SlideShare a Scribd company logo
PRICING OPTIMIZATION
IN DATA REPLY
Ilaria Gianoli | Data Scientist
Giovanni Corradini | Data Scientist
Riccardo Lorenzon | Senior Data Scientist
OPTIMAL DISCOUNT
STRATEGY FOR PRODUCTS
IN CLOSE-OUT PHASE
Ilaria Gianoli | Data Scientist
 Customer:
Retail/GDO Leader
 Description:
Identify the optimal discount
strategy for products in their
close-out phase, as a trade-off
between margin loss and
inventory cost
THE PROBLEM
PROJECT BACKGROUNDInfo
• The purchasing department
establishes when a product goes
out of range
• In the close-out phase, the stores
have limited time to get rid of the
leftover stock, otherwise the have
to pay a penalty
• Each store chooses autonomously
the discount to apply
Alert
• The product prices do not change
often, except during the
marketing campaign
• The wide product range requires
the elasticity model to be product-
specific
SOLUTION OVERVIEW
DATA
TECH
• Elasticity model: linear regression
• Clustering model: DBscan
• Time series forecast: arima + FFNN + seasonal rescaling
ALGOS
Sales
Prices
Product info
Stock
Promotions
SOLUTION DETAIL
STEP 1:
SALES
FORECASTING
STEP 2:
PRICE
ELASTICITY
STEP 3:
DISCOUNT
OPTIMIZATION
• Use all the information about sellout, stock, prices,
calendar, marketing and discount campaigns to
create a clean time series;
• Create a forecast model on a weekly basis according
to the nature of the product (new, young, historical).
The forecast is at a product-store level;
SOLUTION DETAIL
• Use specific department weights to remove
seasonality from the time series;
• Create an elasticity model at product level;
• Clusterize the products according to their sales
potential and price range;
• Create a hierarchical elasticity model
STEP 1:
SALES
FORECASTING
STEP 2:
PRICE
ELASTICITY
STEP 3:
DISCOUNT
OPTIMIZATION
SOLUTION DETAIL
• Use the forecast model to estimate T*, i.e. the time
in which the stock is exhausted;
• Use the price elasticity coefficent to compute the
Δp for the desired Δq;
• Choose the optimal discount as
ത𝑇 = 𝑎𝑟𝑔 max
𝑡 ∈[𝑇,𝑇∗]
(𝑚𝑎𝑟𝑔𝑖𝑛 𝑝 𝑡 − 𝑓𝑒𝑒 𝑡 ) with stock(t) = 0
STEP 1:
SALES
FORECASTING
STEP 2:
PRICE
ELASTICITY
STEP 3:
DISCOUNT
OPTIMIZATION
BUSINESS BENEFITS
Quantitative
• Revenue improvement
• Reduction in penalties
• Reduction in inventory costs
Qualitative
• More visibility to new products
• Better space allocation in stores
• Homogeneity among stores
ONLINE PRICING: FROM
THEORY TO APPLICATION
Giovanni Corradini| Data Scientist
THE PROBLEM
 Customer:
Ticket selling company
 Problem:
Choose the price that maximize the total
revenue through application of Contextual
Multi-Armed Bandit algorithm
THE TRADE-OFF
 Exploration
 Find the best price by proposing different prices
 Many mistakes
 Exploitation
 Propose current best price to make money
 Maybe not the optimal one
A/B TESTING VS
MULTI-ARMED BANDIT
 A/B Testing
 Multi-Armed Bandit
THEORETICAL BACKGROUND
History of
contracts
 Bandit setting:
 Consider n rounds
 At every round we receive a request and propose a price (arm)
 We receive a reward from the environment (the customers)
 The price proposed if the customer bought the ticket
 0 otherwise
 Goal: maximize the sum of the rewards (minimize the “regret”)
BASIC ALGORITHMS
History of
contracts
 ε-greedy
 UCB
BASIC ALGORITHMS
 ε-greedy
 UCB
Round t
Random arm Current best arm
ε 1 − ε
BASIC ALGORITHMS
History of
contracts
 𝜺-greedy
 UCB
Compute UCB
for the mean of
each arm
Round t
Play arm with
highest UCB
UCB1, for arm j
ො𝑥 𝑗 +
2log 𝑡
𝑡𝑗
HYPOTHESIS AND LIMITATIONS
 Stationarity
 People can change behaviour
over time
 No context
 Additional information can be
used to take a better decision
Sliding windows
Contextual MAB
PROJECT BACKGROUND
 A part of the revenue of the provider comes from Metasearch engines
 Providers have access only to the context x and not to the user directly
User MS Provider
R(x) x
p(x)p(x)
SOLUTION OVERVIEW
DATA
TECH
• UCB1
• ORAT (Online Risk Averse Tree)ALGOS
Simulated requests from users
ALGORITHM DETAIL
 Contextual Multi-Armed Bandit
 Decision tree to partition the space of contexts
 Splits are made with confidence level
 A different policy in each partition based on UCB1
 Non-stationary environment
 Sliding window for UCB1
 Batch phase to change the partition of the decision tree
RM-LON
LON-PAR
3
21
! RM-LON
! LON-PAR
BUSINESS BENEFITS
Quantitative
• Increase of revenues
• Decrease of cost of maintenance
Qualitative
• Increase in customer satisfaction
• Increase in analytic know-how of
the process
• Improvement in testing process
RENEWAL PRICE
OPTIMIZATION FOR
SUBSCRIPTION PRODUCTS
Riccardo Lorenzon | Senior Data Scientist
THE PROJECT
 Customer:
Publishing Leader
 Description:
Let an algorithm decide the optimal
prices for renewal to subscription
products, given some boundaries and
objectives input by the customer
SUBSCRIPTION ECONOMY
In the Subscription Economy, every company must better
manage a direct, complex, responsive, multi-channel relationship
with its customers. Customers are absolutely key in this
relationship and rather than putting the focus of the business on
the “product” or the “transaction,” subscription economy
companies live and die by their ability to focus on the
customer. Now, the formula for growth is focused on monetizing
long-term relationships rather than shipping products.
Tien Tzuo – CEO, Zuora
SOLUTION OVERVIEW
DATA
TECH
• Elastic Net Regression
• Simplex Optimization Method + Euristics
ALGOS
History of
subscriptions
Refused price
proposals
Promotions
Customer Service
contacts
SOLUTION OVERVIEW
STEP 1:
DATA MODEL
PREPARATION
STEP 2:
ELASTICITY
CURVES
STEP 3:
PRICE
OPTIMIZATION
DATA PREPARATION
History of
subscriptions
Refused price
proposals
Promotions
Customer Service
contacts
Renewal Price Features
1 50 ...
0 58 ...
... ... ...
ELASTICITY CURVES
𝑙𝑜𝑔𝑖𝑡(𝑝) = 𝑓 𝑋 + 𝑔(𝑌)
𝑙𝑜𝑔𝑖𝑡(ෝ𝑝𝑖) = 𝛼𝑖 ∗ 𝑥 + 𝛽𝑖
ෝ𝑝𝑖 =
1
1 + 𝑒−(𝛼 𝑖∗𝑥+𝛽𝑖)
X: actionable variables
Y: non-actionable variables
p: renewal probability
x: price
ELASTICITY CURVES
We need to estimate a whole probability distribution
What is a good metric?
ELASTICITY CURVES
renewal probability vs. price
expected margin vs. price
PRICE OPTIMIZATION
Let the user input:
• Target KPIs
• Business specific onstraints
Get a global proposal of optimal
price for each contract
BUSINESS BENEFITS
Quantitative
• Increase of Revenues
• Increase of Margins
• Increase of Sales Volume
• Increase of Renewal Rate
• Increase of Campaigns success
rate
• Process Costs reductions
Qualitative • Increase Marketing analytic
know-how of customers
THANK YOU
i.gianoli@reply.it
g.corradini@reply.it
r.lorenzon@reply.it

