SlideShare una empresa de Scribd logo
1 de 31
Descargar para leer sin conexión
A D A P T I V E P R I C I N G W I T H
M A C H I N E I N T E L L I G E N C E
MTL+ECOMMERCE
E VA N P R O D R O M O U
● Founder & CTO, Fuzzy.io
● Former CTO, Breather
● Founder, StatusNet
● Founder, Wikitravel
W H O I S T H I S TA L K F O R ?
● Involved in e-commerce
− “products or services on the Web or mobile”
● Technical understanding
● Decision-making power
W H AT I S “ A D A P T I V E P R I C I N G ” ?
• Changing the price of a product
• Based on the situation
• User attributes
• Product attributes
• Business attributes
W H Y A D A P T I V E P R I C I N G ?
● Profit maximization
● Competition
● Many large retailers use it
● Guide user behaviour
● Activation
● Retention
● Referral
R I S K S
● Too high = don’t convert
● Too low = cut into margin
− May be worthwhile to activate a customer
● Perception of fairness
I M P L E M E N TAT I O N O P T I O N S
● Procedural code
● Markets
● Machine learning
● Fuzzy logic
IF
THEN ELSEIF ELSE
IF
THEN ELSEIF ELSE
IF
THEN ELSEIF ELSE
IF
THEN ELSEIF ELSE
IF
THEN ELSE
IF
THEN ELSE
IF
THEN ELSE
IF
THEN ELSE
IF
THEN ELSE
IF
THEN ELSE
IF
THEN ELSE
IF
THEN ELSE
IF
THEN ELSEIF ELSE
IF
THEN ELSEIF ELSE
IF
THEN ELSEIF ELSE
IF
THEN ELSEIF ELSE
IF
THEN ELSE
IF
THEN ELSE
IF
THEN ELSE
IF
THEN ELSE
IF
THEN ELSE
IF
THEN ELSE
IF
THEN ELSE
P R O B L E M S W I T H P R O C E D U R A L C O D E
● Gets very complicated with multiple
inputs
● Brittle
● Hard to debug
● Hard to maintain
● Thresholds
M A R K E T- B A S E D S O L U T I O N S
● Require a market
● Require something close to real-time
bidding
● Require fungible product or service
− One seller is equivalent to another
M A C H I N E L E A R N I N G
● Requires corpus of training data
− May not be collected
− May be difficult to experiment
● Requires training process
● Unintuitive results
● Harder to audit
● Staff are expensive
F U Z Z Y L O G I C
● Fuzzy sets
− Intuitive categories like “old”, “new”, “good”, “warm”
● Degrees of membership
− 0 to 100%
● Real-world wisdom
− IF userAge IS new THEN discount IS high
F U Z Z Y L O G I C F O R A D A P T I V E P R I C I N G
• Pros
● Uses explicit business rules
● Doesn’t require large training corpus
● Smoothly-varying output — no discontinuities with thresholds
● Handles contradictions well
● Adding and removing inputs well
● Missing data works well
● Easier to audit
F U Z Z Y L O G I C F O R A D A P T I V E P R I C I N G
• Cons
• Requires numerical inputs
D I S C O U N T
● Not a fixed price
● Can use the same agent for multiple
products
● 0% = full price, 100% = free
● Bounded to prevent outrageous prices
W H AT FA C T O R S C A N
A F F E C T P R I C E ?
P R O D U C T P O P U L A R I T Y
● Sales/week
● Smoothes over variations by day-of-week
● Ideally, pre-calculated for previous week
C AT E G O RY P O P U L A R I T Y
● Similar to product popularity, but for
product category
S I T E P E R F O R M A N C E
● Site-wide sales for the week
● Can be in dollars, or # of sales
● Very site-specific
S A L E S P E R H O U R O F W E E K
● Discrepancies between weekday/
weekend, night/day
S A L E S P E R W E E K O F Y E A R
● Especially for seasonal products
● Best for established stores
● At least one year of sales!
U S E R R E C E N C Y
● How long ago did the user sign up?
U S E R A C T I VAT I O N
● Number of sales or dollars
M A R K E T P E N E T R AT I O N
● For geographical markets
● In number/million
O T H E R FA C T O R S
● Influencer
− Number of followers on Twitter
− Number of friends on Facebook
● Social network penetration
− Percentage of followers on Twitter who have
joined
− Percentage of friends on Facebook who have
joined
R U L E S
● Map input factors to output discount
● Usually linear
● Occasionally inversely linear
● More complex rules possible
I N T E G R AT I N G W I T H S T O R E
S O F T WA R E
● Using an SDK
● Or a plugin
F U Z Z Y L E A R N I N G
● In production
● Feedback loop based on profit margin
on the sale
● 0% = no conversion
● Varies fuzzy set boundaries
● Varies weights of fuzzy rules
T H A N K S
Evan Prodromou
evan@fuzzy.io
https://fuzzy.io/

