Social media & web analytics innovation procopio-2012-04
Upcoming SlideShare
Loading in...5
×

Like this? Share it with your network

Share

Social media & web analytics innovation procopio-2012-04

  • 307 views
Uploaded on

My presentation from the Social media & web analytics innovation conference April 2012 in San Francisco put on by theiegroup.com. ...

My presentation from the Social media & web analytics innovation conference April 2012 in San Francisco put on by theiegroup.com.

I cover examples of gaining insights on products from social media conversations

More in: Technology , Business
  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
    Be the first to comment
No Downloads

Views

Total Views
307
On Slideshare
307
From Embeds
0
Number of Embeds
0

Actions

Shares
Downloads
3
Comments
0
Likes
1

Embeds 0

No embeds

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

Cancel
    No notes for slide
  • July 11, 2012 HP Confidential
  • Our CI transformational model addresses CI with four stages to deliver on our business objectives. Each of these stages plays a critical role in delivering on customer needs. This will help to close the information asymmetry gap (the gap between what we want to know about our customers and what is “knowable”) Key components of this model Customer interaction – both simple and complex Infrastructure – intelligent plumbing to support interaction and analysis Analytics – 360 degree view of customer Insight usage – applying CI knowledge to our business objectives By using this approach, we will do a better job at growing and retaining our customers, improving our marketing effectiveness, and building hp customer loyalty. July 11, 2012 HP Confidential
  • Narrative: Customer sentiment is currently locked up in blobs of text – locating deep insights “is like finding a needle in a haystack.” Our two step process makes this easy for us. First, making sense and structure out of the unstructured data, and then second, linking that back to our known transactional world allows us to more quickly find the new insights. HP developed Project Fusion to bring this to life. Key Points: We use proprietary natural language processing and text analytics techniques to score the unstructured data. The scored data highlight potential insights to customer behavior and sentiment We can link scored data back to other structured information and databases for deeper analysis Transition statement: Unstructured data is powerful, but combing it with structured data is even more compelling… July 11, 2012 HP Confidential
  • Narrative: These two views together become very powerful in minimizing the gap. There are endless possibilities of how to position these to create value, but we are focusing on several strategic initiatives, one of which is new product launch insight. Key Points: These two data sets together are more powerful than either one individually. “The sum is greater than the sum of the parts. “ Transition statement: Let me tell you more about our journey from foundation to analytics… July 11, 2012 HP Confidential
  • July 11, 2012 HP Confidential
  • July 11, 2012 HP Confidential
  • July 11, 2012 HP Confidential
  • July 11, 2012 HP Confidential
  • July 11, 2012 HP Confidential
  • July 11, 2012 HP Confidential

