2. People watch one billion hours of YouTube every
day
YouTube’s recommendations drive 70% of what we watch
=
700.000.000 hours of video / day
YouTube generates 6% of Google’s ad sales revenue.
3. Digital Marketing and Recommender Systems
Individualized
customer
experience
Higher
Traffic &
Increased
revenue
Product
Bundling
Engaging
Shoppers
Real-Time
Recommendations
AI-based
Recommender
Systems
Machine Learning Models for
predicting product preference.
Recommender Systems help us to
manage big amounts of customer
data, and to extract preferences on
the individual customers‘ level.
7. Word Embeddings
Feature Vector representations of words
(i.e. representing text as numbers)
Capture semantic and syntactic
relationships.
8. Word Embeddings
Feature Vector representations of words
(i.e. representing text as numbers)
Capture semantic and syntactic
relationships.
0.1 0.67 - --
0.5 0.8 - --
0.01 0.9 - --
king
man
woma
n
queen 0.6 0.19 - --
Word embedding
(e.g. word2vec, GloVe)
Similarity( 0.1 0.67 - -- 0.5 0.8 - --
)=0.8
king man
,
9. Word2vec and Skipgram for Learning Word
Embeddings
0.8 0.01 … 0.89Marketing
Sale
School
art
…
…
….
advertising
Embedding Size
Embeddings
“You shall know a word by the company it keeps” J.R. Firth
Random Initialization1
10. Word2vec and Skipgram for Learning Word
Embeddings
Untrained Model
Task:
Are the two words neighbors?
0.8 0.01 … 0.89Marketing
Sale
School
art
…
…
….
advertising
Embedding Size
Embeddings
“You shall know a word by the company it keeps” J.R. Firth
Random Initialization1 Look up
embeddings2
Marketing
school
Train the model3 Model
Prediction
4
0.45
0.55
Yes
No
11. Word2vec and Skipgram for Learning Word
Embeddings
Untrained Model
Task:
Are the two words neighbors?
0.8 0.01 … 0.89Marketing
Sale
School
art
…
…
….
advertising
Embedding Size
Embeddings
“You shall know a word by the company it keeps” J.R. Firth
Random Initialization1 Look up
embeddings2
Marketing
school
Train the model3 Model
Prediction
4
0.45
0.55
Yes
No
Actual Target &
Error Estimation
5
0
1
Yes
No
Update Model Parameters
12. Word2vec and Skipgram for Learning Word
Embeddings
Marketing is the study and management of exchange relationships.
Source: Wikipedia
Sliding window across running text
context
Input word Output word Target
is marketing 1
is the 1
Dataset
13. Word2vec and Skipgram for Learning Word
Embeddings
Marketing is the study and management of exchange relationships.
Source: Wikipedia
Sliding window across running text
context
Input word Output word Target
is marketing 1
is the 1
the is 1
the study 1
Dataset
14. Word2vec and Skipgram for Learning Word
Embeddings
Dataset
Marketing is the study and management of exchange relationships.
Source: Wikipedia
Input word Output word Target
is marketing 1
is school 0
is the 1
is art 0
the is 1
the cat 0
the study 1
Negative Sampling
17. Researchers from the Web Search, E-
commerce and Marketplace domains
have realized that just like one can
train word embeddings by treating a
sequence of words in a sentence as
context, the same can be done for
training embeddings of user
actions by treating sequence of
user actions as context.
Applying word2vec to Recommenders and Advertising
Mihajlo Grbovic, Airbnb
User activity around an item encodes many
abstract qualities of that item which are difficult to
capture by more direct means (e.g. How do you encode
qualities like “architecture, style and feel” of an Airbnb
listing?
The word2vec approach has proven successful in
extracting these hidden insights.
Being able to compare, search, and categorize items
on these abstract dimensions opens up a lot of
opportunities for smarter, better recommendations.
19. Airbnb Recommender Systems
Airbnb is a marketplace that contains millions of diverse home listings
Potential guests explore the listings through search results generated from a sophisticated Machine Learning models.
Similar Listing Carousel shows listing recommendations related to the current viewed listing.
Initially, search rankings were determined by a set of hard-coded rules based on very
basic signals
The rules were applied to every guest uniformly, rather than taking into account the unique values that could create the kind of
a personalized experience that keeps guests coming back.
Airbnb uses machine learning to offer personalized search experience.
20. Listing
Embeddings in
Search Ranking
Airbnb Recommender Systems
The listing embeddings are vector representations of Airbnb homes learned
from search sessions.
They effectively encode many listing features, such as location, price, listing
type, architecture and listing style, all using only 32 float numbers.
Measure similarities: Similar listings lie nearby in the embedding space.
Improving Similar Listing Recommendations and Real-Time Personalization
in Search Ranking.
36. ML systems are not good at
generalizing when the underlying
data distribution changes.
What is needed to
build a ML product
What’s needed to
build a supervised
learning model
Robustness in AI
37. Covid-19 Pandemic… Sudden change in
Consumers' behavior
New behaviors derail
old recommender
engines,
AI inventory trackers,
and fraud detection
systems
38. Building Robust Recommender Systems
The AI community needs to implement new
approaches and processes for post-deployment
monitoring like:
building an alert system to flag changes,
use human-in-the-loop deployments to
acquire new labels,
assemble a robust MLOps team.
Valuable product
resilient to conditions
change
40. How to build recommender systems without
compromising data privacy?
Building the
foundation for a
responsible
and innovative
Data
Economy
Secure computation (e.g. cryptography).
Secure hardware usage.
Transparency and Audit.
ML Models that can learn from small datasets