Más contenido relacionado

Similar a Adaptive Pricing with Machine Intelligence

How to enrich eRetail consumer experience | Iksula
How to enrich eRetail consumer experience | Iksula How to enrich eRetail consumer experience | Iksula
How to enrich eRetail consumer experience | Iksula Iksula
 
Turn a Profit- Introduction to Conversion Optimisation
Turn a Profit- Introduction to Conversion OptimisationTurn a Profit- Introduction to Conversion Optimisation
Turn a Profit- Introduction to Conversion OptimisationBjarne Viken
 
How to Crush Your 2016 Marketing Goals with Better Reporting
How to Crush Your 2016 Marketing Goals with Better ReportingHow to Crush Your 2016 Marketing Goals with Better Reporting
How to Crush Your 2016 Marketing Goals with Better ReportingJaxzenMarketing
 
Types of ecommerce business models
Types of ecommerce business modelsTypes of ecommerce business models
Types of ecommerce business modelsRyan Ruud
 
Data Wrangling Questionnaire
Data Wrangling QuestionnaireData Wrangling Questionnaire
Data Wrangling QuestionnaireMimi Brown
 
Maximizing the ROI of Gainsight
Maximizing the ROI of GainsightMaximizing the ROI of Gainsight
Maximizing the ROI of GainsightGainsight
 
Web Traffic Acquisition: challenges and opportunities in 2018
Web Traffic Acquisition: challenges and opportunities in 2018Web Traffic Acquisition: challenges and opportunities in 2018
Web Traffic Acquisition: challenges and opportunities in 2018Paolo Margari
 
Presentation on developments in hiring and fintech for HKU Executive certific...
Presentation on developments in hiring and fintech for HKU Executive certific...Presentation on developments in hiring and fintech for HKU Executive certific...
Presentation on developments in hiring and fintech for HKU Executive certific...Kok Tong (K.T.) Khoo
 
Sales Hacking for Startups by @TammyCamp of @500Startups
Sales Hacking for Startups by @TammyCamp of @500StartupsSales Hacking for Startups by @TammyCamp of @500Startups
Sales Hacking for Startups by @TammyCamp of @500StartupsTammy Camp
 
Making a business plan
Making a business planMaking a business plan
Making a business planAtul Puri
 
Scaling for Success: A Strategic Approach to Product Video
Scaling for Success: A Strategic Approach to Product VideoScaling for Success: A Strategic Approach to Product Video
Scaling for Success: A Strategic Approach to Product VideoInvodo
 
Growth Framework for Consumer Startups
Growth Framework for Consumer StartupsGrowth Framework for Consumer Startups
Growth Framework for Consumer StartupsP J
 
Design & usability for increased conversion (MeetMagento Germany 2015)
Design & usability for increased conversion (MeetMagento Germany 2015)Design & usability for increased conversion (MeetMagento Germany 2015)
Design & usability for increased conversion (MeetMagento Germany 2015)Vlad Stanescu
 
