Music Recommendation Engine or Radio?

You're probably familiar with Pandora. It is a music discovery site. I've played with it. It makes me uncomfortable, very quickly. And I think I've figured out why.

Pandora invariably steered me into unfamiliar music. Yes, it was sort of similar to other music that I like. But...

It wasn't music that I like. It was music that was like music I like.

That just isn't good enough.

Supposedly, this, and other similar services, are huge competitors. They are taking over radio's role as a place to discover new music. Maybe they are. It is worth thinking about.

By the way, there are other ways of building a music recommendation engine. You can focus on commonality of thought. That is, look for other songs that people who like your favorites also like. That is the logic behind the book recommendations you get from Amazon. It is the foundation of the Tune Genie music recommendation engine I designed a few years ago. This is perhaps better termed a music "rediscovery" engine, since people will often say something like "Yes! I remember that. Oh, I loved that song...".

And of course, this second kind of technology weaves itself into modern radio station research, with clustering and music fit analysis, geared to creating the most effectively managed experience for thousands of simultaneous listeners.

But let's return to the first issue: music discovery.

Maybe, for some people, it is okay for Pandora to suggest music they've never heard of. Maybe we need to understand this more than do the people at Pandora and the other music recommendation engines.

I think there are two things worth our spending some time thinking about.

1. What is the demand for new music discovery? This breaks down into lots of questions. What percent of people are looking to discover new music? How does that balance with their desire to hear their favorite current songs, and their all-time favorites? How does this demand/balance vary with age and sex and taste in music?

In fact, do we really know that there is a huge, unfulfilled demand that goes beyond the standard profile of 15-22 year old males, who have always shown disdain for commercial radio? Do we know that our problems with younger listeners are really about our not giving them enough music they've never heard before?

2. Do we do a decent job of introducing our listeners to new music? People discover new songs, and they become favorites. And a little later, it happens again with a different song. So, do we play our role well in supporting this?

I know that the conventional wisdom is that we don't. But I don't believe that we are powerless to change that. Most people have lives too busy to allow them to "program themselves" with toys like Pandora. We are experts at doing that, and we do have the time.

Here is my concern.

What if we have given up our power to do a good job of introducing people to new music? When everybody's budget supported weekly call-out music research, we could use our expertise, present new music that, based on our expert knowledge of both the music and our listeners, would often work. And with rapid feedback through music research, we could make corrections.

But the feedback loop isn't what it used to be.

Further, I don't know how many times I've heard a programmer tell me that they can't try adding a song simply because it was a huge hit in England (or wherever) and it sounds to them like it ought to work. They tell me that if they add anything ahead of a songs that one of the major labels is working, the calls to their manager, their format PD, their market PD and their regional PD will all get calls. Why isn't this guy with the program?

So, have we given our power to the labels? And have we shut our ears to listener feedback?

This worries me a little. How about you?

Maybe I Should Send Mark a Bill!

Mark Ramsey, in his Hear 2.0 blog, made reference to  RadioShift, a cool piece of software that allows you to schedule and record Internet radio stations. He calls it "DVR for your radio".

He's right. And it looks like it would be really cool. I clicked on the Buy It button. Whoops!! You've got to have an Apple computer to run it.

Yes, but now I want it. I could buy a Mac. Probably will, but not today, and not just to get RadioShift.

So I did the Google thing and found, for Windows Vista/XP, something called Replay A/V.

It looks like it might be okay. It does say you can "schedule and record" Internet radio.

I spent the money. Now I'll be the guinea pig. I'll come back to you with a full report. I can't actually compare it with RadioShift, but I'll let you know how well it works. I want to record a couple of European clients's midday shows, which of course air at about 2AM my time.

I'll let you know. And Mark, thanks! This really is a great idea, even for us who are stuck with boring computers.

Radio Stations: Stories of Marketing Genius - Not!

A recent blog from Jacobs Media contrasted Apple with radio. To recap: They noted that Steve Jobs is still marketing the iPod heavily, even though it sells like crazy. Contrast that to the General Manager who, when the ratings trends came out and were up, canceled the rest of the marketing buy.

I nearly fell down laughing. I had a very similar thing happen. In my case, it was KKFR, Phoenix, 1987. We designed our own TV spot. It was really good. We talked the GM into a small ad buy. We watched our cume, based on our in-house audience tracking, go from about 5% to 11%. Of course that wasn't accurate, but clearly the spot was helping us achieve "top of mind".

But when our little budget ran out, I went to the GM as asked for a little more. After all, how often can you actually see that a marketing campaign is working? You know what the answer was.

No.

The budget was spent. There was no more budget, even to achieve programming success.

Our new competitor, who was running commercial free though the ratings period, did not stop their marketing.

We seemed to be snatching defeat from the jaws of victory. And clearly, the example given in the Jacobs blog is the same.

Is this a normal part of our industry? I fear that all too often we have people in senior management positions who don't understand the product as an ongoing dialog with the listeners. They don't know that opportunities for growth don't appear magically in a spreadsheet column. And they do the craziest things in the name of this month's budget goals.

