SlideShare uma empresa Scribd logo
1 de 14
Copyright 2014-15 Retail Automata Analytics www.retailreco.com 1
Accurate Recommendations For Retailers
of all sizes and domains
A Predictive Analytics Breakthrough
(This presentation contains brief disclosure of a patent pending technology)
www.retailreco.com
Copyright 2014-15 Retail Automata Analytics www.retailreco.com
Copyright 2014-15 Retail Automata Analytics www.retailreco.com
WHAT WORKS FOR TOP 1% DOES NOT WORK FOR 99%
Challenges of Predictive Analytics for such drastically different data sets are different.
1% 99%
.
Copyright 2014-15 Retail Automata Analytics www.retailreco.com
GENERATING PREDICTIONS FOR 99% RETAILERS IS TOUGH
Process of generating future buys of
customer involves analysis of past
purchase histories of customers and
items. To derive meaningful
analytical insights repeat sales
history of same item is required.
While huge repeat sale history of
any single item is present for top 1%
like Amazon.
For most of the retailers this is an
uncommon luxury.
The problem of Predictive Analytics is much more difficult for most of the retailers
than for the top 1% of retailers.
At the same time bandwidth and $resources necessary for research into Predictive
analytics is also not available for SME retailers.
Copyright 2014-15 Retail Automata Analytics www.retailreco.com
COLD START PROBLEM
For a new item or a new customer there exists no previous data.
Hence no predicted buyers of the item or item to item recommendations can be
made on day one.
Copyright 2014-15 Retail Automata Analytics www.retailreco.com
FREQUENTLY CHANGING CATALOG PROBLEM
By the time enough sales history of an item is recorded. That item is no longer in
the inventory.
An out of stock item can not be recommended to customers. Nor can it become
part of other items "people who bought this also bought these"
recommendations.
One of kind sellers like jewelers where every item is unique can be an extreme
case of frequently changing catalog problem.
Copyright 2014-15 Retail Automata Analytics www.retailreco.com 7
THE RETAILRECO SOLUTION TO RECOMMENDATION PROBLEM
As noted down the most fundamental problem of 99% retailers is the lack of
sufficient sales history.
Products come and go, For every customer characteristic Unique Blue Print of
Relevancy Remains the same.
Copyright 2014-15 Retail Automata Analytics www.retailreco.com 8
THE ABILITY TO DERIVE MEANINGFUL INSIGHT STARTS WITH
DEFINING THE RIGHT ABSTRACTIONS AND MODEL FOR ANALYSIS
WE STARTED WITH IDENTIFICATION OF ENTITIES WHICH
MATTER THE MOST FOR A RETAIL BUSINESS
We form The blueprint or retail DNA of every customer on the basis of most
fundamental buy decision making entities of retail.
Copyright 2014-15 Retail Automata Analytics www.retailreco.com 9
FIVE FUNDAMENTAL BUY DECISION MAKING
ENTITIES OF RETAIL ECOLOGY
Decision Making Feature Sets
A retail business is characterized by one or more types of
products with different features.
Exact values of different features combined together is
the primary buy decision making factor for customer.
Unlike the content based recommender system where
every feature value like “color” is treated as independent
decision factor. In our model the exact values of all
features that has occurred in all historical sources of
customer preference data forms the character of retail
business.
Not many like the “Navy Blue” shirt, while even fewer
people have the preference for “White” jeans.
Copyright 2014-15 Retail Automata Analytics www.retailreco.com 10
SECOND ENTITY: AFFORDABILITY OR PRICE RANGES
Price of an item is a critical buy decision
making factor
Affordability of the same customer can be
different for different types of products.
A person who likes to buy most expensive
Diamond Solitaire ring may be willing to buy
quartz watches only in the lower price ranges.
For predictive analytics purposes a
classification of buy within just a single defined
price range is also not sufficient. Just above or
below the defined price range the person is
still has interest in that specific product type
having same decision making feature set value.
Affordability Price Ranges for any specific
feature set values is given a very special
consideration in our approach of prediction
generation.
Copyright 2014-15 Retail Automata Analytics www.retailreco.com 11
THIRD ENTITY: FRUGALITY OR DISCOUNT SENSITIVITY
Some customers’ have a tendency to be more
sensitive to the amount of discount in making
the buy decision compared to others. This
tendency is not only restricted to the customer
dimension but can be generalized to include
the product dimension also i.e. some products
have the higher likelihood of being bought
with deep discounts while others are not so
sensitive to discounting.
A discounted sale record should have lesser
impact on process of generating predictions,
compared to a sale record at full price.
Furthermore for marketing purposes customer
segmentation on the basis of Frugality
consideration can be very effective for
different business objectives like clearance sale
or premium product launch.
Copyright 2014-15 Retail Automata Analytics www.retailreco.com 12
CUSTOMER EVOLUTION AND SEASONALITY
Buying behaviour of customer changes
over period of time. This is intelligently
captured in our system.
Seasonal purchasing of different
products is different. We note it
down so that retailer can utilize
this information.
Copyright 2014-15 Retail Automata Analytics www.retailreco.com 13
UNIFIED PREDICTIVE RETAIL ECO-SYSTEM
+
Exact values present in all historical data sources,
of all different feature sets and corresponding
affordability price ranges forms the structure of
data used for predictive analytics.
DATA ADAPTERS
Unify the customer preference data from all
historical sources including offline and online
store sales history, shopping cart, browsing
history, social media etc. Each data source can
have different importance or weight.
+ Affect the strength of sales record contribution
to predictive analytics data structure.
Copyright 2014-15 Retail Automata Analytics www.retailreco.com 14
INTELLIGENT CORE
All the disclosure of the invention presented in this presentation are covered under patent application
“Unified Predictive Retail Eco-System” : (number: 2465/MUM/2015).
RESULT: MOST ACCURATE PREDICTIONS OF FUTURE BUYS
FOR RETAILERS OF ALL SIZE AND DOMAINS
Along with the Seasonality of Products and Frugality of customers (as well as
products) noted down. Which are powerful customer segmentation criteria for
RetailReco campaigning system.
A Personalized Omni-Channel world of only relevant products is automatically
created for every customer.
Applies Big Data technologies to handle scalability.
Sparsity in Unified abstracted predictive analytics data
structure is handled by Dimensionality reduction
techniques.
Effect of frequent purchases of a small set of products
or customers buying all products is handled by
normalization techniques.

