SlideShare ist ein Scribd-Unternehmen logo
1 von 22
Downloaden Sie, um offline zu lesen
Customer Intelligence:
A Machine Learning
Approach
Ilya Katsov
Head of Practice, Industrial AI
Grid Dynamics
SEATTLE
MAY 21 2019
ML-based Decision Automation in Marketing Operations
● Billions of micro-decisions in real-time: who, when, how, what, ...
● Complex environment: human behavior, complex business models, hidden factors
● Many building blocks: propensity scoring, recommendation algorithms, multi-armed bandits, etc.
● How to design a system that can make micro-decisions based on business objectives?
Case Study: Environment
Retailer 1 Manufacturer 1
Manufacturer NRetailer M
purchases, clicks, loyalty IDs
...
...
Promotion targeting
system
● Drive traffic
● Improve loyalty
● Increase market share
● Acquire/grow/retain clients
● Improve loyalty
Case Study: Decisions to be Automated
● Targeting – who
○ Exploits variability in tastes, price sensitivity, propensity to buy
○ Optimize short-term or long-term outcomes
● Timing – when
○ Exploits variability in price sensitivity
○ Exploits individual purchasing cycles
● Outreach/budgeting – how many
○ Exploits variability in propensity
● Promotion properties – what
○ Aggregated view on a promotion calendar
Approach
Retailers
Brands
Product
• Willingness to pay
• Stages of journey
• Affinities to brands
• Affinities to channels
Predictive Models
(Digital Twins)
• Propensity
• Life-time
value
• Demand
Economic Models
• What-if analysis
• Optimization
• Opportunity
finding
• Business
objectives
• Constraints
Controls
• Offers
• Channels
• Messages
• Prices
Signals Decisions
Targeting and Timing
Models
7
Incremental revenue
Acquisition Maximization Retention
time
New Cardholder
$/brand
current non-buyers
+
high propensity to buy new product
current buyers
+
high propensity to buy more
current buyers
+
high propensity to buy less
Product Trial
Replenishment
Category Stretch
Retention Alarm
Com
petitive Defence
Look Alike Modeling and Survival Analysis
8
Look Alike Modeling and Survival Analysis
time
no purchase
Model training
Model scoring
purchase
no purchase
behavioral history outcome
Customer
profiles for
training
Customer
profile to be
scored
score
9
Look Alike Modeling and Survival Analysis: Target Metric Design
behavioral history outcome
Unconditional propensity:
Expected LTV:
click/purchase/CTR
3-month spend
Response/value uplift:
Challenges with Basic Propensity Scoring
10
Checking
Account
Credit
Card
Brokerage
Account
Banking /
Telecom
Customer maturity
Product maturity level
Retail
● Does not take into account
product sequences
● Does not optimize offer
sequences (i.e. not strategic)
● Requires separate models
for different
products/offers/objectives
time
profile
profile
Next Best Action Model - Naive Approach
11
profile value (LTV / ROI)
value (LTV / ROI)
value (LTV / ROI)
M
M
M
Time
Offer 1 Offer 2 Offer 3
Offer 3
Offer 2
Offer 1
Offer 3
Offer 2
Offer 3
Offer 2
Offer 1
Offer 1
Next Best Action with Reinforcement Learning
12
Customer state, t
action1
action2
action3
reward32
reward33
reward34
Customer state, t+1 Customer state, t+2 Customer state, t+3
Expected LTV / ROI
Q(s, a)
One
timer
Churner
Repeater
Loyal
customer
Multi
product
● Need to estimate an action-value
function given a certain offer policy:
State
(customer feature vector up to moment t)
Action
(offer feature vector)
● Use Q-function to optimize the offer
policy
s1
s2
s3
s4
s5
Next Best Action with Fitted Q Iteration (FQI)
13
Purchase
Visit
No action
Offer 1 Offer 2 Offer 3
1. Generate a batch of transitions
(each trajectory corresponds to 4 transitions):
{ (state, action, reward, new state) }
2. Initialize approximate
3. Initialize training set
4. For each
5. Learn new from training data
repeat
A simplified test dataset is shown for illustration
Next Best Action with FQI
14
Offer 3
Offer 2
Offer 1 (default)
Low state V
High state V
Customers who got
Offer 3 in early
Customers who did
not get offers or got
Offer 1
Customers who got
Offer 2 early
Customers who got
Offer 2 -> Offer 3
● Max value for each state:
● Next best action for each state (policy):
A simplified test dataset is shown for illustration
Next Best Action with FQI
15
● A generalization of the look alike modeling for multi-step and/or multi-choice strategies
● More control over LTV/ROI metrics
● Can evaluate performance of a new policy based on historical trajectories
● Batch-online learning trade-off: multi armed bandits
Budgeting Models and
Decision Automation
Privileged and Confidential 17
Targeting Thresholds: Static Optimization
High
propensity
Low
propensity
Privileged and Confidential 18
Targeting Thresholds: Dynamic Optimization
time
$$
campaign
duration
target budget
Decrease
propensity
threshold
Increase
propensity
threshold
19
Campaign Parameters Optimization
Purchase
trigger
buy <X buy X+
buy 0 buy 1+
Announcement
Buy X or more units
and save on your
next shopping trip!
Promotion
Y% off
1. Estimate demand elasticity
2. Estimate how many
consumers will buy more,
how many will redeem offers
3. Do break-even analysis for
costs and benefits
20
Solution Design: Technical Perspective
Marketing
Manager
Campaign Template
● Steps
● Offer types
● Forecasting logic
Targeting Score
(Look Alike or Next Best
Action)
Timing Score
(Replenishment)
LTV Score
(Monetary)
Offer Database
Profile Database
Campaign
Planner
Targeting Server
Forecasting
Optimization
Targeting decisions
Budgeting decisions
request response
Marketing
Manager
(merchant)
Decision
automation
Customer
models
Objective Selection
Plan and Forecast
Review
User Experience
Execution and
Measurement
Privileged and Confidential 21
Solution Design: Marketer’s Perspective
Thank you!