More Related Content

What's hot

Odoo OpenERP 7 POS Retail Management
Odoo OpenERP 7 POS Retail ManagementOdoo OpenERP 7 POS Retail Management
Odoo OpenERP 7 POS Retail Management
pragmatic123
 
Product Pricing
Product PricingProduct Pricing
Product Pricing
Jeremy Horn
 
Online Business Models
Online Business ModelsOnline Business Models
Online Business Models
anandgclt
 
1 hrly eb ch 02 competitive advantage
1 hrly eb ch 02 competitive advantage1 hrly eb ch 02 competitive advantage
1 hrly eb ch 02 competitive advantageazmatmengal
 
Lt8 -distri strategiesforaspac
Lt8 -distri strategiesforaspacLt8 -distri strategiesforaspac
Lt8 -distri strategiesforaspacphanquoccuong
 
Assortment optimization based on consumer clustering and behavior modelling
Assortment optimization based on consumer clustering and behavior modellingAssortment optimization based on consumer clustering and behavior modelling
Assortment optimization based on consumer clustering and behavior modelling
ScienceSoft
 
6.4)How do business buyers make their decision?
6.4)How do business buyers make their decision?6.4)How do business buyers make their decision?
6.4)How do business buyers make their decision?
114iiminternship
 
Distribution channels for beginners presentation mar2015
Distribution channels for beginners presentation mar2015Distribution channels for beginners presentation mar2015
Distribution channels for beginners presentation mar2015
Jim Elder
 
Combining the marketing mix by Maxwell Ranasinghe
Combining the marketing mix by Maxwell RanasingheCombining the marketing mix by Maxwell Ranasinghe
Combining the marketing mix by Maxwell Ranasinghe
Maxwell Ranasinghe
 
How should a company set prices initially for products or services?
How should a company set prices initially for products or services?How should a company set prices initially for products or services?
How should a company set prices initially for products or services?Vaishnavi Ketharnathan
 
Schepers
SchepersSchepers
Schepers
Olaf Van Kooten
 
4retal instbyownrship
4retal instbyownrship4retal instbyownrship
4retal instbyownrship
Rishabh Sharma
 
MRS Advanced Analytics Innovation Symposium Presentation
MRS Advanced Analytics Innovation Symposium PresentationMRS Advanced Analytics Innovation Symposium Presentation
MRS Advanced Analytics Innovation Symposium Presentation
MRS
 
Difference between indusrial marketing & consumer marketing
Difference between indusrial marketing & consumer marketingDifference between indusrial marketing & consumer marketing
Difference between indusrial marketing & consumer marketingDr. Chandra Shekhar Singh
 
Industrial Marketing PowerPoint Presentation Slides
Industrial Marketing PowerPoint Presentation SlidesIndustrial Marketing PowerPoint Presentation Slides
Industrial Marketing PowerPoint Presentation Slides
SlideTeam
 
BB Chapter Six: Outlet Selection and Purchase
BB Chapter Six: Outlet Selection and PurchaseBB Chapter Six: Outlet Selection and Purchase
BB Chapter Six: Outlet Selection and PurchaseBBAdvisor
 
Pricing As A Strategic Marketing Tool
Pricing As A Strategic Marketing ToolPricing As A Strategic Marketing Tool
Pricing As A Strategic Marketing Tool
Thomas (Tom) Smith, III
 