Apple gets it.

Two Professionals

Broadcast Architecture and Pinnacle Media are nice people to work with!

Normally, I apply my state-of-the-art music research tools to the analysis of research of my own design and to research that shares my preference for a semantic scale. We use phrases like "I don't like it", "It is one of my favorite songs" etc. Most music research for radio is done is this way.

But there are some companies that measure music preference with a "dial" device. In this approach, the respondent selects a value from 0 to 100 to indicate how much they like the song.

Two new clients have, within the past 3 weeks, needed me to work with "dial" tests. One test was conducted by Broadcast Architecture, the other by Pinnacle. I had not yet updated my new MusicVISTA software to deal with this methodology, so I spent about a week getting that done, and I was ready to rock.

The experience could not have been more pleasant. Bob Lawrence, the President of Pinnacle Media, guided me through the process of working with his data, and Elliott Wood, Senior Vice President at Broadcast Architecture, did the same.

To both, many thanks.

And perhaps best of all, I am now able to tap into yet another data gathering methodology, and help those stations pull every possible advantage from their investment in music research.

One more thing. Both companies include a very nice set of additional questions that go beyond the music opinions and increase the value you receive.

Minute by Minute Ratings?

I love analyzing ratings. I spent many years providing "InstantREPLAY" diary analysis for hundreds of radio stations.

And I'm sure that, if Arbitron makes the raw data available, we'll be able to do even more with the new PPM data.

Some Say: PPM Will Open Up A New World Of Incredible Detail

But. People are suggesting that you'll be able to see when bad song is aired, or a bad bit is done by the morning show.

If you're reading this, you're very likely an experienced programmer or air talent. You've spent a lot of time observing "normal" people as they listen to radio.

How Do People Actually Listen To Radio?

So let me ask you this question: Have you noticed that "normal" people tend to stop what they are doing and run to the radio every time they hear something they aren't excited about?

Let me ask you another question: Have you noticed that "normal" people tend to stop listening when they need to leave for work, pay attention in a conversation, start watching their favorite TV show, or get out of the car to go into the store?

Okay. I'm thinking you answered "NO" and "YES". If not, email me and explain how I'm confused. Because what I'm thinking at this point is that people live their lives, and radio tags along. They don't very often listen to radio is a very active way, focused like a laser beam on what is being aired.

My theory is that radio is a companion.

• It comes on and off at the convenience of the listener.
• Which station gets listened to depends on the mood of the listener, and which station they believe will likely support them at that moment.
• And if, over time, they find that their confidence in your station is misplaced, they will change their opinion. A different station will take your place.

Two Different Models

This is important. Because either...

• Radio listening is a process that involves mood, taste, and finding a station that is like a club you want to belong to.

or

• Radio is a surrogate iPod, and listeners are posed to signal their level of satisfaction with a quick flick of the dial or push of the button.

Which do you believe is the right model? To believe that PPM is going to move you into a world of minute by minute ratings analysis, you've got to have strong faith in the second possibility.

My belief has been that the first model is closer to reality. Should I reconsider?

Thank You! More to come...

Yesterday, September 1, Steve Casey Research began its 19th. year. No exact records exist, but we know that it is safe to say that we've provided some sort of help: programming consultation, music research system design, music test analysis, or ratings analysis, to more than 2,000 radio stations.

Only a small number of the people I've worked with will read this blog, but to you: "THANK YOU!" Words cannot express my gratitude for the support you've given me.

In the coming months, there is a lot more on the drawing board!

I'm expanding our focus on programming consultation. I've just started my work with the fine people at TV2 Radio, Denmark. And I hope to be announcing another project in the next few weeks.

I'll be seeing a lot of you at the NAB European Radio Conference in Barcelona, November 5. I'll be hosting a panel, with consultant Alan Burns and Heart, London head of programming Francis Currie. They will be showing us how they have designed successful AC stations that bring some new ideas to the format. Alan has created the Movin' format, and Heart continues to be the #1 station in one of the world's great radio cities.

You may be aware that the music research analysis I do is supported by a platform called MusicVISTA. What was important about that upgrade, completed just over a year ago, is that we were able to incorporate the very latest software development tools and standards. So, I've found it much easier than ever before to add new capabilities to the platform. When clients have ideas and requests, we are often able to take immediate action. You've noticed (I hope) the large number of changes in just this last year.

I've been blessed with some clients who are always looking for more, and have gathered a nice list of ideas, many of which will be developed in the next few months. I'm looking for more. Please don't be shy with your questions and ideas.

Finally, let me remind you that we are now going into the fall music testing season. A "mean scores only" test is not enough, and in fact can be very misleading. Don't do it!

You need to understand the proper focus for the station, whether you are drifting and in what way, and you need tools that show you how to balance and sequence the music. We have those tools. I hope you'll help make your upcoming year (and our 19th year) even more successful. Allow me to show you how to get everything possible from your efforts to understand your listeners' feelings about your music.