How HubSpot's Reporting Tool Will Revolutionize Your Company
How HubSpot's Reporting Tool Will Revolutionize Your CompanyHow HubSpot's Reporting Tool Will Revolutionize Your Company
How HubSpot's Reporting Tool Will Revolutionize Your CompanyJaxzenMarketing
 
Automated Bidding: Deriving Smart Insights - Sergio Cano
Automated Bidding: Deriving Smart Insights - Sergio CanoAutomated Bidding: Deriving Smart Insights - Sergio Cano
Automated Bidding: Deriving Smart Insights - Sergio CanoState of Search Conference
 
Ross Chayka. How to validate your startup/product idea?
Ross Chayka. How to validate your startup/product idea?Ross Chayka. How to validate your startup/product idea?
Ross Chayka. How to validate your startup/product idea?Rostyslav Chayka
 

Similar a Adaptive Pricing with Machine Intelligence (20)

How to enrich eRetail consumer experience | Iksula
How to enrich eRetail consumer experience | Iksula How to enrich eRetail consumer experience | Iksula
How to enrich eRetail consumer experience | Iksula
 
Turn a Profit- Introduction to Conversion Optimisation
Turn a Profit- Introduction to Conversion OptimisationTurn a Profit- Introduction to Conversion Optimisation
Turn a Profit- Introduction to Conversion Optimisation
 
How to Crush Your 2016 Marketing Goals with Better Reporting
How to Crush Your 2016 Marketing Goals with Better ReportingHow to Crush Your 2016 Marketing Goals with Better Reporting
How to Crush Your 2016 Marketing Goals with Better Reporting
 
Types of ecommerce business models
Types of ecommerce business modelsTypes of ecommerce business models
Types of ecommerce business models
 
Data Wrangling Questionnaire
Data Wrangling QuestionnaireData Wrangling Questionnaire
Data Wrangling Questionnaire
 
Maximizing the ROI of Gainsight
Maximizing the ROI of GainsightMaximizing the ROI of Gainsight
Maximizing the ROI of Gainsight
 
Hc philly-vandernick
Hc philly-vandernickHc philly-vandernick
Hc philly-vandernick
 
Web Traffic Acquisition: challenges and opportunities in 2018
Web Traffic Acquisition: challenges and opportunities in 2018Web Traffic Acquisition: challenges and opportunities in 2018
Web Traffic Acquisition: challenges and opportunities in 2018
 
Presentation on developments in hiring and fintech for HKU Executive certific...
Presentation on developments in hiring and fintech for HKU Executive certific...Presentation on developments in hiring and fintech for HKU Executive certific...
Presentation on developments in hiring and fintech for HKU Executive certific...
 
Sales Hacking for Startups by @TammyCamp of @500Startups
Sales Hacking for Startups by @TammyCamp of @500StartupsSales Hacking for Startups by @TammyCamp of @500Startups
Sales Hacking for Startups by @TammyCamp of @500Startups
 
Measure and optimize
Measure and optimizeMeasure and optimize
Measure and optimize
 
Making a business plan
Making a business planMaking a business plan
Making a business plan
 
Scaling for Success: A Strategic Approach to Product Video
Scaling for Success: A Strategic Approach to Product VideoScaling for Success: A Strategic Approach to Product Video
Scaling for Success: A Strategic Approach to Product Video
 
Growth Framework for Consumer Startups
Growth Framework for Consumer StartupsGrowth Framework for Consumer Startups
Growth Framework for Consumer Startups
 
Design & usability for increased conversion (MeetMagento Germany 2015)
Design & usability for increased conversion (MeetMagento Germany 2015)Design & usability for increased conversion (MeetMagento Germany 2015)
Design & usability for increased conversion (MeetMagento Germany 2015)
 