Mais conteúdo relacionado

Mais procurados

How to Drive Growth in a Multi-channel Retail Business
How to Drive Growth in a Multi-channel Retail BusinessHow to Drive Growth in a Multi-channel Retail Business
How to Drive Growth in a Multi-channel Retail BusinessVision33
 
Mobile Payment Statistics Review, July 2015
Mobile Payment Statistics Review, July 2015Mobile Payment Statistics Review, July 2015
Mobile Payment Statistics Review, July 2015Mocapay
 
Market Sizing
Market SizingMarket Sizing
Market Sizingmontu17
 
Presentación Andres Angelani - eCommerce Day Santiago 2016
Presentación Andres Angelani - eCommerce Day Santiago 2016Presentación Andres Angelani - eCommerce Day Santiago 2016
Presentación Andres Angelani - eCommerce Day Santiago 2016eCommerce Institute
 
New innovative solution for retail stores
New innovative solution for retail storesNew innovative solution for retail stores
New innovative solution for retail storesnassirj
 
Business Intelligence for Retail - ScienceSoft
Business Intelligence for Retail - ScienceSoftBusiness Intelligence for Retail - ScienceSoft
Business Intelligence for Retail - ScienceSoftScienceSoft
 
Is The IT B2B Market Broken?
Is The IT B2B Market Broken? Is The IT B2B Market Broken?
Is The IT B2B Market Broken? Probrand
 

Mais procurados (7)

How to Drive Growth in a Multi-channel Retail Business
How to Drive Growth in a Multi-channel Retail BusinessHow to Drive Growth in a Multi-channel Retail Business
How to Drive Growth in a Multi-channel Retail Business
 