Ppt.brands analysis
Ppt.brands analysisPpt.brands analysis
Ppt.brands analysis
Shiv Prasad
 

What's hot (20)

Odoo OpenERP 7 POS Retail Management
Odoo OpenERP 7 POS Retail ManagementOdoo OpenERP 7 POS Retail Management
Odoo OpenERP 7 POS Retail Management
 
Product Pricing
Product PricingProduct Pricing
Product Pricing
 
Online Business Models
Online Business ModelsOnline Business Models
Online Business Models
 
1 hrly eb ch 02 competitive advantage
1 hrly eb ch 02 competitive advantage1 hrly eb ch 02 competitive advantage
1 hrly eb ch 02 competitive advantage
 
Lt8 -distri strategiesforaspac
Lt8 -distri strategiesforaspacLt8 -distri strategiesforaspac
Lt8 -distri strategiesforaspac
 
Assortment optimization based on consumer clustering and behavior modelling
Assortment optimization based on consumer clustering and behavior modellingAssortment optimization based on consumer clustering and behavior modelling
Assortment optimization based on consumer clustering and behavior modelling
 
6.4)How do business buyers make their decision?
6.4)How do business buyers make their decision?6.4)How do business buyers make their decision?
6.4)How do business buyers make their decision?
 
Distribution channels for beginners presentation mar2015
Distribution channels for beginners presentation mar2015Distribution channels for beginners presentation mar2015
Distribution channels for beginners presentation mar2015
 
Combining the marketing mix by Maxwell Ranasinghe
Combining the marketing mix by Maxwell RanasingheCombining the marketing mix by Maxwell Ranasinghe
Combining the marketing mix by Maxwell Ranasinghe
 
How should a company set prices initially for products or services?
How should a company set prices initially for products or services?How should a company set prices initially for products or services?
How should a company set prices initially for products or services?
 
Schepers
SchepersSchepers
Schepers
 
4retal instbyownrship
4retal instbyownrship4retal instbyownrship
4retal instbyownrship
 
MRS Advanced Analytics Innovation Symposium Presentation
MRS Advanced Analytics Innovation Symposium PresentationMRS Advanced Analytics Innovation Symposium Presentation
MRS Advanced Analytics Innovation Symposium Presentation
 
Difference between indusrial marketing & consumer marketing
Difference between indusrial marketing & consumer marketingDifference between indusrial marketing & consumer marketing
Difference between indusrial marketing & consumer marketing
 
Industrial Marketing PowerPoint Presentation Slides
Industrial Marketing PowerPoint Presentation SlidesIndustrial Marketing PowerPoint Presentation Slides
Industrial Marketing PowerPoint Presentation Slides
 
BB Chapter Six: Outlet Selection and Purchase
BB Chapter Six: Outlet Selection and PurchaseBB Chapter Six: Outlet Selection and Purchase
BB Chapter Six: Outlet Selection and Purchase
 
Pricing As A Strategic Marketing Tool
Pricing As A Strategic Marketing ToolPricing As A Strategic Marketing Tool
Pricing As A Strategic Marketing Tool
 
Pricing
PricingPricing
Pricing
 
Ppt.brands analysis
Ppt.brands analysisPpt.brands analysis
Ppt.brands analysis
 
Ti vo analysis
Ti vo analysisTi vo analysis
Ti vo analysis
 

Similar to Pricing Optimization: Close-out, Online and Renewal strategies, Data Reply

[DSC Europe 22] Using AI to solve complex business problems: optimizing markd...
[DSC Europe 22] Using AI to solve complex business problems: optimizing markd...[DSC Europe 22] Using AI to solve complex business problems: optimizing markd...
[DSC Europe 22] Using AI to solve complex business problems: optimizing markd...
DataScienceConferenc1
 
How to research pricing decisions a presentation from business advantage
How to research pricing decisions   a presentation from business advantageHow to research pricing decisions   a presentation from business advantage
How to research pricing decisions a presentation from business advantage
Business Advantage
 
Is Short Term Delivery Impacting Customer Returns?
Is Short Term Delivery Impacting Customer Returns?Is Short Term Delivery Impacting Customer Returns?
Is Short Term Delivery Impacting Customer Returns?
Jay Ganapathy
 
Price is not a number - the secrets of pricing
Price is not a number - the secrets of pricingPrice is not a number - the secrets of pricing
Price is not a number - the secrets of pricing
Nevo Hadas
 
Cost To Serve
Cost To ServeCost To Serve
Cost To Serve
SCL HUB
 
Competitor & Pricing Intelligence Can Increase Your Retail GMV by 6% | JK Tec...
Competitor & Pricing Intelligence Can Increase Your Retail GMV by 6% | JK Tec...Competitor & Pricing Intelligence Can Increase Your Retail GMV by 6% | JK Tec...
Competitor & Pricing Intelligence Can Increase Your Retail GMV by 6% | JK Tec...
JK Tech
 
Supply Chain Collaboration: Consumer Packaged Goods Manufacturers & Retailers
Supply Chain Collaboration: Consumer Packaged Goods Manufacturers & RetailersSupply Chain Collaboration: Consumer Packaged Goods Manufacturers & Retailers
Supply Chain Collaboration: Consumer Packaged Goods Manufacturers & Retailers
Angela Carver
 
Building an algorithmic price management system using ML
Building an algorithmic price management system using MLBuilding an algorithmic price management system using ML
Building an algorithmic price management system using ML
Grid Dynamics
 
Applications of Big Data in Retail Pricing
Applications of Big Data in Retail PricingApplications of Big Data in Retail Pricing
Applications of Big Data in Retail Pricing
Daltix
 
Supply Chain Spends: Advancing Sourcing Beyond Procurement Suites
Supply Chain Spends: Advancing Sourcing Beyond Procurement Suites Supply Chain Spends: Advancing Sourcing Beyond Procurement Suites
Supply Chain Spends: Advancing Sourcing Beyond Procurement Suites
CombineNet, Inc.
 