BoSUSA20 Online | Matt Lerner | Metrics that Matter
BoSUSA20 Online | Matt Lerner | Metrics that Matter BoSUSA20 Online | Matt Lerner | Metrics that Matter
BoSUSA20 Online | Matt Lerner | Metrics that Matter
 
How HubSpot's Reporting Tool Will Revolutionize Your Company
How HubSpot's Reporting Tool Will Revolutionize Your CompanyHow HubSpot's Reporting Tool Will Revolutionize Your Company
How HubSpot's Reporting Tool Will Revolutionize Your Company
 
Automated Bidding: Deriving Smart Insights - Sergio Cano
Automated Bidding: Deriving Smart Insights - Sergio CanoAutomated Bidding: Deriving Smart Insights - Sergio Cano
Automated Bidding: Deriving Smart Insights - Sergio Cano
 
ROUNDTABLE 2016: BRIGHT
ROUNDTABLE 2016: BRIGHTROUNDTABLE 2016: BRIGHT
ROUNDTABLE 2016: BRIGHT
 
Ross Chayka. How to validate your startup/product idea?
Ross Chayka. How to validate your startup/product idea?Ross Chayka. How to validate your startup/product idea?
Ross Chayka. How to validate your startup/product idea?
 

Último

AlbaniaDreamin24 - How to easily use an API with Flows
AlbaniaDreamin24 - How to easily use an API with FlowsAlbaniaDreamin24 - How to easily use an API with Flows
AlbaniaDreamin24 - How to easily use an API with FlowsThierry TROUIN ☁
 
Russian Call Girls in Kolkata Ishita 🤌 8250192130 🚀 Vip Call Girls Kolkata
Russian Call Girls in Kolkata Ishita 🤌  8250192130 🚀 Vip Call Girls KolkataRussian Call Girls in Kolkata Ishita 🤌  8250192130 🚀 Vip Call Girls Kolkata
Russian Call Girls in Kolkata Ishita 🤌 8250192130 🚀 Vip Call Girls Kolkataanamikaraghav4
 
Best VIP Call Girls Noida Sector 75 Call Me: 8448380779
Best VIP Call Girls Noida Sector 75 Call Me: 8448380779Best VIP Call Girls Noida Sector 75 Call Me: 8448380779
Best VIP Call Girls Noida Sector 75 Call Me: 8448380779Delhi Call girls
 
A Good Girl's Guide to Murder (A Good Girl's Guide to Murder, #1)
A Good Girl's Guide to Murder (A Good Girl's Guide to Murder, #1)A Good Girl's Guide to Murder (A Good Girl's Guide to Murder, #1)
A Good Girl's Guide to Murder (A Good Girl's Guide to Murder, #1)Christopher H Felton
 
VIP 7001035870 Find & Meet Hyderabad Call Girls Dilsukhnagar high-profile Cal...
VIP 7001035870 Find & Meet Hyderabad Call Girls Dilsukhnagar high-profile Cal...VIP 7001035870 Find & Meet Hyderabad Call Girls Dilsukhnagar high-profile Cal...
VIP 7001035870 Find & Meet Hyderabad Call Girls Dilsukhnagar high-profile Cal...aditipandeya
 
象限策略:Google Workspace 与 Microsoft 365 对业务的影响 .pdf
象限策略:Google Workspace 与 Microsoft 365 对业务的影响 .pdf象限策略:Google Workspace 与 Microsoft 365 对业务的影响 .pdf
象限策略:Google Workspace 与 Microsoft 365 对业务的影响 .pdfkeithzhangding
 
Gram Darshan PPT cyber rural in villages of india
Gram Darshan PPT cyber rural  in villages of indiaGram Darshan PPT cyber rural  in villages of india
Gram Darshan PPT cyber rural in villages of indiaimessage0108
 
Call Girls in East Of Kailash 9711199171 Delhi Enjoy Call Girls With Our Escorts
Call Girls in East Of Kailash 9711199171 Delhi Enjoy Call Girls With Our EscortsCall Girls in East Of Kailash 9711199171 Delhi Enjoy Call Girls With Our Escorts
Call Girls in East Of Kailash 9711199171 Delhi Enjoy Call Girls With Our Escortsindian call girls near you
 
Russian Call Girls in Kolkata Samaira 🤌 8250192130 🚀 Vip Call Girls Kolkata
Russian Call Girls in Kolkata Samaira 🤌  8250192130 🚀 Vip Call Girls KolkataRussian Call Girls in Kolkata Samaira 🤌  8250192130 🚀 Vip Call Girls Kolkata
Russian Call Girls in Kolkata Samaira 🤌 8250192130 🚀 Vip Call Girls Kolkataanamikaraghav4
 
VIP 7001035870 Find & Meet Hyderabad Call Girls LB Nagar high-profile Call Girl
VIP 7001035870 Find & Meet Hyderabad Call Girls LB Nagar high-profile Call GirlVIP 7001035870 Find & Meet Hyderabad Call Girls LB Nagar high-profile Call Girl
VIP 7001035870 Find & Meet Hyderabad Call Girls LB Nagar high-profile Call Girladitipandeya
 
FULL ENJOY Call Girls In Mayur Vihar Delhi Contact Us 8377087607
FULL ENJOY Call Girls In Mayur Vihar Delhi Contact Us 8377087607FULL ENJOY Call Girls In Mayur Vihar Delhi Contact Us 8377087607
FULL ENJOY Call Girls In Mayur Vihar Delhi Contact Us 8377087607dollysharma2066
 
Git and Github workshop GDSC MLRITM
Git and Github  workshop GDSC MLRITMGit and Github  workshop GDSC MLRITM
Git and Github workshop GDSC MLRITMgdsc13
 
Call Girls In Mumbai Central Mumbai ❤️ 9920874524 👈 Cash on Delivery
Call Girls In Mumbai Central Mumbai ❤️ 9920874524 👈 Cash on DeliveryCall Girls In Mumbai Central Mumbai ❤️ 9920874524 👈 Cash on Delivery
Call Girls In Mumbai Central Mumbai ❤️ 9920874524 👈 Cash on Deliverybabeytanya
 
定制(CC毕业证书)美国美国社区大学毕业证成绩单原版一比一
定制(CC毕业证书)美国美国社区大学毕业证成绩单原版一比一定制(CC毕业证书)美国美国社区大学毕业证成绩单原版一比一
定制(CC毕业证书)美国美国社区大学毕业证成绩单原版一比一3sw2qly1
 
How is AI changing journalism? (v. April 2024)
How is AI changing journalism? (v. April 2024)How is AI changing journalism? (v. April 2024)
How is AI changing journalism? (v. April 2024)Damian Radcliffe
 
Call Girls South Delhi Delhi reach out to us at ☎ 9711199012
Call Girls South Delhi Delhi reach out to us at ☎ 9711199012Call Girls South Delhi Delhi reach out to us at ☎ 9711199012
Call Girls South Delhi Delhi reach out to us at ☎ 9711199012rehmti665
 
定制(UAL学位证)英国伦敦艺术大学毕业证成绩单原版一比一
定制(UAL学位证)英国伦敦艺术大学毕业证成绩单原版一比一定制(UAL学位证)英国伦敦艺术大学毕业证成绩单原版一比一
定制(UAL学位证)英国伦敦艺术大学毕业证成绩单原版一比一Fs
 
Denver Web Design brochure for public viewing
Denver Web Design brochure for public viewingDenver Web Design brochure for public viewing
Denver Web Design brochure for public viewingbigorange77
 

Último (20)

AlbaniaDreamin24 - How to easily use an API with Flows
AlbaniaDreamin24 - How to easily use an API with FlowsAlbaniaDreamin24 - How to easily use an API with Flows
AlbaniaDreamin24 - How to easily use an API with Flows
 