Weitere ähnliche Inhalte

Was ist angesagt?

Automating Sales Processes To Drive Competitive Advantage
Automating Sales Processes To Drive Competitive AdvantageAutomating Sales Processes To Drive Competitive Advantage
Automating Sales Processes To Drive Competitive AdvantageVisibleThread
 
Sales Learning Curve - Sales Management
Sales Learning Curve - Sales ManagementSales Learning Curve - Sales Management
Sales Learning Curve - Sales ManagementRahul Tanwar
 
Hotel Management Course - Revenue management Concepts
Hotel Management Course - Revenue management Concepts Hotel Management Course - Revenue management Concepts
Hotel Management Course - Revenue management Concepts Manish Gupta
 
Profitability analysis
Profitability analysisProfitability analysis
Profitability analysisJess Wiley
 
Zume in 1 exec short v5
Zume in 1   exec short v5Zume in 1   exec short v5
Zume in 1 exec short v5malcolmwhite
 
Retail sales reporting & analysis
Retail sales reporting & analysisRetail sales reporting & analysis
Retail sales reporting & analysisRetail EDI
 
Sales force automation
Sales force automationSales force automation
Sales force automationFieldAssist1
 
Development and Economic Analysis for Projects
Development and Economic Analysis for ProjectsDevelopment and Economic Analysis for Projects
Development and Economic Analysis for ProjectsAndre Marques Valio
 
Sales Force Automation
Sales Force AutomationSales Force Automation
Sales Force Automationkeatonarter
 
Sales Strategy in a Digitally Connected World
Sales Strategy in a Digitally Connected WorldSales Strategy in a Digitally Connected World
Sales Strategy in a Digitally Connected WorldVishal Sharma
 
Banking Sector and Business Intelligence
Banking Sector and Business IntelligenceBanking Sector and Business Intelligence
Banking Sector and Business IntelligenceNalini Singh
 
How to increase the revenues of the hotel with Revenue management?
How to increase the revenues of the hotel with Revenue management?How to increase the revenues of the hotel with Revenue management?
How to increase the revenues of the hotel with Revenue management?Stanislav Ivanov
 
Revenue Management
Revenue ManagementRevenue Management
Revenue ManagementSagar PATEL
 
Best practices in revenue management
Best practices in revenue managementBest practices in revenue management
Best practices in revenue managementMihran Kalaydjian
 
Universal Analytics and Google Tag Manager - Superweek 2014
Universal Analytics and Google Tag Manager - Superweek 2014Universal Analytics and Google Tag Manager - Superweek 2014
Universal Analytics and Google Tag Manager - Superweek 2014Yehoshua
 

Was ist angesagt? (20)

Churn management
Churn managementChurn management
Churn management
 
Automating Sales Processes To Drive Competitive Advantage
Automating Sales Processes To Drive Competitive AdvantageAutomating Sales Processes To Drive Competitive Advantage
Automating Sales Processes To Drive Competitive Advantage
 
Saa s retail execution solution
Saa s retail execution solutionSaa s retail execution solution
Saa s retail execution solution
 
Viima
ViimaViima
Viima
 
Sales Learning Curve - Sales Management
Sales Learning Curve - Sales ManagementSales Learning Curve - Sales Management
Sales Learning Curve - Sales Management
 
Hotel Management Course - Revenue management Concepts
Hotel Management Course - Revenue management Concepts Hotel Management Course - Revenue management Concepts
Hotel Management Course - Revenue management Concepts
 
Profitability analysis
Profitability analysisProfitability analysis
Profitability analysis
 
Smartsales 2017
Smartsales 2017Smartsales 2017
Smartsales 2017
 
Chapter 7
Chapter 7Chapter 7
Chapter 7
 
Zume in 1 exec short v5
Zume in 1   exec short v5Zume in 1   exec short v5
Zume in 1 exec short v5
 
Retail sales reporting & analysis
Retail sales reporting & analysisRetail sales reporting & analysis
Retail sales reporting & analysis
 
Sales force automation
Sales force automationSales force automation
Sales force automation
 
