OPW – Oct 12 – Fernando is on the rampage again. This time he's ripping on recommender systems. He says that new recommender systems are rubbish. They provide many false positives. Ultimately, people don't know what they want, and what they say they want is often inaccurate. So I had to ask Nick and Gavin at IntroAnalytics what they thought? Here's their response…
We are more interested in the sweet-spot of "attraction", or grey areas of discovery and serendipity, rather than finding the bull's eye of an exact life-partner match. I'm quite annoyed with him that he is calling all dating recommender systems rubbish. Not sure he understand how sophisticated our work is. Is he going to claim that Netflix and Amazon's use of recommender systems is rubbish too?
I'll be launching InternetDatingScience.com at iDate Miami in January. We'll be making more sense of academia and next generation matchmaking for you. – Mark Brooks
We don’t mind a healthy debate. We are strongly willing to stand by the years of dedicated work (and innovation) we’ve put into introAnalytics anytime. Just ask our clients. Or anyone can contact us for a free trial to judge for themselves.
Let’s just keep it professional. Words like “plague” and “rubbish” not necessary in this context.
Yours Sincerely
Nick
We don’t mind a healthy debate. We are strongly willing to stand by the years of dedicated work (and innovation) we’ve put into introAnalytics anytime. Just ask our clients. Or anyone can contact us for a free trial to judge for themselves.
Let’s just keep it professional. Words like “plague” and “rubbish” not necessary in this context.
Yours Sincerely
Nick
Hello Nick:
Have you seen the next generation of recommender systems are going to include personality traits?
That is the only way to improve recommender systems, to include the personality traits of their users.
PAPERS
– “Using Personality Information in Collaborative Filtering for New Users”
“.. we compare the performances of rating-based similarity (RBS), personality-based similarity (PBS) and their hybrid (RPBS) in different start-up settings..”
Figure 1 shows how RPBS and PBS are better models than RBS (in a music dataset)
– “Design and User Issues in Personality-based Recommender Systems”
“.. The overall goal is to develop an efficient personality-based recommender system and to arrive at a series of design guidelines from the perspective of human computer interaction”
That paper calculates personality similarity between users: “.. we treat users’ personality characteristics as a vector as rating records. For each user u, his/her personality descriptor
Pu is a n-dimension vector. Consequently, the similarity between two user u and v can be computed as the Pearson correlation coefficient of their personality descriptors…”
but think for a minute! If you use those Personality-based Recommender Systems for Online Dating Purposes, then they are … guess … Compatibility Matching Algorithms!
If they use the Big5 to assess personality and the Pearson correlation coefficient to calculate similarity, they are nothing new, the same stuff already available in Compatibility Matching Algorithms.
Moreover if a visual personality quizz is used to assess personality of users, like the one offered by VisualDNA or Dewey Color System, it adds a lot of distortion to the measurement, the Personality-based Recommender System will perform worse than actual Compatibility Matching Algorithms!
Regards,
Fernando
Hello Nick:
Have you seen the next generation of recommender systems are going to include personality traits?
That is the only way to improve recommender systems, to include the personality traits of their users.
PAPERS
– “Using Personality Information in Collaborative Filtering for New Users”
“.. we compare the performances of rating-based similarity (RBS), personality-based similarity (PBS) and their hybrid (RPBS) in different start-up settings..”
Figure 1 shows how RPBS and PBS are better models than RBS (in a music dataset)
– “Design and User Issues in Personality-based Recommender Systems”
“.. The overall goal is to develop an efficient personality-based recommender system and to arrive at a series of design guidelines from the perspective of human computer interaction”
That paper calculates personality similarity between users: “.. we treat users’ personality characteristics as a vector as rating records. For each user u, his/her personality descriptor
Pu is a n-dimension vector. Consequently, the similarity between two user u and v can be computed as the Pearson correlation coefficient of their personality descriptors…”
but think for a minute! If you use those Personality-based Recommender Systems for Online Dating Purposes, then they are … guess … Compatibility Matching Algorithms!