UNVEILING VALUE-BASED BIDDING SECRETS FOR MAXIMUM EFFICIENCY GAIN.pptx
UNVEILING VALUE-BASED BIDDING SECRETS FOR MAXIMUM EFFICIENCY GAIN.pptxUNVEILING VALUE-BASED BIDDING SECRETS FOR MAXIMUM EFFICIENCY GAIN.pptx
UNVEILING VALUE-BASED BIDDING SECRETS FOR MAXIMUM EFFICIENCY GAIN.pptx
Doug Hall
 
Lean canvas @ Université TOTAL 2016
Lean canvas @ Université TOTAL 2016Lean canvas @ Université TOTAL 2016
Lean canvas @ Université TOTAL 2016
Santiago LEFEBVRE
 
Warehouse and distribution footprint
Warehouse and distribution footprintWarehouse and distribution footprint
Warehouse and distribution footprint
Implement Consulting Group
 
Strategy DevelopmentWeek 3Objectives Week 3Devel.docx
Strategy DevelopmentWeek 3Objectives Week 3Devel.docxStrategy DevelopmentWeek 3Objectives Week 3Devel.docx
Strategy DevelopmentWeek 3Objectives Week 3Devel.docx
johniemcm5zt
 
Retail Webinar - How to Stay 10 Steps Ahead of Retail Competitors?
Retail Webinar - How to Stay 10 Steps Ahead of Retail Competitors?Retail Webinar - How to Stay 10 Steps Ahead of Retail Competitors?
Retail Webinar - How to Stay 10 Steps Ahead of Retail Competitors?
JK Tech
 
Analytics for the supply chain
Analytics for the supply chain Analytics for the supply chain
Analytics for the supply chain
Saurav Kumar
 

Similar to Pricing Optimization: Close-out, Online and Renewal strategies, Data Reply (20)

business model chapter 4
business model chapter 4business model chapter 4
business model chapter 4
 
[DSC Europe 22] Using AI to solve complex business problems: optimizing markd...
[DSC Europe 22] Using AI to solve complex business problems: optimizing markd...[DSC Europe 22] Using AI to solve complex business problems: optimizing markd...
[DSC Europe 22] Using AI to solve complex business problems: optimizing markd...
 
How to research pricing decisions a presentation from business advantage
How to research pricing decisions   a presentation from business advantageHow to research pricing decisions   a presentation from business advantage
How to research pricing decisions a presentation from business advantage
 
Is Short Term Delivery Impacting Customer Returns?
Is Short Term Delivery Impacting Customer Returns?Is Short Term Delivery Impacting Customer Returns?
Is Short Term Delivery Impacting Customer Returns?
 
Price is not a number - the secrets of pricing
Price is not a number - the secrets of pricingPrice is not a number - the secrets of pricing
Price is not a number - the secrets of pricing
 
Cost To Serve
Cost To ServeCost To Serve
Cost To Serve
 
Cost To Serve
Cost To ServeCost To Serve
Cost To Serve
 
Competitor & Pricing Intelligence Can Increase Your Retail GMV by 6% | JK Tec...
Competitor & Pricing Intelligence Can Increase Your Retail GMV by 6% | JK Tec...Competitor & Pricing Intelligence Can Increase Your Retail GMV by 6% | JK Tec...
Competitor & Pricing Intelligence Can Increase Your Retail GMV by 6% | JK Tec...
 
Supply Chain Collaboration: Consumer Packaged Goods Manufacturers & Retailers
Supply Chain Collaboration: Consumer Packaged Goods Manufacturers & RetailersSupply Chain Collaboration: Consumer Packaged Goods Manufacturers & Retailers
Supply Chain Collaboration: Consumer Packaged Goods Manufacturers & Retailers
 
Building an algorithmic price management system using ML
Building an algorithmic price management system using MLBuilding an algorithmic price management system using ML
Building an algorithmic price management system using ML
 
Applications of Big Data in Retail Pricing
Applications of Big Data in Retail PricingApplications of Big Data in Retail Pricing
Applications of Big Data in Retail Pricing
 
Supply Chain Spends: Advancing Sourcing Beyond Procurement Suites
Supply Chain Spends: Advancing Sourcing Beyond Procurement Suites Supply Chain Spends: Advancing Sourcing Beyond Procurement Suites
Supply Chain Spends: Advancing Sourcing Beyond Procurement Suites
 
SES London
SES LondonSES London
SES London
 
UNVEILING VALUE-BASED BIDDING SECRETS FOR MAXIMUM EFFICIENCY GAIN.pptx
UNVEILING VALUE-BASED BIDDING SECRETS FOR MAXIMUM EFFICIENCY GAIN.pptxUNVEILING VALUE-BASED BIDDING SECRETS FOR MAXIMUM EFFICIENCY GAIN.pptx
UNVEILING VALUE-BASED BIDDING SECRETS FOR MAXIMUM EFFICIENCY GAIN.pptx
 
Lean canvas @ Université TOTAL 2016
Lean canvas @ Université TOTAL 2016Lean canvas @ Université TOTAL 2016
Lean canvas @ Université TOTAL 2016
 
Warehouse and distribution footprint
Warehouse and distribution footprintWarehouse and distribution footprint
Warehouse and distribution footprint
 
Strategy DevelopmentWeek 3Objectives Week 3Devel.docx
Strategy DevelopmentWeek 3Objectives Week 3Devel.docxStrategy DevelopmentWeek 3Objectives Week 3Devel.docx
Strategy DevelopmentWeek 3Objectives Week 3Devel.docx
 
Bmgt 411 week_8
Bmgt 411 week_8Bmgt 411 week_8
Bmgt 411 week_8
 
Retail Webinar - How to Stay 10 Steps Ahead of Retail Competitors?
Retail Webinar - How to Stay 10 Steps Ahead of Retail Competitors?Retail Webinar - How to Stay 10 Steps Ahead of Retail Competitors?
Retail Webinar - How to Stay 10 Steps Ahead of Retail Competitors?
 