Development and Economic Analysis for Projects
Development and Economic Analysis for ProjectsDevelopment and Economic Analysis for Projects
Development and Economic Analysis for Projects
 
Sales Force Automation
Sales Force AutomationSales Force Automation
Sales Force Automation
 
Sales Strategy in a Digitally Connected World
Sales Strategy in a Digitally Connected WorldSales Strategy in a Digitally Connected World
Sales Strategy in a Digitally Connected World
 
Banking Sector and Business Intelligence
Banking Sector and Business IntelligenceBanking Sector and Business Intelligence
Banking Sector and Business Intelligence
 
How to increase the revenues of the hotel with Revenue management?
How to increase the revenues of the hotel with Revenue management?How to increase the revenues of the hotel with Revenue management?
How to increase the revenues of the hotel with Revenue management?
 
Revenue Management
Revenue ManagementRevenue Management
Revenue Management
 
Best practices in revenue management
Best practices in revenue managementBest practices in revenue management
Best practices in revenue management
 
Universal Analytics and Google Tag Manager - Superweek 2014
Universal Analytics and Google Tag Manager - Superweek 2014Universal Analytics and Google Tag Manager - Superweek 2014
Universal Analytics and Google Tag Manager - Superweek 2014
 

Ähnlich wie Customer intelligence: a machine learning approach 5/21/2019

IBM Transforming Customer Relationships Through Predictive Analytics
IBM Transforming Customer Relationships Through Predictive AnalyticsIBM Transforming Customer Relationships Through Predictive Analytics
IBM Transforming Customer Relationships Through Predictive AnalyticsSFIMA
 
The Sales Productivity Benchmark: Rate your Sales Force Against World Class
The Sales Productivity Benchmark: Rate your Sales Force Against World ClassThe Sales Productivity Benchmark: Rate your Sales Force Against World Class
The Sales Productivity Benchmark: Rate your Sales Force Against World ClassSBI | Sales Benchmark Index
 
Customer Retention Summit Integrated Insight V1
Customer Retention Summit   Integrated Insight V1Customer Retention Summit   Integrated Insight V1
Customer Retention Summit Integrated Insight V1Tony Mooney
 
Data Science, Analytics & Critical Thinking
Data Science, Analytics & Critical ThinkingData Science, Analytics & Critical Thinking
Data Science, Analytics & Critical ThinkingAditya Madiraju
 
Data Drive Better Sales Conversions - Dawn of the Data Age Lecture Series
Data Drive Better Sales Conversions  - Dawn of the Data Age Lecture SeriesData Drive Better Sales Conversions  - Dawn of the Data Age Lecture Series
Data Drive Better Sales Conversions - Dawn of the Data Age Lecture SeriesLuciano Pesci, PhD
 
Next Best Action for B2B account based marketing
Next Best Action for B2B account based marketing Next Best Action for B2B account based marketing
Next Best Action for B2B account based marketing Edmond Sam
 
Customer Analytics and Segmentation
Customer Analytics and SegmentationCustomer Analytics and Segmentation
Customer Analytics and Segmentationhybridmarketer
 
The Paradigm: From Sales to Profits Using Optimization Analytics
The Paradigm: From Sales to Profits Using Optimization AnalyticsThe Paradigm: From Sales to Profits Using Optimization Analytics
The Paradigm: From Sales to Profits Using Optimization AnalyticsVivastream
 
Windsor marketing attribution_webinar
Windsor marketing attribution_webinarWindsor marketing attribution_webinar
Windsor marketing attribution_webinarnkolster
 
Richard Marshall EARL 2019.pptx
Richard Marshall EARL 2019.pptxRichard Marshall EARL 2019.pptx
Richard Marshall EARL 2019.pptxDean Maitland
 
GMDC Conference Presentation
GMDC Conference PresentationGMDC Conference Presentation
GMDC Conference PresentationEric Togneri
 
E-commerce Berlin Expo 2018 - How to boost your online sales using machine le...
E-commerce Berlin Expo 2018 - How to boost your online sales using machine le...E-commerce Berlin Expo 2018 - How to boost your online sales using machine le...
E-commerce Berlin Expo 2018 - How to boost your online sales using machine le...E-Commerce Berlin EXPO
 
Successful Customer Communications Strategies in 8 Steps and 2 Case Studies
Successful Customer Communications Strategies in 8 Steps and 2 Case StudiesSuccessful Customer Communications Strategies in 8 Steps and 2 Case Studies
Successful Customer Communications Strategies in 8 Steps and 2 Case StudiesVivastream
 
Value analysis methodology
Value analysis methodologyValue analysis methodology
Value analysis methodologybarcelona98
 

Ähnlich wie Customer intelligence: a machine learning approach 5/21/2019 (20)

IBM Transforming Customer Relationships Through Predictive Analytics
IBM Transforming Customer Relationships Through Predictive AnalyticsIBM Transforming Customer Relationships Through Predictive Analytics
IBM Transforming Customer Relationships Through Predictive Analytics
 