Russian Call Girls in Kolkata Ishita 🤌 8250192130 🚀 Vip Call Girls Kolkata
Russian Call Girls in Kolkata Ishita 🤌  8250192130 🚀 Vip Call Girls KolkataRussian Call Girls in Kolkata Ishita 🤌  8250192130 🚀 Vip Call Girls Kolkata
Russian Call Girls in Kolkata Ishita 🤌 8250192130 🚀 Vip Call Girls Kolkata
 
Best VIP Call Girls Noida Sector 75 Call Me: 8448380779
Best VIP Call Girls Noida Sector 75 Call Me: 8448380779Best VIP Call Girls Noida Sector 75 Call Me: 8448380779
Best VIP Call Girls Noida Sector 75 Call Me: 8448380779
 
A Good Girl's Guide to Murder (A Good Girl's Guide to Murder, #1)
A Good Girl's Guide to Murder (A Good Girl's Guide to Murder, #1)A Good Girl's Guide to Murder (A Good Girl's Guide to Murder, #1)
A Good Girl's Guide to Murder (A Good Girl's Guide to Murder, #1)
 
VIP 7001035870 Find & Meet Hyderabad Call Girls Dilsukhnagar high-profile Cal...
VIP 7001035870 Find & Meet Hyderabad Call Girls Dilsukhnagar high-profile Cal...VIP 7001035870 Find & Meet Hyderabad Call Girls Dilsukhnagar high-profile Cal...
VIP 7001035870 Find & Meet Hyderabad Call Girls Dilsukhnagar high-profile Cal...
 
象限策略:Google Workspace 与 Microsoft 365 对业务的影响 .pdf
象限策略:Google Workspace 与 Microsoft 365 对业务的影响 .pdf象限策略:Google Workspace 与 Microsoft 365 对业务的影响 .pdf
象限策略:Google Workspace 与 Microsoft 365 对业务的影响 .pdf
 
Gram Darshan PPT cyber rural in villages of india
Gram Darshan PPT cyber rural  in villages of indiaGram Darshan PPT cyber rural  in villages of india
Gram Darshan PPT cyber rural in villages of india
 
Call Girls in East Of Kailash 9711199171 Delhi Enjoy Call Girls With Our Escorts
Call Girls in East Of Kailash 9711199171 Delhi Enjoy Call Girls With Our EscortsCall Girls in East Of Kailash 9711199171 Delhi Enjoy Call Girls With Our Escorts
Call Girls in East Of Kailash 9711199171 Delhi Enjoy Call Girls With Our Escorts
 
Russian Call Girls in Kolkata Samaira 🤌 8250192130 🚀 Vip Call Girls Kolkata
Russian Call Girls in Kolkata Samaira 🤌  8250192130 🚀 Vip Call Girls KolkataRussian Call Girls in Kolkata Samaira 🤌  8250192130 🚀 Vip Call Girls Kolkata
Russian Call Girls in Kolkata Samaira 🤌 8250192130 🚀 Vip Call Girls Kolkata
 
VIP 7001035870 Find & Meet Hyderabad Call Girls LB Nagar high-profile Call Girl
VIP 7001035870 Find & Meet Hyderabad Call Girls LB Nagar high-profile Call GirlVIP 7001035870 Find & Meet Hyderabad Call Girls LB Nagar high-profile Call Girl
VIP 7001035870 Find & Meet Hyderabad Call Girls LB Nagar high-profile Call Girl
 
FULL ENJOY Call Girls In Mayur Vihar Delhi Contact Us 8377087607
FULL ENJOY Call Girls In Mayur Vihar Delhi Contact Us 8377087607FULL ENJOY Call Girls In Mayur Vihar Delhi Contact Us 8377087607
FULL ENJOY Call Girls In Mayur Vihar Delhi Contact Us 8377087607
 
