The document introduces FeatureByte, a platform for creating machine learning features. It allows users to quickly create features, experiment with different features, and deploy features without needing to manage pipelines. The document provides an overview of FeatureByte's architecture and how it leverages existing data warehouses. It then demonstrates how to use FeatureByte to transform nine feature ideas for a grocery dataset into actual machine learning inputs, including summarizing the process for each feature idea. Finally, it shows how to obtain training data and deploy the new features via a REST API.

1. Transforming Feature Ideas
into Machine Learning Inputs
Xavier Conort
9th May 2023 - Singapore

2. Transforming Feature Ideas into actionable ML inputs
2
FeatureByte is a free and source-available platform designed to
empower data enthusiasts who love creating innovative features and
improving model accuracy through data.
With FeatureByte, you can:
● Quickly create features,
● Seamlessly experiment with features and
● Effortlessly deploy features
All without the headache of creating and managing new pipelines.

3. