Sunday, May 11, 2014

THE PGSC SCORE, PART III: A LOOK AT CONTESTANT PLACEMENT BASED ON AGE, GENDER, GEOGRAPHY AND GENRE (AGGG)

This is part III of an article about the PGSC score metric to quantify Idol placement:
PART I: THE PGSC SCORE, PART I: PGSC (PERFORMANCE, SONG FRESHNESS, GROWTH AND CONSISTENCY) VERSUS ACTUAL IDOL RANK
THE PGSC SCORE, PART II: UPDATED FEATURES (GEOGRAPHIC LOCATION, AGE AND GENRE)

*Part I contains the ranks of the Idol contestants on a season-by-season basis, based on the PGSC score. Think of this as the way the contestants should be ranked, assuming neutral ground and zero pimpage. It is also the way I would rank them.
*Part II ranks the Idol contestants based on PGSC score, according to genre.
*Part III, which is this article, attempts to use historical rank data since AI3 to put actual rank numbers into contestants, based on PGSC score, and based on the features added in at Part II. Unlike Part I, this is how we predict the audience would vote based on these features, and this model gets more informed as we get more data points (more seasons).

As explained in the title above, from part II of my study I utilized the four features I implemented for the PGSC score, and for greater accuracy of specific trends within the PGSC score, I used the 8-degree polynomial function  for each of those features, and took averages of the four. Remember, the smaller the number, the better!--that means you're ranked higher. The average rank corresponds to the average rank within the top ten--an average of 2.54, as was Scotty McCreery's case, means the model is predicting an outcome between 2nd and 3rd place for that particular contestant, or if that contestant is the highest rank of that season, as was in McCreery's case, then he/she is the predicted winner of the season. There are certain errors for sure, but it attempts to create a model using prior knowledge of past seasons to update the current knowledge on how to peg contestant placement. It's not Bayesian, but it's informed to a certain degree.


Saturday, May 10, 2014

THE PGSC SCORE, PART II: UPDATED FEATURES (GEOGRAPHIC LOCATION, AGE AND GENRE)

This is part II of an article about the PGSC score metric to quantify Idol placement:
PART I: THE PGSC SCORE, PART I: PGSC (PERFORMANCE, SONG FRESHNESS, GROWTH AND CONSISTENCY) VERSUS ACTUAL IDOL RANK

*Part I contains the ranks of the Idol contestants on a season-by-season basis, based on the PGSC score. Think of this as the way the contestants should be ranked, assuming neutral ground and zero pimpage. It is also the way I would rank them.
*Part II ranks the Idol contestants based on PGSC score, according to genre.

I've integrated several features used in previous models to this PGSC score model. Check it out below:


Friday, May 9, 2014

THE PGSC SCORE, PART I: PGSC (PERFORMANCE, SONG FRESHNESS, GROWTH AND CONSISTENCY) VERSUS ACTUAL IDOL RANK



So I recently created a model which I thought was able to perfectly encapsulate the general fan's assessments of the majority top ten American Idol contestants, starting from AI3 all the way to what we have now in AI13, independent of producer and judge manipulation. We start with AI3 because that's when we are able to chart one of our metrics, as will be explained below. This is the likely ranking of the contestant had every contestant played on a neutral ground.


Friday, April 25, 2014

THE WAYS A SONG CAN IMPACT THE CHR CHARTS



CHR is essentially "pop", or mainstream music. It gets the big audience numbers--for instance, right now, the #10 song on the pop charts sees similar audience numbers as the #1 song in country, which carries the next highest audience. The #12 song on pop, relatively speaking, can be the #1 song in HAC in audience share. #15 on pop gets #1 in rhythmic and urban. #24 in pop translates to about #1 in urban AC and AC. #28 in pop translates to #1 in alternative. So CHR is the major chart, and it more or less drives a ton of single sales: every song in the top 33 of CHR right now, for instance, is in the top 100 of itunes. With the exception of two songs, every song in the top 15 of CHR right now is in the top 21. This does not necessarily translate to album sales that hit expectations, given that acts that chart high in CHR tend to have outsized expectations compared to those that chart high in other genres, but when you drive singles sales, it builds up your brand, and over time should help album sales. There are acts (like Jason DeRulo, etc) that are more singles than album-driven, but many acts that hit it big in CHR, with over 100K in sales (a very good number in today's awful album-selling market).

What constitutes CHR? Here they are:

Friday, April 11, 2014

ALTERNATE WNTS, THE VOICE (SEASONS 5 AND 6)

We currently don't have anything that consolidates the quality of Voice performances, and the amount of buzz contestants have, into numbers. Well, with the power of social media...anything's possible. So we've used youtube shenanigans again and started normalizing things to illustrate the power of performance level across all the contestants who had their full auditions shown (sorry, Joshua Howard, and Austin whoever...among others, we can't quantify you). At this point, we have a ton of contestants so it's hard to normalize between so many, but here's what we have so far:

THE ALTERNATE WNTS, X FACTOR US (ACROSS ALL SEASONS)

I know the show's canceled, but having already done this for the Voice's Season 5 and the beginnings of Season 6 (see here) and also having done rudimentary work on AI13 with this metric (see here), we can make cross comparisons between the three shows. It's not super exact, but it's the best we can do with these numbers, since social media is everywhere for all three shows.

First, here's the contestant ranks, organized by buzz and performance levels. There will be revelations...

THE ALTERNATE WNTS, AMERICAN IDOL SEASON 13

So, we all know WNTS scours the interwebs to take aggregates of scores--whether from IDF, frauen blogs or other places. Lately, they have been taking in email submissions from people to submit their scores, because of the paucity of this stuff online.

I've got an alternate option: using the social media aspect to scour the performance value of contestants. But I'll also have something that WNTS doesn't have: a buzz meter. The social media aspect also presents an international flavor to the rankings, since it's just not centralized to America; this might make it different from WNTS, which tends to update their rankings East Coast first, then West Coast. Obviously, there's a ton of factors for what goes into the social media rating: the song being sung terribly is obviously one, but boring songs, the song being sung less well than the original, are all reasons for low(er) rankings. Higher rankings may involve creativity, good singing/emotion, good song selection, etc. The buzz meter shows who is really raking in the views. Let's note that I've consolidated each ranking for each particular night and used a Gaussian normalization to equalize the values between 0-100, much like what WNTS does. The performance ratings are somewhat similar, but also have some key differences. Take a look for yourself.

So far, I've done everything this season. Here's what I have: