designing a better online music store (by:larm 2008)

30
Designing a Better Online Music Store by:Larm 2008

Upload: vegard-sandvold

Post on 13-Dec-2014

289 views

Category:

Entertainment & Humor


0 download

DESCRIPTION

A better online music store is built on search and recommendation. It brings more money for rights holders, publishers and retailers, more visibility and promotion for artists, and more music and fun for consumers.

TRANSCRIPT

Page 1: Designing a Better Online Music Store (by:Larm 2008)

Designing a Better Online Music Store

by:Larm 2008

Page 2: Designing a Better Online Music Store (by:Larm 2008)

Vegard Sandvold

● Enterprise Search Consultant– Comperio AS (FAST

Search & Transfer)

● Music Technologist & Entreprenour– Musikkteknologen.no

– LiveRevolution.net

Page 3: Designing a Better Online Music Store (by:Larm 2008)

Outline

1. Why we need better online music stores

2. Power of The Long Tail

3. Role of recommender systems in e-commerce

4. Expert, social and content-based recommendations

5. Demo

6. Additional thoughts and conclusion

Page 4: Designing a Better Online Music Store (by:Larm 2008)
Page 5: Designing a Better Online Music Store (by:Larm 2008)

1.0

ShelvesClerk

http://flickr.com/photos/lynt/162883105/

Page 6: Designing a Better Online Music Store (by:Larm 2008)

1.5

Shelves

Clerk

Page 7: Designing a Better Online Music Store (by:Larm 2008)
Page 8: Designing a Better Online Music Store (by:Larm 2008)

Better... how?

● Rights Holders, Publishers and Retailers– «Make more money»

● Artists– «Visibility and promotion»

● Consumers– «Broaden my horizon»

– «Something new that will impress my friends»

– «I'm in the mood for some soft rock ballads»

Page 9: Designing a Better Online Music Store (by:Larm 2008)

Long Tail Economics

● The cost of shelf space online is ZERO● Therefore:

1. Make everything available

2. Help me find it

● «Recommender systems expose consumers to a larger selection of interesting and relevant music»

Page 10: Designing a Better Online Music Store (by:Larm 2008)

The Shape of The Long Tail

The Long Tail

The Hits

Items

Pop

ular

ity

Page 11: Designing a Better Online Music Store (by:Larm 2008)

Said in Another Way...

0

10

20

30

40

50

60

70

80

90

100

0 10 20 30 40 50 60 70 80 90 100

Products

Sal

es (

$)

1

10

100

1 10 100

Products

Sal

es (

$)

Page 12: Designing a Better Online Music Store (by:Larm 2008)

Source: «I Tube, You Tube, Everybody Tubes: Analyzing the World’s Largest User Generated Content Video System»,Cha et.al., ACM Internet Measurement Conference 2007.

Page 13: Designing a Better Online Music Store (by:Larm 2008)

What is a Recommender

● System that connects (relevant) items to items, items to users, and users to users

● Way to navigate large data collections● Content relevance filter● Important characteristics include:

– Transparency

– Familiarity vs. novelty

– Completeness

Page 14: Designing a Better Online Music Store (by:Larm 2008)

Orders of Information Management

1st order

Structuring

3rd order

Tagging and other

metadata

2nd order

Classification

Page 15: Designing a Better Online Music Store (by:Larm 2008)

Recommendation Strategies

1. Expert

2. Social

3. Content-based

Page 16: Designing a Better Online Music Store (by:Larm 2008)

Expert Recommendations

● «I'm telling you that you will like this, because I know a lot about music»

● Pros– Transparency of the recommendations

– Can differentiate between “good and bad” music, according to the expert

● Cons– Not personalized

– Limited coverage

– No scalingSource: Celma & Lamere, Music Recommendation Tutorial, ISMIR 2007

Page 17: Designing a Better Online Music Store (by:Larm 2008)

http://www.viruscomix.com/page398.html

Non-expert Recommendations

Page 18: Designing a Better Online Music Store (by:Larm 2008)

Social recommenders

● «You will like this, because it's popular with people like you»

● Pros– Works for and between everything

● Cons– Lack of transparency

– Already popular items stay popular (the rich get richer effect)

– Cold start, new items enter at the bottom

Page 19: Designing a Better Online Music Store (by:Larm 2008)

Source: Celma & Lamere, Music Recommendation Tutorial, ISMIR 2007

Artists Similar to U2

Page 20: Designing a Better Online Music Store (by:Larm 2008)

Small-world Networks

Page 21: Designing a Better Online Music Store (by:Larm 2008)
Page 22: Designing a Better Online Music Store (by:Larm 2008)

The Long Tail Reach of Amazon

Page 23: Designing a Better Online Music Store (by:Larm 2008)

Social Tagging

Pros● Order emerges from chaos

(folksonomies)● Layers of metadata

Cons● Polysemy, synonyms, spelling● Idiosyncracity● Sparsity

Page 24: Designing a Better Online Music Store (by:Larm 2008)

Content-based Recommendations

● «You will like this, because it sounds like something you already like»

● Objective musical similarity– Timbre, instrumentation, rhythm, tempo, intensity

● Pros– No popularity bias

– No cold-start

– No manual effort required

● Cons– Not so transparent

– Can't tell «good» from «bad»

Page 25: Designing a Better Online Music Store (by:Larm 2008)

Demo

Comperio Music Search

Page 26: Designing a Better Online Music Store (by:Larm 2008)

The Effect of CB Recommendations

Source: Celma & Lamere, Music Recommendation Tutorial, ISMIR 2007

Page 27: Designing a Better Online Music Store (by:Larm 2008)

User Ratings – Yes and No

● Very effective, but highly suggestive– We trust other people

– We tend to like what others like

● Can counteract Long Tail effects● This is viral marketing!

Page 28: Designing a Better Online Music Store (by:Larm 2008)

Viral Marketing

1. Social links and sharing

2. Widgets

Page 29: Designing a Better Online Music Store (by:Larm 2008)

Conclusion

● A Better Online Music Store is built on search and recommendation

● More money for Rights Holders, Publishers and Retailers

● Visibility and promotion for Artists● More music and fun for Consumers

Page 30: Designing a Better Online Music Store (by:Larm 2008)

Thank you!

● Check out «Widgets, Viral Marketing and Findability» by Andrew Dubber– 14:15 in this auditorium

Vegard Sandvold+47 48 23 92 32

[email protected]