Mobile Payment Statistics Review, July 2015
Mobile Payment Statistics Review, July 2015Mobile Payment Statistics Review, July 2015
Mobile Payment Statistics Review, July 2015
 
Market Sizing
Market SizingMarket Sizing
Market Sizing
 
Presentación Andres Angelani - eCommerce Day Santiago 2016
Presentación Andres Angelani - eCommerce Day Santiago 2016Presentación Andres Angelani - eCommerce Day Santiago 2016
Presentación Andres Angelani - eCommerce Day Santiago 2016
 
New innovative solution for retail stores
New innovative solution for retail storesNew innovative solution for retail stores
New innovative solution for retail stores
 
Business Intelligence for Retail - ScienceSoft
Business Intelligence for Retail - ScienceSoftBusiness Intelligence for Retail - ScienceSoft
Business Intelligence for Retail - ScienceSoft
 
Is The IT B2B Market Broken?
Is The IT B2B Market Broken? Is The IT B2B Market Broken?
Is The IT B2B Market Broken?
 

Destaque (6)

Test day 2012
Test day 2012Test day 2012
Test day 2012
 
La empresa
La empresaLa empresa
La empresa
 
Practica de word de andrea celi
Practica de word de andrea celiPractica de word de andrea celi
Practica de word de andrea celi
 
Análisis y recuperación de costes
Análisis y recuperación de costesAnálisis y recuperación de costes
Análisis y recuperación de costes
 
Programa congreso ALV
Programa congreso ALVPrograma congreso ALV
Programa congreso ALV
 
Pacie bloque 0
Pacie bloque 0Pacie bloque 0
Pacie bloque 0
 

Semelhante a breakthroughinpredictiveanalyticsforretailers-150728062328-lva1-app6891

Explicato Company Overview
Explicato Company OverviewExplicato Company Overview
Explicato Company OverviewGeorge Yankov
 
Ecomm Excellence Study USA 2016
Ecomm Excellence Study USA 2016Ecomm Excellence Study USA 2016
Ecomm Excellence Study USA 2016Vicki Chown
 
Global Shop 2010 Destination + Impulse
Global Shop 2010 Destination + ImpulseGlobal Shop 2010 Destination + Impulse
Global Shop 2010 Destination + Impulseprodmell
 
The New-Era Digital Store: Expectations, Insights and Consumer Individuality
The New-Era Digital Store: Expectations, Insights and Consumer IndividualityThe New-Era Digital Store: Expectations, Insights and Consumer Individuality
The New-Era Digital Store: Expectations, Insights and Consumer IndividualityMozu
 
DATA MINING IN RETAIL SECTOR
DATA MINING IN RETAIL SECTORDATA MINING IN RETAIL SECTOR
DATA MINING IN RETAIL SECTORRenuka Chand
 
Learn the Role of Big Data in Retail Industry
Learn the Role of Big Data in Retail IndustryLearn the Role of Big Data in Retail Industry
Learn the Role of Big Data in Retail IndustryeTailing India
 
Learn the Role of Big Data in Retail Industry
Learn the Role of Big Data in Retail IndustryLearn the Role of Big Data in Retail Industry
Learn the Role of Big Data in Retail IndustryAshish Jhalani
 
AGC-Changing-Consumer-Shopping-Experience-Jan-2015
AGC-Changing-Consumer-Shopping-Experience-Jan-2015AGC-Changing-Consumer-Shopping-Experience-Jan-2015
AGC-Changing-Consumer-Shopping-Experience-Jan-2015Linda Gridley
 
Marketing analytics Topics
Marketing analytics TopicsMarketing analytics Topics
Marketing analytics TopicsParshuram Yadav
 
Junivo Solutions - Smart Touchpoint Platform
Junivo Solutions - Smart Touchpoint PlatformJunivo Solutions - Smart Touchpoint Platform
Junivo Solutions - Smart Touchpoint PlatformMurat Eren
 
marketing analytics 1.pptx
marketing analytics 1.pptxmarketing analytics 1.pptx
marketing analytics 1.pptxnagarajan740445
 
Optilox Presentation
Optilox PresentationOptilox Presentation
Optilox PresentationNitish Singh
 