The Sales Productivity Benchmark: Rate your Sales Force Against World Class
The Sales Productivity Benchmark: Rate your Sales Force Against World ClassThe Sales Productivity Benchmark: Rate your Sales Force Against World Class
The Sales Productivity Benchmark: Rate your Sales Force Against World Class
 
Customer Retention Summit Integrated Insight V1
Customer Retention Summit   Integrated Insight V1Customer Retention Summit   Integrated Insight V1
Customer Retention Summit Integrated Insight V1
 
Data Science, Analytics & Critical Thinking
Data Science, Analytics & Critical ThinkingData Science, Analytics & Critical Thinking
Data Science, Analytics & Critical Thinking
 
Data Drive Better Sales Conversions - Dawn of the Data Age Lecture Series
Data Drive Better Sales Conversions  - Dawn of the Data Age Lecture SeriesData Drive Better Sales Conversions  - Dawn of the Data Age Lecture Series
Data Drive Better Sales Conversions - Dawn of the Data Age Lecture Series
 
Next Best Action for B2B account based marketing
Next Best Action for B2B account based marketing Next Best Action for B2B account based marketing
Next Best Action for B2B account based marketing
 
Customer Analytics and Segmentation
Customer Analytics and SegmentationCustomer Analytics and Segmentation
Customer Analytics and Segmentation
 
Session 10 MG 220 BBA - 8 Sep 10
Session 10   MG 220 BBA - 8 Sep 10Session 10   MG 220 BBA - 8 Sep 10
Session 10 MG 220 BBA - 8 Sep 10
 
The Paradigm: From Sales to Profits Using Optimization Analytics
The Paradigm: From Sales to Profits Using Optimization AnalyticsThe Paradigm: From Sales to Profits Using Optimization Analytics
The Paradigm: From Sales to Profits Using Optimization Analytics
 
Session 9 mg 220 mba - 20 sep 10
Session 9   mg 220 mba - 20 sep 10Session 9   mg 220 mba - 20 sep 10
Session 9 mg 220 mba - 20 sep 10
 
Windsor marketing attribution_webinar
Windsor marketing attribution_webinarWindsor marketing attribution_webinar
Windsor marketing attribution_webinar
 
Richard Marshall EARL 2019.pptx
Richard Marshall EARL 2019.pptxRichard Marshall EARL 2019.pptx
Richard Marshall EARL 2019.pptx
 
Crm
CrmCrm
Crm
 
GMDC Conference Presentation
GMDC Conference PresentationGMDC Conference Presentation
GMDC Conference Presentation
 
E-commerce Berlin Expo 2018 - How to boost your online sales using machine le...
E-commerce Berlin Expo 2018 - How to boost your online sales using machine le...E-commerce Berlin Expo 2018 - How to boost your online sales using machine le...
E-commerce Berlin Expo 2018 - How to boost your online sales using machine le...
 
Joint account plan jap
Joint account plan   japJoint account plan   jap
Joint account plan jap
 
Successful Customer Communications Strategies in 8 Steps and 2 Case Studies
Successful Customer Communications Strategies in 8 Steps and 2 Case StudiesSuccessful Customer Communications Strategies in 8 Steps and 2 Case Studies
Successful Customer Communications Strategies in 8 Steps and 2 Case Studies
 
Sales forecasting
Sales forecastingSales forecasting
Sales forecasting
 
Value analysis methodology
Value analysis methodologyValue analysis methodology
Value analysis methodology
 
Joint Account Plan
Joint Account Plan Joint Account Plan
Joint Account Plan
 

Mehr von Grid Dynamics

Are you keeping up with your customer
Are you keeping up with your customer Are you keeping up with your customer
Are you keeping up with your customer Grid Dynamics
 
"Implementing data quality automation with open source stack" - Max Martynov,...
"Implementing data quality automation with open source stack" - Max Martynov,..."Implementing data quality automation with open source stack" - Max Martynov,...
"Implementing data quality automation with open source stack" - Max Martynov,...Grid Dynamics
 
"How to build cool & useful voice commerce applications (such as devices like...
"How to build cool & useful voice commerce applications (such as devices like..."How to build cool & useful voice commerce applications (such as devices like...
"How to build cool & useful voice commerce applications (such as devices like...Grid Dynamics
 
"Challenges for AI in Healthcare" - Peter Graven Ph.D
"Challenges for AI in Healthcare" - Peter Graven Ph.D"Challenges for AI in Healthcare" - Peter Graven Ph.D
"Challenges for AI in Healthcare" - Peter Graven Ph.DGrid Dynamics
 
Dynamic Talks: "Applications of Big Data, Machine Learning and Artificial Int...
Dynamic Talks: "Applications of Big Data, Machine Learning and Artificial Int...Dynamic Talks: "Applications of Big Data, Machine Learning and Artificial Int...
Dynamic Talks: "Applications of Big Data, Machine Learning and Artificial Int...Grid Dynamics
 