If they use the Big5 to assess personality and the Pearson correlation coefficient to calculate similarity, they are nothing new, the same stuff already available in Compatibility Matching Algorithms.
Moreover if a visual personality quizz is used to assess personality of users, like the one offered by VisualDNA or Dewey Color System, it adds a lot of distortion to the measurement, the Personality-based Recommender System will perform worse than actual Compatibility Matching Algorithms!
Regards,
Fernando
Hi Fernando,
I’ve been reading this blog for a year or so now and have noticed you are probably one of the most prolific commenters on postings. However you don’t seem to have a good word to say about anyone or anything in the industry.
If we are all so bad how is the industry making so much money.
It’s really easy to critise anything and really difficult to build a business that makes money. Have you ever done the latter? If not why do you feel you are qualified to critise the entire industry.
Mark
Hi Fernando,
I’ve been reading this blog for a year or so now and have noticed you are probably one of the most prolific commenters on postings. However you don’t seem to have a good word to say about anyone or anything in the industry.
If we are all so bad how is the industry making so much money.
It’s really easy to critise anything and really difficult to build a business that makes money. Have you ever done the latter? If not why do you feel you are qualified to critise the entire industry.
Mark
Hi Fernando,
As someone who has followed this blog for many years, I have been aware of and have read your posts over this time… I have even agreed with some of them publicly. Go back 18 months or so and you were actually posting insightful and valuable observations on the online dating industry, which you were clearly passionate about and invested a great deal of time in following. For me, this ‘Fernando’ of old was worth listening to, someone whose opinion I wouldn’t always agree with but would want to hear.
Then something happened… I don’t know what but your comments and observations became highly negative and bitter. This negativity grew and manifested itself via comments not just of this blog but on virtually every single online dating story on the web that allowed the reader to post a comment. Why so negative… just what happened?
If you really don’t believe in the online dating industry and you personally think it is ‘a hoax’ then for your own well being I really think it is time for you to question why you continue to invest some much of your time in a tireless crusade of negativity towards it.
Online dating is the third largest paid for content business and despite your personal beliefs provides a valuable service to millions of single people across the globe looking to meet their Soulmate.
Honestly Fernando… life’s too short to be on a permanent downer… for your own well being I really hope you can return to the Fernando of old.
Matthew
Hi Fernando,
As someone who has followed this blog for many years, I have been aware of and have read your posts over this time… I have even agreed with some of them publicly. Go back 18 months or so and you were actually posting insightful and valuable observations on the online dating industry, which you were clearly passionate about and invested a great deal of time in following. For me, this ‘Fernando’ of old was worth listening to, someone whose opinion I wouldn’t always agree with but would want to hear.
Then something happened… I don’t know what but your comments and observations became highly negative and bitter. This negativity grew and manifested itself via comments not just of this blog but on virtually every single online dating story on the web that allowed the reader to post a comment. Why so negative… just what happened?
If you really don’t believe in the online dating industry and you personally think it is ‘a hoax’ then for your own well being I really think it is time for you to question why you continue to invest some much of your time in a tireless crusade of negativity towards it.
Online dating is the third largest paid for content business and despite your personal beliefs provides a valuable service to millions of single people across the globe looking to meet their Soulmate.
Honestly Fernando… life’s too short to be on a permanent downer… for your own well being I really hope you can return to the Fernando of old.
Matthew
Please people stop being so serious. If Fernando stops his ranting, who is actually going to comment on the stories. Keep going Fernando you have fans out there!!
Please people stop being so serious. If Fernando stops his ranting, who is actually going to comment on the stories. Keep going Fernando you have fans out there!!
The billion dollar question is: What constitutes a “successful relationship” and for which of the 2 parties are you acting more favourably in a test/algorithm/matching system?
Over 50% of marriages breakup. Others should break up but don’t. Others are held together because of religious/social reasons. Some casual relationships become serious. Some people don’t marry and have strong relationships.
Every relationship is as individual as the 2 people getting into it so how can people fall into a 16 category personality profile?
My guess is that maintaining a meaningful relationship between partners is harder than starting one. As people grow, needs change and complexities of relationships increase and decrease.