Model Call Girl in Jamuna Vihar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in  Jamuna Vihar Delhi reach out to us at 🔝9953056974🔝Model Call Girl in  Jamuna Vihar Delhi reach out to us at 🔝9953056974🔝
Model Call Girl in Jamuna Vihar Delhi reach out to us at 🔝9953056974🔝
 
Git and Github workshop GDSC MLRITM
Git and Github  workshop GDSC MLRITMGit and Github  workshop GDSC MLRITM
Git and Github workshop GDSC MLRITM
 
Call Girls In Mumbai Central Mumbai ❤️ 9920874524 👈 Cash on Delivery
Call Girls In Mumbai Central Mumbai ❤️ 9920874524 👈 Cash on DeliveryCall Girls In Mumbai Central Mumbai ❤️ 9920874524 👈 Cash on Delivery
Call Girls In Mumbai Central Mumbai ❤️ 9920874524 👈 Cash on Delivery
 
定制(CC毕业证书)美国美国社区大学毕业证成绩单原版一比一
定制(CC毕业证书)美国美国社区大学毕业证成绩单原版一比一定制(CC毕业证书)美国美国社区大学毕业证成绩单原版一比一
定制(CC毕业证书)美国美国社区大学毕业证成绩单原版一比一
 
How is AI changing journalism? (v. April 2024)
How is AI changing journalism? (v. April 2024)How is AI changing journalism? (v. April 2024)
How is AI changing journalism? (v. April 2024)
 
Call Girls South Delhi Delhi reach out to us at ☎ 9711199012
Call Girls South Delhi Delhi reach out to us at ☎ 9711199012Call Girls South Delhi Delhi reach out to us at ☎ 9711199012
Call Girls South Delhi Delhi reach out to us at ☎ 9711199012
 
定制(UAL学位证)英国伦敦艺术大学毕业证成绩单原版一比一
定制(UAL学位证)英国伦敦艺术大学毕业证成绩单原版一比一定制(UAL学位证)英国伦敦艺术大学毕业证成绩单原版一比一
定制(UAL学位证)英国伦敦艺术大学毕业证成绩单原版一比一
 
Denver Web Design brochure for public viewing
Denver Web Design brochure for public viewingDenver Web Design brochure for public viewing
Denver Web Design brochure for public viewing
 
Rohini Sector 26 Call Girls Delhi 9999965857 @Sabina Saikh No Advance
Rohini Sector 26 Call Girls Delhi 9999965857 @Sabina Saikh No AdvanceRohini Sector 26 Call Girls Delhi 9999965857 @Sabina Saikh No Advance
Rohini Sector 26 Call Girls Delhi 9999965857 @Sabina Saikh No Advance
 