Dynamic Talks: "Digital Transformation in Banking & Financial Services… a per...
Dynamic Talks: "Digital Transformation in Banking & Financial Services… a per...Dynamic Talks: "Digital Transformation in Banking & Financial Services… a per...
Dynamic Talks: "Digital Transformation in Banking & Financial Services… a per...Grid Dynamics
 
Dynamic Talks: "Data Strategy as a Conduit for Data Maturity and Monetization...
Dynamic Talks: "Data Strategy as a Conduit for Data Maturity and Monetization...Dynamic Talks: "Data Strategy as a Conduit for Data Maturity and Monetization...
Dynamic Talks: "Data Strategy as a Conduit for Data Maturity and Monetization...Grid Dynamics
 
Dynamics Talks: "Writing Spark Pipelines with Less Boilerplate Code" - Egor P...
Dynamics Talks: "Writing Spark Pipelines with Less Boilerplate Code" - Egor P...Dynamics Talks: "Writing Spark Pipelines with Less Boilerplate Code" - Egor P...
Dynamics Talks: "Writing Spark Pipelines with Less Boilerplate Code" - Egor P...Grid Dynamics
 
"Trends in Building Advanced Analytics Platform for Large Enterprises" - Atul...
"Trends in Building Advanced Analytics Platform for Large Enterprises" - Atul..."Trends in Building Advanced Analytics Platform for Large Enterprises" - Atul...
"Trends in Building Advanced Analytics Platform for Large Enterprises" - Atul...Grid Dynamics
 
The New Era of Public Safety Records Management: Dynamic talks Chicago 9/24/2019
The New Era of Public Safety Records Management: Dynamic talks Chicago 9/24/2019The New Era of Public Safety Records Management: Dynamic talks Chicago 9/24/2019
The New Era of Public Safety Records Management: Dynamic talks Chicago 9/24/2019Grid Dynamics
 
Dynamic Talks: "Implementing data quality automation with open source stack" ...
Dynamic Talks: "Implementing data quality automation with open source stack" ...Dynamic Talks: "Implementing data quality automation with open source stack" ...
Dynamic Talks: "Implementing data quality automation with open source stack" ...Grid Dynamics
 
"Implementing AI for New Business Models and Efficiencies" - Parag Shrivastav...
"Implementing AI for New Business Models and Efficiencies" - Parag Shrivastav..."Implementing AI for New Business Models and Efficiencies" - Parag Shrivastav...
"Implementing AI for New Business Models and Efficiencies" - Parag Shrivastav...Grid Dynamics
 
Reducing No-shows and Late Cancelations in Healthcare Enterprise" - Shervin M...
Reducing No-shows and Late Cancelations in Healthcare Enterprise" - Shervin M...Reducing No-shows and Late Cancelations in Healthcare Enterprise" - Shervin M...
Reducing No-shows and Late Cancelations in Healthcare Enterprise" - Shervin M...Grid Dynamics
 
"ML Services - How do you begin and when do you start scaling?" - Madhura Dud...
"ML Services - How do you begin and when do you start scaling?" - Madhura Dud..."ML Services - How do you begin and when do you start scaling?" - Madhura Dud...
"ML Services - How do you begin and when do you start scaling?" - Madhura Dud...Grid Dynamics
 
Realtime Contextual Product Recommendations…that scale and generate revenue -...
Realtime Contextual Product Recommendations…that scale and generate revenue -...Realtime Contextual Product Recommendations…that scale and generate revenue -...
Realtime Contextual Product Recommendations…that scale and generate revenue -...Grid Dynamics
 
Best practices for enterprise-grade microservices implementations with Google...
Best practices for enterprise-grade microservices implementations with Google...Best practices for enterprise-grade microservices implementations with Google...
Best practices for enterprise-grade microservices implementations with Google...Grid Dynamics
 
Attribution Modelling 101: Credit Where Credit is Due!: Dynamic talks Seattle...
Attribution Modelling 101: Credit Where Credit is Due!: Dynamic talks Seattle...Attribution Modelling 101: Credit Where Credit is Due!: Dynamic talks Seattle...
Attribution Modelling 101: Credit Where Credit is Due!: Dynamic talks Seattle...Grid Dynamics
 
Building an algorithmic price management system using ML: Dynamic talks Seatt...
Building an algorithmic price management system using ML: Dynamic talks Seatt...Building an algorithmic price management system using ML: Dynamic talks Seatt...
Building an algorithmic price management system using ML: Dynamic talks Seatt...Grid Dynamics
 
Improving Customer Experience via Experimentation Dynamic Talks: San Francisc...
Improving Customer Experience via Experimentation Dynamic Talks: San Francisc...Improving Customer Experience via Experimentation Dynamic Talks: San Francisc...
Improving Customer Experience via Experimentation Dynamic Talks: San Francisc...Grid Dynamics
 
Cloud and microservices on the enterprise level: Dynamic Talks Portland 5/16/...
Cloud and microservices on the enterprise level: Dynamic Talks Portland 5/16/...Cloud and microservices on the enterprise level: Dynamic Talks Portland 5/16/...
Cloud and microservices on the enterprise level: Dynamic Talks Portland 5/16/...Grid Dynamics
 

Mehr von Grid Dynamics (20)

Are you keeping up with your customer
Are you keeping up with your customer Are you keeping up with your customer
Are you keeping up with your customer
 
"Implementing data quality automation with open source stack" - Max Martynov,...
"Implementing data quality automation with open source stack" - Max Martynov,..."Implementing data quality automation with open source stack" - Max Martynov,...
"Implementing data quality automation with open source stack" - Max Martynov,...
 