Analytics for the supply chain
Analytics for the supply chain Analytics for the supply chain
Analytics for the supply chain
 

More from Data Science Milan

ML & Graph algorithms to prevent financial crime in digital payments
ML & Graph  algorithms to prevent  financial crime in  digital paymentsML & Graph  algorithms to prevent  financial crime in  digital payments
ML & Graph algorithms to prevent financial crime in digital payments
Data Science Milan
 
How to use the Economic Complexity Index to guide innovation plans
How to use the Economic Complexity Index to guide innovation plansHow to use the Economic Complexity Index to guide innovation plans
How to use the Economic Complexity Index to guide innovation plans
Data Science Milan
 
Robustness Metrics for ML Models based on Deep Learning Methods
Robustness Metrics for ML Models based on Deep Learning MethodsRobustness Metrics for ML Models based on Deep Learning Methods
Robustness Metrics for ML Models based on Deep Learning Methods
Data Science Milan
 
"You don't need a bigger boat": serverless MLOps for reasonable companies
"You don't need a bigger boat": serverless MLOps for reasonable companies"You don't need a bigger boat": serverless MLOps for reasonable companies
"You don't need a bigger boat": serverless MLOps for reasonable companies
Data Science Milan
 
Question generation using Natural Language Processing by QuestGen.AI
Question generation using Natural Language Processing by QuestGen.AIQuestion generation using Natural Language Processing by QuestGen.AI
Question generation using Natural Language Processing by QuestGen.AI
Data Science Milan
 
Speed up data preparation for ML pipelines on AWS
Speed up data preparation for ML pipelines on AWSSpeed up data preparation for ML pipelines on AWS
Speed up data preparation for ML pipelines on AWS
Data Science Milan
 
Serverless machine learning architectures at Helixa
Serverless machine learning architectures at HelixaServerless machine learning architectures at Helixa
Serverless machine learning architectures at Helixa
Data Science Milan
 
MLOps with a Feature Store: Filling the Gap in ML Infrastructure
MLOps with a Feature Store: Filling the Gap in ML InfrastructureMLOps with a Feature Store: Filling the Gap in ML Infrastructure
MLOps with a Feature Store: Filling the Gap in ML Infrastructure
Data Science Milan
 
Reinforcement Learning Overview | Marco Del Pra
Reinforcement Learning Overview | Marco Del PraReinforcement Learning Overview | Marco Del Pra
Reinforcement Learning Overview | Marco Del Pra
Data Science Milan
 
Time Series Classification with Deep Learning | Marco Del Pra
Time Series Classification with Deep Learning | Marco Del PraTime Series Classification with Deep Learning | Marco Del Pra
Time Series Classification with Deep Learning | Marco Del Pra
Data Science Milan
 
Ludwig: A code-free deep learning toolbox | Piero Molino, Uber AI
Ludwig: A code-free deep learning toolbox | Piero Molino, Uber AILudwig: A code-free deep learning toolbox | Piero Molino, Uber AI
Ludwig: A code-free deep learning toolbox | Piero Molino, Uber AI
Data Science Milan
 
Audience projection of target consumers over multiple domains a ner and baye...
Audience projection of target consumers over multiple domains  a ner and baye...Audience projection of target consumers over multiple domains  a ner and baye...
Audience projection of target consumers over multiple domains a ner and baye...
Data Science Milan
 
Weak supervised learning - Kristina Khvatova
Weak supervised learning - Kristina KhvatovaWeak supervised learning - Kristina Khvatova
Weak supervised learning - Kristina Khvatova
Data Science Milan
 
GANs beyond nice pictures: real value of data generation, Alex Honchar
GANs beyond nice pictures: real value of data generation, Alex HoncharGANs beyond nice pictures: real value of data generation, Alex Honchar
GANs beyond nice pictures: real value of data generation, Alex Honchar
Data Science Milan
 
Continual/Lifelong Learning with Deep Architectures, Vincenzo Lomonaco
Continual/Lifelong Learning with Deep Architectures, Vincenzo LomonacoContinual/Lifelong Learning with Deep Architectures, Vincenzo Lomonaco
Continual/Lifelong Learning with Deep Architectures, Vincenzo Lomonaco
Data Science Milan
 
3D Point Cloud analysis using Deep Learning
3D Point Cloud analysis using Deep Learning3D Point Cloud analysis using Deep Learning
3D Point Cloud analysis using Deep Learning
Data Science Milan
 
Deep time-to-failure: predicting failures, churns and customer lifetime with ...
Deep time-to-failure: predicting failures, churns and customer lifetime with ...Deep time-to-failure: predicting failures, churns and customer lifetime with ...
Deep time-to-failure: predicting failures, churns and customer lifetime with ...
Data Science Milan
 