Surely we should “let love happen” between 2 people and hope for the best.
The billion dollar question is: What constitutes a “successful relationship” and for which of the 2 parties are you acting more favourably in a test/algorithm/matching system?
Over 50% of marriages breakup. Others should break up but don’t. Others are held together because of religious/social reasons. Some casual relationships become serious. Some people don’t marry and have strong relationships.
Every relationship is as individual as the 2 people getting into it so how can people fall into a 16 category personality profile?
My guess is that maintaining a meaningful relationship between partners is harder than starting one. As people grow, needs change and complexities of relationships increase and decrease.
Surely we should “let love happen” between 2 people and hope for the best.
“Every relationship is as individual as the 2 people getting into it so how can people fall into a 16 category personality profile?”
A 16 category personality profile is for ipsative tests like the MBTI used by PerfectMatch, the DISC used by ThomasKnowsPeople and the propietary test invented by Dr. Helen Fisher in Chemistry.
The 16PF5 normative personality test codifies personality with 16 independent variables taking integer values from 1 to 10 in stens (standardized tens).
(A) Warmth; (B) Reasoning; (C) Emotional Stability; (E) Dominance, (F) Liveliness; (G) RuleConsciousness; (H) Social Boldness; (I) Sensitivity; (L) Vigilance; (M) Abstractedness; (N) Privateness (O) Apprehension; (Q1) Openness to Change; (Q2) SelfReliance; (Q3) Perfectionism; (Q4) Tension.
The ensemble (whole set of different valid possibilities) of the 16PF5 is: 10E16, big number as All World Population is nearly 6.7 * 10E9
The 16PF5 result is a quantized pattern, like
John’s 16PF5 Profile A:6.B:7.C:6.E:8.F:9.G:6.H:7.I:7.L:8.M:7.N:2.O:5.Q1:8.Q2:7.Q3:3.Q4:4
Lucy’s 16PF5 Profile A:5.B:7.C:4.E:8.F:7.G:4.H:5.I:6.L:4.M:6.N:8.O:9.Q1:6.Q2:8.Q3:4.Q4:4
I had invented a high precision quantitative method to compare similarity between those quantized patterns, e.g.:
John’s pattern is 74.79865772% +/- 0.00000001% similar to Lucy’s.
“Every relationship is as individual as the 2 people getting into it so how can people fall into a 16 category personality profile?”
A 16 category personality profile is for ipsative tests like the MBTI used by PerfectMatch, the DISC used by ThomasKnowsPeople and the propietary test invented by Dr. Helen Fisher in Chemistry.
The 16PF5 normative personality test codifies personality with 16 independent variables taking integer values from 1 to 10 in stens (standardized tens).
(A) Warmth; (B) Reasoning; (C) Emotional Stability; (E) Dominance, (F) Liveliness; (G) RuleConsciousness; (H) Social Boldness; (I) Sensitivity; (L) Vigilance; (M) Abstractedness; (N) Privateness (O) Apprehension; (Q1) Openness to Change; (Q2) SelfReliance; (Q3) Perfectionism; (Q4) Tension.
The ensemble (whole set of different valid possibilities) of the 16PF5 is: 10E16, big number as All World Population is nearly 6.7 * 10E9
The 16PF5 result is a quantized pattern, like
John’s 16PF5 Profile A:6.B:7.C:6.E:8.F:9.G:6.H:7.I:7.L:8.M:7.N:2.O:5.Q1:8.Q2:7.Q3:3.Q4:4
Lucy’s 16PF5 Profile A:5.B:7.C:4.E:8.F:7.G:4.H:5.I:6.L:4.M:6.N:8.O:9.Q1:6.Q2:8.Q3:4.Q4:4
I had invented a high precision quantitative method to compare similarity between those quantized patterns, e.g.:
John’s pattern is 74.79865772% +/- 0.00000001% similar to Lucy’s.
I don’t get Fernando’s maths, but the product sounds interesting. I will be in Miami where hopefully it will be explained in laymans terms
I don’t get Fernando’s maths, but the product sounds interesting. I will be in Miami where hopefully it will be explained in laymans terms