Retail Analytics Helps You Grow Your Sales (Everything You Should Know)
Retail Analytics Helps You Grow Your Sales (Everything You Should Know)Retail Analytics Helps You Grow Your Sales (Everything You Should Know)
Retail Analytics Helps You Grow Your Sales (Everything You Should Know)Kavika Roy
 
DemandTec Whitepaper: Consumer Centric Merchandising
DemandTec Whitepaper: Consumer Centric MerchandisingDemandTec Whitepaper: Consumer Centric Merchandising
DemandTec Whitepaper: Consumer Centric MerchandisingIBM DemandTec
 
Merchandise Management PowerPoint Presentation Slides
Merchandise Management PowerPoint Presentation SlidesMerchandise Management PowerPoint Presentation Slides
Merchandise Management PowerPoint Presentation SlidesSlideTeam
 
E-retail Management PowerPoint Presentation Slides
E-retail Management PowerPoint Presentation SlidesE-retail Management PowerPoint Presentation Slides
E-retail Management PowerPoint Presentation SlidesSlideTeam
 
Business Plan ICADDY et retail Analytics
Business Plan ICADDY et retail AnalyticsBusiness Plan ICADDY et retail Analytics
Business Plan ICADDY et retail AnalyticsMikaël Monjour
 
SAP WHITEPAPER: Reacting in the Retail Moment, Analyzing Big Data in Real Tim...
SAP WHITEPAPER: Reacting in the Retail Moment, Analyzing Big Data in Real Tim...SAP WHITEPAPER: Reacting in the Retail Moment, Analyzing Big Data in Real Tim...
SAP WHITEPAPER: Reacting in the Retail Moment, Analyzing Big Data in Real Tim...Beyond Technologies
 

Semelhante a breakthroughinpredictiveanalyticsforretailers-150728062328-lva1-app6891 (20)

Explicato Company Overview
Explicato Company OverviewExplicato Company Overview
Explicato Company Overview
 
Product Behavior Analytics - RetailReco
Product Behavior Analytics - RetailRecoProduct Behavior Analytics - RetailReco
Product Behavior Analytics - RetailReco
 
Ecomm Excellence Study USA 2016
Ecomm Excellence Study USA 2016Ecomm Excellence Study USA 2016
Ecomm Excellence Study USA 2016
 
Global Shop 2010 Destination + Impulse
Global Shop 2010 Destination + ImpulseGlobal Shop 2010 Destination + Impulse
Global Shop 2010 Destination + Impulse
 
The New-Era Digital Store: Expectations, Insights and Consumer Individuality
The New-Era Digital Store: Expectations, Insights and Consumer IndividualityThe New-Era Digital Store: Expectations, Insights and Consumer Individuality
The New-Era Digital Store: Expectations, Insights and Consumer Individuality
 
The Missing Link
The Missing LinkThe Missing Link
The Missing Link
 
DATA MINING IN RETAIL SECTOR
DATA MINING IN RETAIL SECTORDATA MINING IN RETAIL SECTOR
DATA MINING IN RETAIL SECTOR
 
Learn the Role of Big Data in Retail Industry
Learn the Role of Big Data in Retail IndustryLearn the Role of Big Data in Retail Industry
Learn the Role of Big Data in Retail Industry
 
Learn the Role of Big Data in Retail Industry
Learn the Role of Big Data in Retail IndustryLearn the Role of Big Data in Retail Industry
Learn the Role of Big Data in Retail Industry
 
AGC-Changing-Consumer-Shopping-Experience-Jan-2015
AGC-Changing-Consumer-Shopping-Experience-Jan-2015AGC-Changing-Consumer-Shopping-Experience-Jan-2015
AGC-Changing-Consumer-Shopping-Experience-Jan-2015
 
Marketing analytics Topics
Marketing analytics TopicsMarketing analytics Topics
Marketing analytics Topics
 
Junivo Solutions - Smart Touchpoint Platform
Junivo Solutions - Smart Touchpoint PlatformJunivo Solutions - Smart Touchpoint Platform
Junivo Solutions - Smart Touchpoint Platform
 
marketing analytics 1.pptx
marketing analytics 1.pptxmarketing analytics 1.pptx
marketing analytics 1.pptx
 
