For e-commerce marketers, selecting and presenting the right products based on a user's mindset and stage of the purchase funnel is key to optimizing conversions. But with thousands of products to choose from, how does a retailer select just a few personalized recommendations for each visitor?
We've learned a thing or two from powering tens of millions of recommendations on behalf of our clients and we're thrilled to share this understanding with you in the presentation below. We're confident you'll gain a better understanding of recommendations. And if you'd like to implement these strategies on your site, please contact us for a live demo.
3. AVERAGE
ORDER VALUE
Encourage the user to
explore products“I’m just browsing around”
CLICK
THROUGH
RATE
Optimize conversions by selecting and presenting the most relevant
products based on user’s mindset and stage of purchase funnel.
BROWSING SITE
PRODUCT VIEW
ADD TO CART
PURCHASE
REPURCHASE
THE VALUE OF RECOMMENDATIONS
Do not distract yet
increase cart value
CONVERSION
RATE
“I’m looking for something specific”
“I want to buy now”
Surface related products &
drive the user to convert
7. Filter Products
Rule-based selection of
the set of eligible products
Reorder the eligible
products by strategy score
Score Products
Based on your
recommendation strategy
THE 3-STEP MACHINE
Sort & Present
10. MOST POPULAR PRODUCTS
Global
Now6 Months Ago
Purchase
Recent
Add to cart
Product view
● Weighted sum of all product
interactions by all users
● Favors recent interactions
11. SIMILAR PRODUCTS
Contextual (by products)
Categories:
Men's Tops Short Sleeve
Shirts
Keywords:
Stay Ready Stay Cool Loose
Charged Cotton HeatGear
New Arrivals Microthread
● Keywords and categories value
comparison between the
product in context and all other
products in feed
● Factors in product popularity
12. BOUGHT TOGETHER
Contextual (by products)
● Occurrences of product(s) in
context purchased in the same
transaction with other products
● Demotes products bought
together with many items
13. AFFINITY BASED
Personalized (by user)
● Derive user preference from
interactions with products (real
time + previous sessions)
● Reorder the most popular
items by user preference of
product attributes
14. COLLABORATIVE FILTERING
Personalized (by user)
● Identify the products a user is
most likely to purchase
● Based on what similar users
have purchased
USER 1
USER 2
USER 3
USER 4
ITEM 1 ITEM 2 ITEM 3
16. • Dynamic Filters Using ‘Product Dimensions’
• Targeted Merchandising Rules
FILTER PRODUCTS BY PRODUCT ATTRIBUTES
17. ● Match the viewed product in selected attributes (PDP)
● Differ from the viewed product in selected attributes (PDP)
● Category: Current / Parent / Any (PDP or Category)
INSERT DYNAMIC FILTERS USING PRODUCT DIMENSIONS
18. ● Only Include (whitelist)
● Exclude (blacklist)
● Pin Product to Slot
DEPLOY TARGETED MERCHANDISING RULES
21. PRODUCT
PAGES
HIGH INTENT SIGNALS LOW / NO INTENT SIGNALS
Similar + Bought Together Similar
Viewed Together
Filters: Match theme and category of product displayed
24. TEST & TARGET DIFFERENT LAYOUTS & STRATEGIES
50%
50%
Users Condition
Yes
No
MOST
POPULAR
SIMILAR
PRODUCTS
MOST
POPULAR COLLABORATIVE
FILTERING
25. FUSE MULTIPLE
RECOMMENDATION
STRATEGIES
“I’m just browsing around”
“I’m looking for something
specific”
“I want to buy now”
Encourage the user to
explore products
MOST
POPULAR
TRENDING
NOW
NEWEST
SIMILAR
PRODUCTS
BOUGHT
TOGETHER
VIEWED
TOGETHER
VIEWED AND
THEN BOUGHT
AFFINITY
BASED
COLLABORATIVE
FILTERING
GlobalContextualPersonalized
Do not distract yet
increase cart value
Surface related products &
drive the user to convert