50 Shades of Text - Leveraging Natural Language Processing (NLP), Alessandro ...
50 Shades of Text - Leveraging Natural Language Processing (NLP), Alessandro ...50 Shades of Text - Leveraging Natural Language Processing (NLP), Alessandro ...
50 Shades of Text - Leveraging Natural Language Processing (NLP), Alessandro ...
Data Science Milan
 
"How Pirelli uses Domino and Plotly for Smart Manufacturing" by Alberto Arrig...
"How Pirelli uses Domino and Plotly for Smart Manufacturing" by Alberto Arrig..."How Pirelli uses Domino and Plotly for Smart Manufacturing" by Alberto Arrig...
"How Pirelli uses Domino and Plotly for Smart Manufacturing" by Alberto Arrig...
Data Science Milan
 
A view of graph data usage by Cerved
A view of graph data usage by CervedA view of graph data usage by Cerved
A view of graph data usage by Cerved
Data Science Milan
 

More from Data Science Milan (20)

ML & Graph algorithms to prevent financial crime in digital payments
ML & Graph  algorithms to prevent  financial crime in  digital paymentsML & Graph  algorithms to prevent  financial crime in  digital payments
ML & Graph algorithms to prevent financial crime in digital payments
 
How to use the Economic Complexity Index to guide innovation plans
How to use the Economic Complexity Index to guide innovation plansHow to use the Economic Complexity Index to guide innovation plans
How to use the Economic Complexity Index to guide innovation plans
 
Robustness Metrics for ML Models based on Deep Learning Methods
Robustness Metrics for ML Models based on Deep Learning MethodsRobustness Metrics for ML Models based on Deep Learning Methods
Robustness Metrics for ML Models based on Deep Learning Methods
 
"You don't need a bigger boat": serverless MLOps for reasonable companies
"You don't need a bigger boat": serverless MLOps for reasonable companies"You don't need a bigger boat": serverless MLOps for reasonable companies
"You don't need a bigger boat": serverless MLOps for reasonable companies
 
Question generation using Natural Language Processing by QuestGen.AI
Question generation using Natural Language Processing by QuestGen.AIQuestion generation using Natural Language Processing by QuestGen.AI
Question generation using Natural Language Processing by QuestGen.AI
 
Speed up data preparation for ML pipelines on AWS
Speed up data preparation for ML pipelines on AWSSpeed up data preparation for ML pipelines on AWS
Speed up data preparation for ML pipelines on AWS
 
Serverless machine learning architectures at Helixa
Serverless machine learning architectures at HelixaServerless machine learning architectures at Helixa
Serverless machine learning architectures at Helixa
 
MLOps with a Feature Store: Filling the Gap in ML Infrastructure
MLOps with a Feature Store: Filling the Gap in ML InfrastructureMLOps with a Feature Store: Filling the Gap in ML Infrastructure
MLOps with a Feature Store: Filling the Gap in ML Infrastructure
 
Reinforcement Learning Overview | Marco Del Pra
Reinforcement Learning Overview | Marco Del PraReinforcement Learning Overview | Marco Del Pra
Reinforcement Learning Overview | Marco Del Pra
 
Time Series Classification with Deep Learning | Marco Del Pra
Time Series Classification with Deep Learning | Marco Del PraTime Series Classification with Deep Learning | Marco Del Pra
Time Series Classification with Deep Learning | Marco Del Pra
 
Ludwig: A code-free deep learning toolbox | Piero Molino, Uber AI
Ludwig: A code-free deep learning toolbox | Piero Molino, Uber AILudwig: A code-free deep learning toolbox | Piero Molino, Uber AI
Ludwig: A code-free deep learning toolbox | Piero Molino, Uber AI
 
Audience projection of target consumers over multiple domains a ner and baye...
Audience projection of target consumers over multiple domains  a ner and baye...Audience projection of target consumers over multiple domains  a ner and baye...
Audience projection of target consumers over multiple domains a ner and baye...
 
Weak supervised learning - Kristina Khvatova
Weak supervised learning - Kristina KhvatovaWeak supervised learning - Kristina Khvatova
Weak supervised learning - Kristina Khvatova
 
GANs beyond nice pictures: real value of data generation, Alex Honchar
GANs beyond nice pictures: real value of data generation, Alex HoncharGANs beyond nice pictures: real value of data generation, Alex Honchar
GANs beyond nice pictures: real value of data generation, Alex Honchar
 
Continual/Lifelong Learning with Deep Architectures, Vincenzo Lomonaco
Continual/Lifelong Learning with Deep Architectures, Vincenzo LomonacoContinual/Lifelong Learning with Deep Architectures, Vincenzo Lomonaco
Continual/Lifelong Learning with Deep Architectures, Vincenzo Lomonaco
 
3D Point Cloud analysis using Deep Learning
3D Point Cloud analysis using Deep Learning3D Point Cloud analysis using Deep Learning
3D Point Cloud analysis using Deep Learning
 
Deep time-to-failure: predicting failures, churns and customer lifetime with ...
Deep time-to-failure: predicting failures, churns and customer lifetime with ...Deep time-to-failure: predicting failures, churns and customer lifetime with ...
Deep time-to-failure: predicting failures, churns and customer lifetime with ...
 
50 Shades of Text - Leveraging Natural Language Processing (NLP), Alessandro ...
50 Shades of Text - Leveraging Natural Language Processing (NLP), Alessandro ...50 Shades of Text - Leveraging Natural Language Processing (NLP), Alessandro ...
50 Shades of Text - Leveraging Natural Language Processing (NLP), Alessandro ...
 