"How to build cool & useful voice commerce applications (such as devices like...
"How to build cool & useful voice commerce applications (such as devices like..."How to build cool & useful voice commerce applications (such as devices like...
"How to build cool & useful voice commerce applications (such as devices like...
 
"Challenges for AI in Healthcare" - Peter Graven Ph.D
"Challenges for AI in Healthcare" - Peter Graven Ph.D"Challenges for AI in Healthcare" - Peter Graven Ph.D
"Challenges for AI in Healthcare" - Peter Graven Ph.D
 
Dynamic Talks: "Applications of Big Data, Machine Learning and Artificial Int...
Dynamic Talks: "Applications of Big Data, Machine Learning and Artificial Int...Dynamic Talks: "Applications of Big Data, Machine Learning and Artificial Int...
Dynamic Talks: "Applications of Big Data, Machine Learning and Artificial Int...
 
Dynamic Talks: "Digital Transformation in Banking & Financial Services… a per...
Dynamic Talks: "Digital Transformation in Banking & Financial Services… a per...Dynamic Talks: "Digital Transformation in Banking & Financial Services… a per...
Dynamic Talks: "Digital Transformation in Banking & Financial Services… a per...
 
Dynamic Talks: "Data Strategy as a Conduit for Data Maturity and Monetization...
Dynamic Talks: "Data Strategy as a Conduit for Data Maturity and Monetization...Dynamic Talks: "Data Strategy as a Conduit for Data Maturity and Monetization...
Dynamic Talks: "Data Strategy as a Conduit for Data Maturity and Monetization...
 
Dynamics Talks: "Writing Spark Pipelines with Less Boilerplate Code" - Egor P...
Dynamics Talks: "Writing Spark Pipelines with Less Boilerplate Code" - Egor P...Dynamics Talks: "Writing Spark Pipelines with Less Boilerplate Code" - Egor P...
Dynamics Talks: "Writing Spark Pipelines with Less Boilerplate Code" - Egor P...
 
"Trends in Building Advanced Analytics Platform for Large Enterprises" - Atul...
"Trends in Building Advanced Analytics Platform for Large Enterprises" - Atul..."Trends in Building Advanced Analytics Platform for Large Enterprises" - Atul...
"Trends in Building Advanced Analytics Platform for Large Enterprises" - Atul...
 
The New Era of Public Safety Records Management: Dynamic talks Chicago 9/24/2019
The New Era of Public Safety Records Management: Dynamic talks Chicago 9/24/2019The New Era of Public Safety Records Management: Dynamic talks Chicago 9/24/2019
The New Era of Public Safety Records Management: Dynamic talks Chicago 9/24/2019
 
Dynamic Talks: "Implementing data quality automation with open source stack" ...
Dynamic Talks: "Implementing data quality automation with open source stack" ...Dynamic Talks: "Implementing data quality automation with open source stack" ...
Dynamic Talks: "Implementing data quality automation with open source stack" ...
 
"Implementing AI for New Business Models and Efficiencies" - Parag Shrivastav...
"Implementing AI for New Business Models and Efficiencies" - Parag Shrivastav..."Implementing AI for New Business Models and Efficiencies" - Parag Shrivastav...
"Implementing AI for New Business Models and Efficiencies" - Parag Shrivastav...
 
Reducing No-shows and Late Cancelations in Healthcare Enterprise" - Shervin M...
Reducing No-shows and Late Cancelations in Healthcare Enterprise" - Shervin M...Reducing No-shows and Late Cancelations in Healthcare Enterprise" - Shervin M...
Reducing No-shows and Late Cancelations in Healthcare Enterprise" - Shervin M...
 
"ML Services - How do you begin and when do you start scaling?" - Madhura Dud...
"ML Services - How do you begin and when do you start scaling?" - Madhura Dud..."ML Services - How do you begin and when do you start scaling?" - Madhura Dud...
"ML Services - How do you begin and when do you start scaling?" - Madhura Dud...
 
Realtime Contextual Product Recommendations…that scale and generate revenue -...
Realtime Contextual Product Recommendations…that scale and generate revenue -...Realtime Contextual Product Recommendations…that scale and generate revenue -...
Realtime Contextual Product Recommendations…that scale and generate revenue -...
 
Best practices for enterprise-grade microservices implementations with Google...
Best practices for enterprise-grade microservices implementations with Google...Best practices for enterprise-grade microservices implementations with Google...
Best practices for enterprise-grade microservices implementations with Google...
 
