The Centrality of a Detailed Understanding
of your Audience
What publishing used to be like!
What publishing looks like now..
The Excellent
Way,

Waaay

Down…
Ultimately ads constitute a large fraction of our revenue!

And clearly we depend heavily on the top 2 to do well…
Ultimately ads constitute a large fraction of our revenue!

And clearly we depend heavily on the top 2 to do well.
“We are but barnacles living off the back of a massive ad whale…”
Ultimately ads constitute a large fraction of our revenue!

And clearly we depend heavily on the top 2 to do well.
“We are but barnacles living off the back of a massive ad whale…”
There’s actually a non-trivial symbiosis here
Instead of obligate commensalism…
It’s an asymmetric relationship, to be sure, but

publishers provide the ‘real estate’ over which 

these big whales make their revenue. And we

make their platforms sticky.
Publishers
• Like barnacles there’s a lot of competition for space
• The terms of that competition are dictated by black-box algorithms
• They get to keep all that good data
Not all smooth sailing on the back of the whale
Hopeless…?
How do we gain an advantage?
Can we predict our way to a competitive edge?
15
Marketing ApproachIlluminating the structure of social diffusion
To simplify we remove the leaves—uniques that arrive on our content through shared
links and only view. We’re left with just sharers.
In this case 40 sharers generate a cascade bringing in 2886 views - a 70x efficiency!
Next Steps!
Knowledge Graph
• Tracks intra-Mashable network of share
interactions

• Anonymously tracks browsing behavior and
usage attributes

• Allows us to observe and perhaps predict
cross network sharing events
18
Social cascades are fascinating…can we get a deeper view?
What can one do with this sort of
data?
Marketing ApproachArriving at a phenomenological model
The above is a cascade generated from a simulation with simple update rules.
It bears a strong resemblance to what we actually see in our share button experiment.
In fact, it turns out that a simple model of leave growth/viewer rate yields a model of share behavior with
predictive power!
Marketing ApproachVelocity
● Discovered right as it was
published
● Over 3,000 data points
collected
● Several points where story
trajectory changed & prediction
found & adapted.
● Early projections very
accurately modeled each
subseries in the total dataset.
Success!
22
• Facebook’s Accuracy: 79.5%
• Velocity’s Accuracy:
• 75% accurate after 5min across all content
• 80% accurate after 5hrs across all content
• 95% accurate after 1 day across all content
• 100% accurate after 5min for 70% of content!!
Marketing
Approach
Admiral Robert FitzRoy:
Marketing
Approach
Admiral Robert FitzRoy:
Data Scientist?
First Times Weather Forecast
Aug 1, 1861
Marketing
Approach
Admiral Robert FitzRoy:
a true Data Scientist
• attacked a problem for which there was no or mostly dirty
data - data collection and munging
• formulated/borrowed a model appropriate to the data
• crafted a classifier (for storm prediction) and aimed for
increasing accuracy
• over-inflated title - Meteorological Statist…
• under routine evaluation to justify his salary
Social cascades are fascinating…can we get a deeper view?
What can one do with this sort of
data?
1) Build Velocity
2) Segment your audience by graph properties
Marketing ApproachA great read!
arXiv:1506.03022 [cs.SI]
Marketing ApproachThe majority illusion!
The topological basis of the Majority Illusion
Marketing ApproachOur results!
5000 10000 15000 20000 25000
nth Engaging
Node
0.2
0.4
0.6
0.8
1.0
α
α(t) for Second Largest Cascade
Surprising!
KG
Through these sorts of properties:
• We’re able to identify community structure by
topic
• Make branded content campaigns
significantly more efficient
Conclusion
Publishers are heavily challenged
but
• It’s possible to carve out a data advantage
• Turn it into a predictive analytic capability
• And even a bit of competitive analysis