Optilox Presentation
Optilox PresentationOptilox Presentation
Optilox Presentation
 
Retail Analytics Helps You Grow Your Sales (Everything You Should Know)
Retail Analytics Helps You Grow Your Sales (Everything You Should Know)Retail Analytics Helps You Grow Your Sales (Everything You Should Know)
Retail Analytics Helps You Grow Your Sales (Everything You Should Know)
 
DemandTec Whitepaper: Consumer Centric Merchandising
DemandTec Whitepaper: Consumer Centric MerchandisingDemandTec Whitepaper: Consumer Centric Merchandising
DemandTec Whitepaper: Consumer Centric Merchandising
 
Merchandise Management PowerPoint Presentation Slides
Merchandise Management PowerPoint Presentation SlidesMerchandise Management PowerPoint Presentation Slides
Merchandise Management PowerPoint Presentation Slides
 
E-retail Management PowerPoint Presentation Slides
E-retail Management PowerPoint Presentation SlidesE-retail Management PowerPoint Presentation Slides
E-retail Management PowerPoint Presentation Slides
 
Business Plan ICADDY et retail Analytics
Business Plan ICADDY et retail AnalyticsBusiness Plan ICADDY et retail Analytics
Business Plan ICADDY et retail Analytics
 
SAP WHITEPAPER: Reacting in the Retail Moment, Analyzing Big Data in Real Tim...
SAP WHITEPAPER: Reacting in the Retail Moment, Analyzing Big Data in Real Tim...SAP WHITEPAPER: Reacting in the Retail Moment, Analyzing Big Data in Real Tim...
SAP WHITEPAPER: Reacting in the Retail Moment, Analyzing Big Data in Real Tim...
 