Transcript

  • 1. S o c ia l in t e l l ig e n c e : a p p l y in g n e w in s ig h t s t o b u s in e s sM ic h a e l P r o c o p io@ M ic h a e l P r o c o p ioL in k e d In .c o m /in /M ic h a e l P r o c o p io1©C o p ©C oigphytr 2 0 1 t 02H e1 w lH et w -P a c k aa cd k D ervd e D e v e leonptmCeonm pCa nmyp, a .P y , L .P . yr ig h 0 0 e t l e t t -P r a lo pm t o Ln .
  • 2. C u s t o m e r In t e l l ig e n c e T r a n s f o r m a t io n Mo d e l Tr an s ac t io n s Demo grap h ic S y n d ic a t e d P r im a r S o c ia l D y n a m ic Gr o w a n d y M e d ia Pr e f e r e R e t a in Re s e a r nces your ch Cu s t o m e r s Im p r o v e 360 M a r k e t in g Information Asymmetry In f r a s t Cu s t o m e r V ie w E f f e c t iv e ructure nes s B u il d Br a n d Lo y a l t y Be y o n d Un s t r u c t Re a s o n Us e r D ig it a l In D ir e c ured Py s c h o g r Survey Br e a d t Data a p h ic Cr u m b s Ch an n e To u c h l H is t o r y2 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P .
  • 3. R e s e a r c h q u e s t io n s Fo c uW e d e v e l o p e d t w o h y p o t h e s is t o st e s t t h e b u s in e s s b e n e f it s f o rt h e p r o je c t H y p o t h e s is #1 A strong med ia signal for a prod uct may lead to increased sales/registrations. #2 A strong negative pol arity in med ia signal for a prod uct may lead to increased support tickets.3 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P .
  • 4. M a k in g s e n s e o f u n s t r u c t u r e d d a t a “I d o n ’t k n o w w h a t p e o p l e a r e c o m p l a in in g a b o u t r e g a r d in g t h e s o f t w a r e b u t it in s t a l l e d s e a m l e s s l y a n d is in t u it iv e in it s o p e r a t io n s . E v e n t h o u g h I a m d is s a t is f ie d w it h t h e p a p e r t r a y a l l t o g e t h e r I a m h a p p y w it h t h is p r in t e r .” Sentiment Attributes Attributes Measures4 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P .
  • 5. M in im iz in g t h e k n o w l e d g e g a p w it hm e r g in g u n s t r u c t u r e d w it h s t r u c t u r e dd ata P r o d u c t P r o f il e Behavior #purc h as es # # s e r v ic e prod uct t ic k e t s o rd ers lau n c h d ate 2 ,1 3 1 ,5 1 7 85 6 98 1 0 /1 /2 0 1 0 •S a l e s STRUCTURED DB •Fr e q u e n c y Product ID • Va l u e Pr o d u c t • S e r v ic e Un d e r s t a n d in g Product ID Perception UNSTRUCTURED DB • C a r t r id g e Pa p e r P r ic e P r in t e r Tr a y S e n t im e n t 0 +1 -1 +1 • In t e n t io n s5 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P . •
  • 6. F in d in g s – H y p o t h e s is A Hyp o t h e D r iv s is A strong med ia signal for a prod uct #1 Consumerr& Prof Reviews, e s may l ead to increased Consumer & Prof Ratings, sal es/registrations. Rating Source* Data Products Data Reviewed 384 Consumer reviews fromP h o t o s m a r t p r in t e r 1 Amazon, CNET and HP Forums  6 Professional reviews fromP h o t o s m a r t p r in t e r 2 CNET, PC World  51 5K purchases6 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P .
  • 7. F in d in g s – H y p o t h e s is #1 – A s t r o n g m e d ia s ig n a l f o r aP h o t o psrm d u ctt A a y l e a d t o oar m Analys is Res ults in c r e a s e d s a l e s /r e g is t r a t io n s . r = 0 .5 8 r = 0 .7 2 (e x c l u d e s h o l id a y s e a s o n ) •M e d iu m t o h ig h level o f C o r r e l a t io n •M e d ia s ig n a l f r o m consumer forums ten d s to fo llo w Pu r c h a s e s W e ig h t e d R a t in g purch as e tren d s (C o n s u m e r +7 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P . P r o f e s s io n a l )
  • 8. A strong med ia signal for aF in d in g s – H y p o t h e s is #1 product may l ead to increasedPh o t o s m a r t B . sales/registrations Analys is Res ults r = 0 .5 9 r = 0 .9 6 (e x c l u d e s h o l id a y s e a s o n ) •M e d iu m t o h ig h l e v e l o f C o r r e l a t io n •M e d ia s ig n a l f r o m consumer forums Pu r c h a W e ig h t e d R a t in g ten d s to fo llo w ses (C o n s u m e r + purch as e tren d s8 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P . P r o f e s s io n a l )
  • 9. Hypo t h Hypothesis e s is A strong med ia signal for a P a a t ia sl Str tu product may lead to increased ly sal / registrations. es C o n f ir m ed Possible Business Application Analysis/Findings • O p p o r t u n it ie s f o r O u t b o u n d M a r k e t in g • M o d e r a t e C o r r e l a t io n O p t im iz a t io n (m a r k e t in g b e t w e e n o v e r a l l m e d ia m ix – s p e n d , a u d ie n c e , s ig n a l a n d s a l e s t r e n d s ch an n el) • S t r o n g C o r r e l a t io n • In c r e a s e d s a l e s a n d w h e n a d ju s t e d f o r o p e r a t io n s f o r e c a s t a c c u r a c y b y m o n it o r in g s e a s o n a l it y9 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P . a n d m e a s u r in g