"How Pirelli uses Domino and Plotly for Smart Manufacturing" by Alberto Arrig...
"How Pirelli uses Domino and Plotly for Smart Manufacturing" by Alberto Arrig..."How Pirelli uses Domino and Plotly for Smart Manufacturing" by Alberto Arrig...
"How Pirelli uses Domino and Plotly for Smart Manufacturing" by Alberto Arrig...
 
A view of graph data usage by Cerved
A view of graph data usage by CervedA view of graph data usage by Cerved
A view of graph data usage by Cerved
 

Recently uploaded

Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
OnBoard
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
Jemma Hussein Allen
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
Dorra BARTAGUIZ
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Product School
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
Laura Byrne
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
DianaGray10
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
Prayukth K V
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
DianaGray10
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
g2nightmarescribd
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
91mobiles
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Ramesh Iyer
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
KatiaHIMEUR1
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
Product School
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
Alan Dix
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
Product School
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
UiPathCommunity
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Albert Hoitingh
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
ThousandEyes
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
James Anderson
 

Recently uploaded (20)

Leading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdfLeading Change strategies and insights for effective change management pdf 1.pdf
Leading Change strategies and insights for effective change management pdf 1.pdf
 
The Future of Platform Engineering
The Future of Platform EngineeringThe Future of Platform Engineering
The Future of Platform Engineering
 
Elevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object CalisthenicsElevating Tactical DDD Patterns Through Object Calisthenics
Elevating Tactical DDD Patterns Through Object Calisthenics
 
Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...Designing Great Products: The Power of Design and Leadership by Chief Designe...
Designing Great Products: The Power of Design and Leadership by Chief Designe...
 
The Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and SalesThe Art of the Pitch: WordPress Relationships and Sales
The Art of the Pitch: WordPress Relationships and Sales
 
UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4UiPath Test Automation using UiPath Test Suite series, part 4
UiPath Test Automation using UiPath Test Suite series, part 4
 
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 previewState of ICS and IoT Cyber Threat Landscape Report 2024 preview
State of ICS and IoT Cyber Threat Landscape Report 2024 preview
 
UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3UiPath Test Automation using UiPath Test Suite series, part 3
UiPath Test Automation using UiPath Test Suite series, part 3
 
Generating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using SmithyGenerating a custom Ruby SDK for your web service or Rails API using Smithy
Generating a custom Ruby SDK for your web service or Rails API using Smithy
 
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdfSmart TV Buyer Insights Survey 2024 by 91mobiles.pdf
Smart TV Buyer Insights Survey 2024 by 91mobiles.pdf
 
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
Builder.ai Founder Sachin Dev Duggal's Strategic Approach to Create an Innova...
 
Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !Securing your Kubernetes cluster_ a step-by-step guide to success !
Securing your Kubernetes cluster_ a step-by-step guide to success !
 
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
AI for Every Business: Unlocking Your Product's Universal Potential by VP of ...
 
Epistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI supportEpistemic Interaction - tuning interfaces to provide information for AI support
Epistemic Interaction - tuning interfaces to provide information for AI support
 
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
De-mystifying Zero to One: Design Informed Techniques for Greenfield Innovati...
 
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
Dev Dives: Train smarter, not harder – active learning and UiPath LLMs for do...
 
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
Encryption in Microsoft 365 - ExpertsLive Netherlands 2024
 
Assuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyesAssuring Contact Center Experiences for Your Customers With ThousandEyes
Assuring Contact Center Experiences for Your Customers With ThousandEyes
 
FIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdfFIDO Alliance Osaka Seminar: Overview.pdf
FIDO Alliance Osaka Seminar: Overview.pdf
 
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
GDG Cloud Southlake #33: Boule & Rebala: Effective AppSec in SDLC using Deplo...
 