Adaptive Pricing with Machine Intelligence

  • 1. A D A P T I V E P R I C I N G W I T H M A C H I N E I N T E L L I G E N C E MTL+ECOMMERCE
  • 2. E VA N P R O D R O M O U ● Founder & CTO, Fuzzy.io ● Former CTO, Breather ● Founder, StatusNet ● Founder, Wikitravel
  • 3. W H O I S T H I S TA L K F O R ? ● Involved in e-commerce − “products or services on the Web or mobile” ● Technical understanding ● Decision-making power
  • 4. W H AT I S “ A D A P T I V E P R I C I N G ” ? • Changing the price of a product • Based on the situation • User attributes • Product attributes • Business attributes
  • 5. W H Y A D A P T I V E P R I C I N G ? ● Profit maximization ● Competition ● Many large retailers use it ● Guide user behaviour ● Activation ● Retention ● Referral
  • 6. R I S K S ● Too high = don’t convert ● Too low = cut into margin − May be worthwhile to activate a customer ● Perception of fairness
  • 7. I M P L E M E N TAT I O N O P T I O N S ● Procedural code ● Markets ● Machine learning ● Fuzzy logic
  • 8. IF THEN ELSEIF ELSE IF THEN ELSEIF ELSE IF THEN ELSEIF ELSE IF THEN ELSEIF ELSE IF THEN ELSE IF THEN ELSE IF THEN ELSE IF THEN ELSE IF THEN ELSE IF THEN ELSE IF THEN ELSE IF THEN ELSE IF THEN ELSEIF ELSE IF THEN ELSEIF ELSE IF THEN ELSEIF ELSE IF THEN ELSEIF ELSE IF THEN ELSE IF THEN ELSE IF THEN ELSE IF THEN ELSE IF THEN ELSE IF THEN ELSE IF THEN ELSE
  • 9. P R O B L E M S W I T H P R O C E D U R A L C O D E ● Gets very complicated with multiple inputs ● Brittle ● Hard to debug ● Hard to maintain ● Thresholds
  • 10.
  • 11. M A R K E T- B A S E D S O L U T I O N S ● Require a market ● Require something close to real-time bidding ● Require fungible product or service − One seller is equivalent to another
  • 12.
  • 13. M A C H I N E L E A R N I N G ● Requires corpus of training data − May not be collected − May be difficult to experiment ● Requires training process ● Unintuitive results ● Harder to audit ● Staff are expensive
  • 14. F U Z Z Y L O G I C ● Fuzzy sets − Intuitive categories like “old”, “new”, “good”, “warm” ● Degrees of membership − 0 to 100% ● Real-world wisdom − IF userAge IS new THEN discount IS high
  • 15. F U Z Z Y L O G I C F O R A D A P T I V E P R I C I N G • Pros ● Uses explicit business rules ● Doesn’t require large training corpus ● Smoothly-varying output — no discontinuities with thresholds ● Handles contradictions well ● Adding and removing inputs well ● Missing data works well ● Easier to audit
  • 16. F U Z Z Y L O G I C F O R A D A P T I V E P R I C I N G • Cons • Requires numerical inputs
  • 17. D I S C O U N T ● Not a fixed price ● Can use the same agent for multiple products ● 0% = full price, 100% = free ● Bounded to prevent outrageous prices
  • 18. W H AT FA C T O R S C A N A F F E C T P R I C E ?
  • 19. P R O D U C T P O P U L A R I T Y ● Sales/week ● Smoothes over variations by day-of-week ● Ideally, pre-calculated for previous week
  • 20. C AT E G O RY P O P U L A R I T Y ● Similar to product popularity, but for product category
  • 21. S I T E P E R F O R M A N C E ● Site-wide sales for the week ● Can be in dollars, or # of sales ● Very site-specific
  • 22. S A L E S P E R H O U R O F W E E K ● Discrepancies between weekday/ weekend, night/day
  • 23. S A L E S P E R W E E K O F Y E A R ● Especially for seasonal products ● Best for established stores ● At least one year of sales!
  • 24. U S E R R E C E N C Y ● How long ago did the user sign up?
  • 25. U S E R A C T I VAT I O N ● Number of sales or dollars
  • 26. M A R K E T P E N E T R AT I O N ● For geographical markets ● In number/million
  • 27. O T H E R FA C T O R S ● Influencer − Number of followers on Twitter − Number of friends on Facebook ● Social network penetration − Percentage of followers on Twitter who have joined − Percentage of friends on Facebook who have joined
  • 28. R U L E S ● Map input factors to output discount ● Usually linear ● Occasionally inversely linear ● More complex rules possible
  • 29. I N T E G R AT I N G W I T H S T O R E S O F T WA R E ● Using an SDK ● Or a plugin
  • 30. F U Z Z Y L E A R N I N G ● In production ● Feedback loop based on profit margin on the sale ● 0% = no conversion ● Varies fuzzy set boundaries ● Varies weights of fuzzy rules
  • 31. T H A N K S Evan Prodromou evan@fuzzy.io https://fuzzy.io/