Attribution Modelling 101: Credit Where Credit is Due!: Dynamic talks Seattle...
Attribution Modelling 101: Credit Where Credit is Due!: Dynamic talks Seattle...Attribution Modelling 101: Credit Where Credit is Due!: Dynamic talks Seattle...
Attribution Modelling 101: Credit Where Credit is Due!: Dynamic talks Seattle...
 
Building an algorithmic price management system using ML: Dynamic talks Seatt...
Building an algorithmic price management system using ML: Dynamic talks Seatt...Building an algorithmic price management system using ML: Dynamic talks Seatt...
Building an algorithmic price management system using ML: Dynamic talks Seatt...
 
Improving Customer Experience via Experimentation Dynamic Talks: San Francisc...
Improving Customer Experience via Experimentation Dynamic Talks: San Francisc...Improving Customer Experience via Experimentation Dynamic Talks: San Francisc...
Improving Customer Experience via Experimentation Dynamic Talks: San Francisc...
 
Cloud and microservices on the enterprise level: Dynamic Talks Portland 5/16/...
Cloud and microservices on the enterprise level: Dynamic Talks Portland 5/16/...Cloud and microservices on the enterprise level: Dynamic Talks Portland 5/16/...
Cloud and microservices on the enterprise level: Dynamic Talks Portland 5/16/...
 

Kürzlich hochgeladen

Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024The Digital Insurer
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking MenDelhi Call girls
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxKatpro Technologies
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityPrincipled Technologies
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024The Digital Insurer
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking MenDelhi Call girls
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Servicegiselly40
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsEnterprise Knowledge
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024Results
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...gurkirankumar98700
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreternaman860154
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Allon Mureinik
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptxHampshireHUG
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)Gabriella Davis
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024The Digital Insurer
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationMichael W. Hawkins
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...Martijn de Jong
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonetsnaman860154
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilV3cube
 

Kürzlich hochgeladen (20)

Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024Finology Group – Insurtech Innovation Award 2024
Finology Group – Insurtech Innovation Award 2024
 
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
08448380779 Call Girls In Diplomatic Enclave Women Seeking Men
 
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptxFactors to Consider When Choosing Accounts Payable Services Providers.pptx
Factors to Consider When Choosing Accounts Payable Services Providers.pptx
 
Boost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivityBoost PC performance: How more available memory can improve productivity
Boost PC performance: How more available memory can improve productivity
 
Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024Axa Assurance Maroc - Insurer Innovation Award 2024
Axa Assurance Maroc - Insurer Innovation Award 2024
 
08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men08448380779 Call Girls In Civil Lines Women Seeking Men
08448380779 Call Girls In Civil Lines Women Seeking Men
 
CNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of ServiceCNv6 Instructor Chapter 6 Quality of Service
CNv6 Instructor Chapter 6 Quality of Service
 
IAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI SolutionsIAC 2024 - IA Fast Track to Search Focused AI Solutions
IAC 2024 - IA Fast Track to Search Focused AI Solutions
 
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law DevelopmentsTrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
TrustArc Webinar - Stay Ahead of US State Data Privacy Law Developments
 
A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024A Call to Action for Generative AI in 2024
A Call to Action for Generative AI in 2024
 
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
Kalyanpur ) Call Girls in Lucknow Finest Escorts Service 🍸 8923113531 🎰 Avail...
 
Presentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreterPresentation on how to chat with PDF using ChatGPT code interpreter
Presentation on how to chat with PDF using ChatGPT code interpreter
 
Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)Injustice - Developers Among Us (SciFiDevCon 2024)
Injustice - Developers Among Us (SciFiDevCon 2024)
 
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
04-2024-HHUG-Sales-and-Marketing-Alignment.pptx
 
A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)A Domino Admins Adventures (Engage 2024)
A Domino Admins Adventures (Engage 2024)
 
Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024Tata AIG General Insurance Company - Insurer Innovation Award 2024
Tata AIG General Insurance Company - Insurer Innovation Award 2024
 
GenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day PresentationGenCyber Cyber Security Day Presentation
GenCyber Cyber Security Day Presentation
 
2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...2024: Domino Containers - The Next Step. News from the Domino Container commu...
2024: Domino Containers - The Next Step. News from the Domino Container commu...
 
How to convert PDF to text with Nanonets
How to convert PDF to text with NanonetsHow to convert PDF to text with Nanonets
How to convert PDF to text with Nanonets
 
Developing An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of BrazilDeveloping An App To Navigate The Roads of Brazil
Developing An App To Navigate The Roads of Brazil
 