Pricing Optimization: Close-out, Online and Renewal strategies, Data Reply

  • 1. PRICING OPTIMIZATION IN DATA REPLY Ilaria Gianoli | Data Scientist Giovanni Corradini | Data Scientist Riccardo Lorenzon | Senior Data Scientist
  • 2. OPTIMAL DISCOUNT STRATEGY FOR PRODUCTS IN CLOSE-OUT PHASE Ilaria Gianoli | Data Scientist
  • 3.  Customer: Retail/GDO Leader  Description: Identify the optimal discount strategy for products in their close-out phase, as a trade-off between margin loss and inventory cost THE PROBLEM
  • 4. PROJECT BACKGROUNDInfo • The purchasing department establishes when a product goes out of range • In the close-out phase, the stores have limited time to get rid of the leftover stock, otherwise the have to pay a penalty • Each store chooses autonomously the discount to apply Alert • The product prices do not change often, except during the marketing campaign • The wide product range requires the elasticity model to be product- specific
  • 5. SOLUTION OVERVIEW DATA TECH • Elasticity model: linear regression • Clustering model: DBscan • Time series forecast: arima + FFNN + seasonal rescaling ALGOS Sales Prices Product info Stock Promotions
  • 6. SOLUTION DETAIL STEP 1: SALES FORECASTING STEP 2: PRICE ELASTICITY STEP 3: DISCOUNT OPTIMIZATION • Use all the information about sellout, stock, prices, calendar, marketing and discount campaigns to create a clean time series; • Create a forecast model on a weekly basis according to the nature of the product (new, young, historical). The forecast is at a product-store level;
  • 7. SOLUTION DETAIL • Use specific department weights to remove seasonality from the time series; • Create an elasticity model at product level; • Clusterize the products according to their sales potential and price range; • Create a hierarchical elasticity model STEP 1: SALES FORECASTING STEP 2: PRICE ELASTICITY STEP 3: DISCOUNT OPTIMIZATION
  • 8. SOLUTION DETAIL • Use the forecast model to estimate T*, i.e. the time in which the stock is exhausted; • Use the price elasticity coefficent to compute the Δp for the desired Δq; • Choose the optimal discount as ത𝑇 = 𝑎𝑟𝑔 max 𝑡 ∈[𝑇,𝑇∗] (𝑚𝑎𝑟𝑔𝑖𝑛 𝑝 𝑡 − 𝑓𝑒𝑒 𝑡 ) with stock(t) = 0 STEP 1: SALES FORECASTING STEP 2: PRICE ELASTICITY STEP 3: DISCOUNT OPTIMIZATION
  • 9. BUSINESS BENEFITS Quantitative • Revenue improvement • Reduction in penalties • Reduction in inventory costs Qualitative • More visibility to new products • Better space allocation in stores • Homogeneity among stores
  • 10. ONLINE PRICING: FROM THEORY TO APPLICATION Giovanni Corradini| Data Scientist
  • 11. THE PROBLEM  Customer: Ticket selling company  Problem: Choose the price that maximize the total revenue through application of Contextual Multi-Armed Bandit algorithm
  • 12. THE TRADE-OFF  Exploration  Find the best price by proposing different prices  Many mistakes  Exploitation  Propose current best price to make money  Maybe not the optimal one
  • 13. A/B TESTING VS MULTI-ARMED BANDIT  A/B Testing  Multi-Armed Bandit
  • 14. THEORETICAL BACKGROUND History of contracts  Bandit setting:  Consider n rounds  At every round we receive a request and propose a price (arm)  We receive a reward from the environment (the customers)  The price proposed if the customer bought the ticket  0 otherwise  Goal: maximize the sum of the rewards (minimize the “regret”)
  • 16. BASIC ALGORITHMS  ε-greedy  UCB Round t Random arm Current best arm ε 1 − ε
  • 17. BASIC ALGORITHMS History of contracts  𝜺-greedy  UCB Compute UCB for the mean of each arm Round t Play arm with highest UCB UCB1, for arm j ො𝑥 𝑗 + 2log 𝑡 𝑡𝑗
  • 18. HYPOTHESIS AND LIMITATIONS  Stationarity  People can change behaviour over time  No context  Additional information can be used to take a better decision Sliding windows Contextual MAB
  • 19. PROJECT BACKGROUND  A part of the revenue of the provider comes from Metasearch engines  Providers have access only to the context x and not to the user directly User MS Provider R(x) x p(x)p(x)
  • 20. SOLUTION OVERVIEW DATA TECH • UCB1 • ORAT (Online Risk Averse Tree)ALGOS Simulated requests from users
  • 21. ALGORITHM DETAIL  Contextual Multi-Armed Bandit  Decision tree to partition the space of contexts  Splits are made with confidence level  A different policy in each partition based on UCB1  Non-stationary environment  Sliding window for UCB1  Batch phase to change the partition of the decision tree RM-LON LON-PAR 3 21 ! RM-LON ! LON-PAR
  • 22. BUSINESS BENEFITS Quantitative • Increase of revenues • Decrease of cost of maintenance Qualitative • Increase in customer satisfaction • Increase in analytic know-how of the process • Improvement in testing process
  • 23. RENEWAL PRICE OPTIMIZATION FOR SUBSCRIPTION PRODUCTS Riccardo Lorenzon | Senior Data Scientist
  • 24. THE PROJECT  Customer: Publishing Leader  Description: Let an algorithm decide the optimal prices for renewal to subscription products, given some boundaries and objectives input by the customer
  • 25. SUBSCRIPTION ECONOMY In the Subscription Economy, every company must better manage a direct, complex, responsive, multi-channel relationship with its customers. Customers are absolutely key in this relationship and rather than putting the focus of the business on the “product” or the “transaction,” subscription economy companies live and die by their ability to focus on the customer. Now, the formula for growth is focused on monetizing long-term relationships rather than shipping products. Tien Tzuo – CEO, Zuora
  • 26. SOLUTION OVERVIEW DATA TECH • Elastic Net Regression • Simplex Optimization Method + Euristics ALGOS History of subscriptions Refused price proposals Promotions Customer Service contacts
  • 27. SOLUTION OVERVIEW STEP 1: DATA MODEL PREPARATION STEP 2: ELASTICITY CURVES STEP 3: PRICE OPTIMIZATION
  • 28. DATA PREPARATION History of subscriptions Refused price proposals Promotions Customer Service contacts Renewal Price Features 1 50 ... 0 58 ... ... ... ...
  • 29. ELASTICITY CURVES 𝑙𝑜𝑔𝑖𝑡(𝑝) = 𝑓 𝑋 + 𝑔(𝑌) 𝑙𝑜𝑔𝑖𝑡(ෝ𝑝𝑖) = 𝛼𝑖 ∗ 𝑥 + 𝛽𝑖 ෝ𝑝𝑖 = 1 1 + 𝑒−(𝛼 𝑖∗𝑥+𝛽𝑖) X: actionable variables Y: non-actionable variables p: renewal probability x: price
  • 30. ELASTICITY CURVES We need to estimate a whole probability distribution What is a good metric?
  • 31. ELASTICITY CURVES renewal probability vs. price expected margin vs. price
  • 32. PRICE OPTIMIZATION Let the user input: • Target KPIs • Business specific onstraints Get a global proposal of optimal price for each contract
  • 33. BUSINESS BENEFITS Quantitative • Increase of Revenues • Increase of Margins • Increase of Sales Volume • Increase of Renewal Rate • Increase of Campaigns success rate • Process Costs reductions Qualitative • Increase Marketing analytic know-how of customers