breakthroughinpredictiveanalyticsforretailers-150728062328-lva1-app6891

  • 1. Copyright 2014-15 Retail Automata Analytics www.retailreco.com 1 Accurate Recommendations For Retailers of all sizes and domains A Predictive Analytics Breakthrough (This presentation contains brief disclosure of a patent pending technology) www.retailreco.com
  • 2. Copyright 2014-15 Retail Automata Analytics www.retailreco.com
  • 3. Copyright 2014-15 Retail Automata Analytics www.retailreco.com WHAT WORKS FOR TOP 1% DOES NOT WORK FOR 99% Challenges of Predictive Analytics for such drastically different data sets are different. 1% 99% .
  • 4. Copyright 2014-15 Retail Automata Analytics www.retailreco.com GENERATING PREDICTIONS FOR 99% RETAILERS IS TOUGH Process of generating future buys of customer involves analysis of past purchase histories of customers and items. To derive meaningful analytical insights repeat sales history of same item is required. While huge repeat sale history of any single item is present for top 1% like Amazon. For most of the retailers this is an uncommon luxury. The problem of Predictive Analytics is much more difficult for most of the retailers than for the top 1% of retailers. At the same time bandwidth and $resources necessary for research into Predictive analytics is also not available for SME retailers.
  • 5. Copyright 2014-15 Retail Automata Analytics www.retailreco.com COLD START PROBLEM For a new item or a new customer there exists no previous data. Hence no predicted buyers of the item or item to item recommendations can be made on day one.
  • 6. Copyright 2014-15 Retail Automata Analytics www.retailreco.com FREQUENTLY CHANGING CATALOG PROBLEM By the time enough sales history of an item is recorded. That item is no longer in the inventory. An out of stock item can not be recommended to customers. Nor can it become part of other items "people who bought this also bought these" recommendations. One of kind sellers like jewelers where every item is unique can be an extreme case of frequently changing catalog problem.
  • 7. Copyright 2014-15 Retail Automata Analytics www.retailreco.com 7 THE RETAILRECO SOLUTION TO RECOMMENDATION PROBLEM As noted down the most fundamental problem of 99% retailers is the lack of sufficient sales history. Products come and go, For every customer characteristic Unique Blue Print of Relevancy Remains the same.
  • 8. Copyright 2014-15 Retail Automata Analytics www.retailreco.com 8 THE ABILITY TO DERIVE MEANINGFUL INSIGHT STARTS WITH DEFINING THE RIGHT ABSTRACTIONS AND MODEL FOR ANALYSIS WE STARTED WITH IDENTIFICATION OF ENTITIES WHICH MATTER THE MOST FOR A RETAIL BUSINESS We form The blueprint or retail DNA of every customer on the basis of most fundamental buy decision making entities of retail.
  • 9. Copyright 2014-15 Retail Automata Analytics www.retailreco.com 9 FIVE FUNDAMENTAL BUY DECISION MAKING ENTITIES OF RETAIL ECOLOGY Decision Making Feature Sets A retail business is characterized by one or more types of products with different features. Exact values of different features combined together is the primary buy decision making factor for customer. Unlike the content based recommender system where every feature value like “color” is treated as independent decision factor. In our model the exact values of all features that has occurred in all historical sources of customer preference data forms the character of retail business. Not many like the “Navy Blue” shirt, while even fewer people have the preference for “White” jeans.
  • 10. Copyright 2014-15 Retail Automata Analytics www.retailreco.com 10 SECOND ENTITY: AFFORDABILITY OR PRICE RANGES Price of an item is a critical buy decision making factor Affordability of the same customer can be different for different types of products. A person who likes to buy most expensive Diamond Solitaire ring may be willing to buy quartz watches only in the lower price ranges. For predictive analytics purposes a classification of buy within just a single defined price range is also not sufficient. Just above or below the defined price range the person is still has interest in that specific product type having same decision making feature set value. Affordability Price Ranges for any specific feature set values is given a very special consideration in our approach of prediction generation.
  • 11. Copyright 2014-15 Retail Automata Analytics www.retailreco.com 11 THIRD ENTITY: FRUGALITY OR DISCOUNT SENSITIVITY Some customers’ have a tendency to be more sensitive to the amount of discount in making the buy decision compared to others. This tendency is not only restricted to the customer dimension but can be generalized to include the product dimension also i.e. some products have the higher likelihood of being bought with deep discounts while others are not so sensitive to discounting. A discounted sale record should have lesser impact on process of generating predictions, compared to a sale record at full price. Furthermore for marketing purposes customer segmentation on the basis of Frugality consideration can be very effective for different business objectives like clearance sale or premium product launch.
  • 12. Copyright 2014-15 Retail Automata Analytics www.retailreco.com 12 CUSTOMER EVOLUTION AND SEASONALITY Buying behaviour of customer changes over period of time. This is intelligently captured in our system. Seasonal purchasing of different products is different. We note it down so that retailer can utilize this information.
  • 13. Copyright 2014-15 Retail Automata Analytics www.retailreco.com 13 UNIFIED PREDICTIVE RETAIL ECO-SYSTEM + Exact values present in all historical data sources, of all different feature sets and corresponding affordability price ranges forms the structure of data used for predictive analytics. DATA ADAPTERS Unify the customer preference data from all historical sources including offline and online store sales history, shopping cart, browsing history, social media etc. Each data source can have different importance or weight. + Affect the strength of sales record contribution to predictive analytics data structure.
  • 14. Copyright 2014-15 Retail Automata Analytics www.retailreco.com 14 INTELLIGENT CORE All the disclosure of the invention presented in this presentation are covered under patent application “Unified Predictive Retail Eco-System” : (number: 2465/MUM/2015). RESULT: MOST ACCURATE PREDICTIONS OF FUTURE BUYS FOR RETAILERS OF ALL SIZE AND DOMAINS Along with the Seasonality of Products and Frugality of customers (as well as products) noted down. Which are powerful customer segmentation criteria for RetailReco campaigning system. A Personalized Omni-Channel world of only relevant products is automatically created for every customer. Applies Big Data technologies to handle scalability. Sparsity in Unified abstracted predictive analytics data structure is handled by Dimensionality reduction techniques. Effect of frequent purchases of a small set of products or customers buying all products is handled by normalization techniques.