recommender system in retail - sas
TRANSCRIPT
![Page 1: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/1.jpg)
© 2015 Shoppers Drug Mart. All rights reserved. Unauthorized duplication or distribution in whole or in part via any channel without written permission strictly prohibited.
RECOMMENDER SYSTEM IN RETAIL
![Page 2: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/2.jpg)
TRADITIONAL RETAIL APPROACH TO INCREASE CUSTOMER
ENGAGEMENT & LOYALTY
• Traditionally Non-
personalized channels and
mass offers have had the
strongest presence
• Success is difficult to measure
• Future of retail focuses on
customer needs
![Page 3: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/3.jpg)
SHIFT TO CUSTOMER CENTRICITY
High ResponseSignificantly Increase Response
Target CustomersBased on propensity
to purchase product
Relevant Sku
XYZ
Incremental
RevenueFocused on Customer
Centricity
PersonalizationPersonalize each unique product
based on relevance to Target
customers
![Page 4: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/4.jpg)
Who
Else?
![Page 5: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/5.jpg)
EVERYDAY APPLICATIONS OF PERSONALIZATION
RECOMMENDER SYSTEMS
![Page 6: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/6.jpg)
6
RECOMMENDER SYSTEMS
System to recommend items to users based on
examples of their preferences/purchases/ratings
![Page 7: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/7.jpg)
CURRENT STATE
STRATEGY
AT SDM?
![Page 8: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/8.jpg)
RECOMMENDER SYSTEM AT SDM
DIRECT MAIL DIGITAL
![Page 9: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/9.jpg)
CUSTOMER-CENTRIC APPROACH TO
PERSONALIZATION
Cross-Sell
Thank You
Up-Sell
Other
Acquisition Onboard Grow Maintain Decline
High
Low
Low
Medium
Low
Low
Medium
Predict attrition,
proactive
approach
Leverage “look-
alike” models
Need to
understand
potential value
Medium
Medium
Medium
New products,
brands,
preference centre
Low
High Medium Low
High
New channels,
vehicles (RBC,
etc…)
• Ultimate goal: Build personalization with 100% variability across all
levers (currency, product, etc…) and types of offers
• Leverage Customer segments & prediction to drive offer type pairing
Offer Type
![Page 10: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/10.jpg)
METHODOLOGY EXAMPLE - CATEGORY AFFINITY
Light
Bulbs
Cx
Access
Vitamins
LOW AFFINITY
Ladies
Frag
![Page 11: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/11.jpg)
DIRECT MAIL EXAMPLE
11
Increase Incremental Sales and Profitability by
focusing on customers purchasing more
products per basket
Cu
sto
me
r C
ou
nt
![Page 12: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/12.jpg)
CURRENT STATE
HOW WE
DO IT AT
SDM?
![Page 13: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/13.jpg)
TWO APPROACHES TO RECOMMENDER SYSTEMS:
Content Based
• Focuses on properties of items
• Similarity of items is determined
by measuring the similarity in their
properties
• Example: Profiling of Internet
Movie Database (IMDB) - assigns a
genre to every movie
Collaborative-Filtering
• Focuses on the relationship
between users and items
• Similarity of items is determined
by the similarity of the ratings of
those items by the users who have
rated both items
• Example: Recommending
Products / Movies
Specialized Application General Application
![Page 14: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/14.jpg)
COLLABORATIVE FILTERING
Bayesian-network
models
Dimension
Reduction
Item-based
nearest neighbor
User-based
nearest neighbor
Non-
probabilistic
Algorithms
Collaborative
Filtering
Probabilistic
Algorithms
![Page 15: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/15.jpg)
Correlation
Match
15
A 9
B 3
C
: :
Z 5
A
B
C 9
: :
Z 10
A 5
B 3
C
: :
Z 7
A
B
C 8
: :
Z
A 6
B 4
C
: :
Z
A 10
B 4
C 8
. .
Z 1
A 9
B 3
C
. .
Z 5
A 9
B 3
C
: :
Z 5
A 10
B 4
C 8
. .
Z 1
C
COLLABORATIVE FILTERING
Transactions /
Ratings
Active
User
Extract
Recommendations
A 5
B 3
C
. .
Z 7
![Page 16: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/16.jpg)
Cosine Similaritymeasures similarity between two
vectors of an inner product
space that measures
the cosine of the angle between
them
Jaccard Similaritymeasures similarity between finite
sample sets, and is defined as the
size of the intersection divided by
the size of the union of the
sample set
The Pearson
correlation The Pearson correlation similarity of
two users x, y
METHODOLOGY - MEASURING SIMILARITIES
![Page 17: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/17.jpg)
Ben Jade Torri
MEASURING SIMILARITIES …. CONTD
Example :
Users Product 1 Product 2 Product 3 Product 4 Product 5 Product 6
Average -
User
Tom 3 5 4 1 3.25
Matt 3 4 4 1 3
Ben 4 3 3 1 2.75
Jade 4 4 4 3 1 3.2
Torri 5 4 5 3 4.25
Average-
Prod 4.3 3.4 4.5 3.5 1.4
Similarity
between
Product 1 & 2
![Page 18: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/18.jpg)
BAYESIAN METHOD
We are looking for products or product groups that fall in the area that is
‘Above Average Odds’. This means that the product or product group is most
likely associated with ‘Incremental basket’
18
![Page 19: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/19.jpg)
RECOMMENDER APPROACHES
![Page 20: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/20.jpg)
MEASUREMENT
![Page 21: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/21.jpg)
TEST & LEARN
• Evaluation of Predicted Ratings
(Mean Average Error, RMSE)
• Evaluation of top-N reccos
• MAE
• Accuracy
• Precision and Recall (F1 Score)
• ROC Curves
• Test vs Control
MEASUREEffectiveness of
Recommendations
• Incorporate New Methodologies
into current Recommender
Systems
• Enhance contribution of
LifeTime Value Models
• Bundling of Product
• Feed Results to
SDM portal:
Next Steps
![Page 22: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/22.jpg)
CHALLENGES
![Page 23: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/23.jpg)
CHALLENGES
Problems with Collaborative Filtering method:
Cold Start: There needs to be enough users already in the system to find a match
Sparsity: If there are many items to be recommended, even if there are many users, the user/ratings matrix is sparse, and it is hard to find users that have rated the same items
First Rater: Cannot recommend an item that has not been previously rated New items Esoteric items
Popularity Bias: Cannot recommend items to someone with unique tastes Tends to recommend popular items
![Page 24: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/24.jpg)
CHALLENGES
Problems with Content-based method:
Requires content that can be encoded as
meaningful features
Users’ tastes must be represented as a learnable
function of these content features
Unable to exploit quality judgments of other users Unless these are somehow included in the content
features
![Page 25: RECOMMENDER SYSTEM IN RETAIL - SAS](https://reader034.vdocuments.us/reader034/viewer/2022042702/62657dcb3ccedb5f50192615/html5/thumbnails/25.jpg)
MAIN CHALLENGES
SERVERS!
Sparsity of DataSize of Data
(Data Computation)
SERVERS!SERVERS!