  • 10. F in d in g s – H y p o t h e s is #2 A strong negative polarity in med ia signal for a prod uct may– Ph o t o s m a r t A lead to increased support tickets Analys is Res ults r = — 0 .6 2 (O v e r a l l p r o d u c t q u a l it y ) r = — 0 .9 5 (P r in t Q u a l it y ) • H ig h C o r r e l a t io n • C o r r e l a t io n strength T ic k e t s /P u r Co n s u m e r in c r e a s e s a s t h e ch as e n e g a t iv e a t t r ib u t e 1 0 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v sl o p m e nt Cim p e n n, Lt . e e n t o m a y .P g r a n u l a r it y
  • 11. F in d in g s – H y p o t h e s is #2 A strong negative polarity in –Ph o t o s m a r t B med ia signal for a prod uct may lead to increased support tickets. Analys is Res ults r = — 0 .9 (O v e r a l l prod uct q u a l it y ) r = — 0 .7 (P r in t Q u a l it y ) T ic k e t s /P u r c h a s e C o n s u m e r n e g a t iv e s e n t im e n t • H ig h1 1 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P . C o r r e l a t io n
  • 12. F in d in g s – H y p o t h e s is #2 Hyp o t h es i D r iv e r s sA strong negative polarity in med ia signal • Consumerfor a product may lead to increased Sentiment Score • Prod uctsupport tickets. Attributes Dat a Products Data Reviewed  384 Consumer reviews and sentimentP h o t o s m a r t P r in t e r 1 from Amazon, CNET and HP ForumsP h o t o s m a r t P r in t e r 2  54K Service tickets Co n c lu s i Hypothesis Status Analysis/Findingss on Possible Business Application  S t r o n g c o r r e l a t io n b e t w e e n  O p e r a t io n a l E f f ic ie n c y : i.e . m a n a g in g t h e Confirmed n e g a t iv e m e d ia s ig n a l a n d c u s t o m e r Cu s t o m e r s u p p o r t r e s o u r c e s b as e d o n s upp o rt c alls . c o n s u m e r s e n t im e n t s ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P .1 2  P r o a c t iv e P r o d u c t q u a l it y v a l id a t io n a n d
  • 13. D EMO 11 3 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P .
  • 14. D E M O 2 – VAL U E F O R M O N E Y1 4 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P .
  • 15. D E M O 3 – R E M O V E T W IT T E R1 5 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P .
  • 16. D EMO 41 6 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P .
  • 17. D E M O 5 – R E M O V E VAL U E F O R M O N E Y1 7 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P .
  • 18. D E M O 6 – B R AN D P O S IT IO N1 8 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P .
  • 19. D E M O 7 – T IE T O IN T E R N AL D ATA1 9 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P .
  • 20. D E M O 8 – F IN D AD VO C A E S T20 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P .
  • 21. S o c ia l In t e l l ig e n c e Th e w a r r a n t y &s N H AN C E n AR R AN T Y &E o l u t io W c l a im s , q u a l it yC L AIM S M AN AG E M E N T man agemen t an dW IT H S O C IAL pro d uct d evelo pmen tIN T E L L IG E N C E d epartmen tsP R IM AR Y E U R O P E AN g a t h e r e d in f o r m a t io nAU T O M O T IV E M AN U F AC T U R E R r e l a t e d t o q u a l it y S it u a t io n is s u e s a n d p r o d u c t d efects through the w arran ty pro ces s . •T im e d e l a y in g e t t in g d ata21 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P . •L a b o r in t e n s iv e t o
  • 22. S o c ia l In t e l l ig e n c es o l u t io n S o l u t io n Re s u l t s E n h a n c e e x is t in g M o r e e f f e c t iv e s e a r c h a n d a n a l y s is a n a l y s is o f p l a t f o r m w it h S o c ia l s truc tured an d M e d ia d a t a unstructured Ea s e o f u s e f r o n t e n d , in f o r m a t io n l ik e “G o o g l e ” s e a r c h . Id e n t if y in g p o t e n t ia l En a b l e u s e r s t o d o d e f e c t s a n d q u a l it y in t u it iv e r o o t c a u s e is s u e s o v e r a m o n t h a n a l y s is , id e n t if y in g e a r l ie r t h r o u g h c a u s e c o n n e c t io n s s o c ia l m e d ia betw een w arran ty in f o r m a t io n c a s e s a n d S o c ia l M e d ia 22 ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P . U n d e r s t a n d in g
  • 23. T h a n k Yo u Yo u r @q u h a e t P r on o p? M ic e s l io c s io L in k e d In .c o m /in /M ic h a e l P23 r o c o p io ©C o p y r ig h t 2 0 1 0 H e w l e t t -P a c k a r d D e v e l o p m e n t C o m p a n y , L .P .