Customer intelligence: a machine learning approach 5/21/2019

  • 1. Customer Intelligence: A Machine Learning Approach Ilya Katsov Head of Practice, Industrial AI Grid Dynamics SEATTLE MAY 21 2019
  • 2. ML-based Decision Automation in Marketing Operations ● Billions of micro-decisions in real-time: who, when, how, what, ... ● Complex environment: human behavior, complex business models, hidden factors ● Many building blocks: propensity scoring, recommendation algorithms, multi-armed bandits, etc. ● How to design a system that can make micro-decisions based on business objectives?
  • 3. Case Study: Environment Retailer 1 Manufacturer 1 Manufacturer NRetailer M purchases, clicks, loyalty IDs ... ... Promotion targeting system ● Drive traffic ● Improve loyalty ● Increase market share ● Acquire/grow/retain clients ● Improve loyalty
  • 4. Case Study: Decisions to be Automated ● Targeting – who ○ Exploits variability in tastes, price sensitivity, propensity to buy ○ Optimize short-term or long-term outcomes ● Timing – when ○ Exploits variability in price sensitivity ○ Exploits individual purchasing cycles ● Outreach/budgeting – how many ○ Exploits variability in propensity ● Promotion properties – what ○ Aggregated view on a promotion calendar
  • 5. Approach Retailers Brands Product • Willingness to pay • Stages of journey • Affinities to brands • Affinities to channels Predictive Models (Digital Twins) • Propensity • Life-time value • Demand Economic Models • What-if analysis • Optimization • Opportunity finding • Business objectives • Constraints Controls • Offers • Channels • Messages • Prices Signals Decisions
  • 7. 7 Incremental revenue Acquisition Maximization Retention time New Cardholder $/brand current non-buyers + high propensity to buy new product current buyers + high propensity to buy more current buyers + high propensity to buy less Product Trial Replenishment Category Stretch Retention Alarm Com petitive Defence Look Alike Modeling and Survival Analysis
  • 8. 8 Look Alike Modeling and Survival Analysis time no purchase Model training Model scoring purchase no purchase behavioral history outcome Customer profiles for training Customer profile to be scored score
  • 9. 9 Look Alike Modeling and Survival Analysis: Target Metric Design behavioral history outcome Unconditional propensity: Expected LTV: click/purchase/CTR 3-month spend Response/value uplift:
  • 10. Challenges with Basic Propensity Scoring 10 Checking Account Credit Card Brokerage Account Banking / Telecom Customer maturity Product maturity level Retail ● Does not take into account product sequences ● Does not optimize offer sequences (i.e. not strategic) ● Requires separate models for different products/offers/objectives time
  • 11. profile profile Next Best Action Model - Naive Approach 11 profile value (LTV / ROI) value (LTV / ROI) value (LTV / ROI) M M M Time Offer 1 Offer 2 Offer 3 Offer 3 Offer 2 Offer 1 Offer 3 Offer 2 Offer 3 Offer 2 Offer 1 Offer 1
  • 12. Next Best Action with Reinforcement Learning 12 Customer state, t action1 action2 action3 reward32 reward33 reward34 Customer state, t+1 Customer state, t+2 Customer state, t+3 Expected LTV / ROI Q(s, a) One timer Churner Repeater Loyal customer Multi product ● Need to estimate an action-value function given a certain offer policy: State (customer feature vector up to moment t) Action (offer feature vector) ● Use Q-function to optimize the offer policy s1 s2 s3 s4 s5
  • 13. Next Best Action with Fitted Q Iteration (FQI) 13 Purchase Visit No action Offer 1 Offer 2 Offer 3 1. Generate a batch of transitions (each trajectory corresponds to 4 transitions): { (state, action, reward, new state) } 2. Initialize approximate 3. Initialize training set 4. For each 5. Learn new from training data repeat A simplified test dataset is shown for illustration
  • 14. Next Best Action with FQI 14 Offer 3 Offer 2 Offer 1 (default) Low state V High state V Customers who got Offer 3 in early Customers who did not get offers or got Offer 1 Customers who got Offer 2 early Customers who got Offer 2 -> Offer 3 ● Max value for each state: ● Next best action for each state (policy): A simplified test dataset is shown for illustration
  • 15. Next Best Action with FQI 15 ● A generalization of the look alike modeling for multi-step and/or multi-choice strategies ● More control over LTV/ROI metrics ● Can evaluate performance of a new policy based on historical trajectories ● Batch-online learning trade-off: multi armed bandits
  • 17. Privileged and Confidential 17 Targeting Thresholds: Static Optimization High propensity Low propensity
  • 18. Privileged and Confidential 18 Targeting Thresholds: Dynamic Optimization time $$ campaign duration target budget Decrease propensity threshold Increase propensity threshold
  • 19. 19 Campaign Parameters Optimization Purchase trigger buy <X buy X+ buy 0 buy 1+ Announcement Buy X or more units and save on your next shopping trip! Promotion Y% off 1. Estimate demand elasticity 2. Estimate how many consumers will buy more, how many will redeem offers 3. Do break-even analysis for costs and benefits
  • 20. 20 Solution Design: Technical Perspective Marketing Manager Campaign Template ● Steps ● Offer types ● Forecasting logic Targeting Score (Look Alike or Next Best Action) Timing Score (Replenishment) LTV Score (Monetary) Offer Database Profile Database Campaign Planner Targeting Server Forecasting Optimization Targeting decisions Budgeting decisions request response Marketing Manager (merchant) Decision automation Customer models
  • 21. Objective Selection Plan and Forecast Review User Experience Execution and Measurement Privileged and Confidential 21 Solution Design: Marketer’s Perspective