The Centrality of a Detailed Understanding of your Audience

  • 1.
    The Centrality ofa Detailed Understanding of your Audience
  • 2.
  • 3.
  • 4.
  • 6.
  • 7.
    Ultimately ads constitutea large fraction of our revenue! And clearly we depend heavily on the top 2 to do well…
  • 8.
    Ultimately ads constitutea large fraction of our revenue! And clearly we depend heavily on the top 2 to do well. “We are but barnacles living off the back of a massive ad whale…”
  • 9.
    Ultimately ads constitutea large fraction of our revenue! And clearly we depend heavily on the top 2 to do well. “We are but barnacles living off the back of a massive ad whale…”
  • 10.
    There’s actually anon-trivial symbiosis here Instead of obligate commensalism…
  • 11.
    It’s an asymmetricrelationship, to be sure, but publishers provide the ‘real estate’ over which these big whales make their revenue. And we make their platforms sticky. Publishers
  • 12.
    • Like barnaclesthere’s a lot of competition for space • The terms of that competition are dictated by black-box algorithms • They get to keep all that good data Not all smooth sailing on the back of the whale
  • 14.
    Hopeless…? How do wegain an advantage? Can we predict our way to a competitive edge?
  • 15.
  • 16.
    Marketing ApproachIlluminating thestructure of social diffusion To simplify we remove the leaves—uniques that arrive on our content through shared links and only view. We’re left with just sharers. In this case 40 sharers generate a cascade bringing in 2886 views - a 70x efficiency!
  • 17.
    Next Steps! Knowledge Graph •Tracks intra-Mashable network of share interactions • Anonymously tracks browsing behavior and usage attributes • Allows us to observe and perhaps predict cross network sharing events
  • 18.
  • 19.
    Social cascades arefascinating…can we get a deeper view? What can one do with this sort of data?
  • 20.
    Marketing ApproachArriving ata phenomenological model The above is a cascade generated from a simulation with simple update rules. It bears a strong resemblance to what we actually see in our share button experiment. In fact, it turns out that a simple model of leave growth/viewer rate yields a model of share behavior with predictive power!
  • 21.
    Marketing ApproachVelocity ● Discoveredright as it was published ● Over 3,000 data points collected ● Several points where story trajectory changed & prediction found & adapted. ● Early projections very accurately modeled each subseries in the total dataset. Success!
  • 22.
  • 23.
    • Facebook’s Accuracy:79.5% • Velocity’s Accuracy: • 75% accurate after 5min across all content • 80% accurate after 5hrs across all content • 95% accurate after 1 day across all content • 100% accurate after 5min for 70% of content!!
  • 26.
  • 27.
    Marketing Approach Admiral Robert FitzRoy: DataScientist? First Times Weather Forecast Aug 1, 1861
  • 28.
    Marketing Approach Admiral Robert FitzRoy: atrue Data Scientist • attacked a problem for which there was no or mostly dirty data - data collection and munging • formulated/borrowed a model appropriate to the data • crafted a classifier (for storm prediction) and aimed for increasing accuracy • over-inflated title - Meteorological Statist… • under routine evaluation to justify his salary
  • 29.
    Social cascades arefascinating…can we get a deeper view? What can one do with this sort of data? 1) Build Velocity 2) Segment your audience by graph properties
  • 30.
    Marketing ApproachA greatread! arXiv:1506.03022 [cs.SI]
  • 31.
    Marketing ApproachThe majorityillusion! The topological basis of the Majority Illusion
  • 32.
    Marketing ApproachOur results! 500010000 15000 20000 25000 nth Engaging Node 0.2 0.4 0.6 0.8 1.0 α α(t) for Second Largest Cascade Surprising!
  • 33.
    KG Through these sortsof properties: • We’re able to identify community structure by topic • Make branded content campaigns significantly more efficient
  • 34.
    Conclusion Publishers are heavilychallenged but • It’s possible to carve out a data advantage • Turn it into a predictive analytic capability • And even a bit of competitive analysis