proof its algorithm is better than searching by your own! http://onlinedatingsoundbarrier.blogspot.com.ar/2016/03/eharmony-uk-continues-brains-behind.html

Article and Paper: ... computers are better judges of personality than friends and family

Stanford researchers have found that computers can judge personality traits more accurately than one's friends and colleagues. In fact, artificial intelligence can draw inferences about a person as accurately as a spouse.
http://news.stanford.edu/news/2015/january/personality-computer-knows-011215.html

PAPER:  Computer-based personality judgments are more accurate than those made by humans
http://www.pnas.org/content/early/2015/01/07/1418680112.abstract

Nothing new.
http://onlinedatingsoundbarrier.blogspot.com.ar/2014/10/twitter-teams-with-ibm-for-business.html
but remember:  The Big Five normative personality test is obsolete, it has been proven as an incomplete and incorrect model of personality. The HEXACO (a.k.a. Big Six) is another oversimplification.   Online Dating sites OFFERING COMPATIBILITY MATCHING METHODS BASED ON PERSONALITY SIMILARITY have very big databases, in the range of 20,000,000 (twenty million) profiles, so the Big Five model or the HEXACO model are not enough for predictive purposes. That is why I suggest the 16PF5 test instead.
The same applies for Personality Based Recommender Systems.
http://onlinedatingsoundbarrier.blogspot.com.ar/2015/01/paper-personality-systems-framework.html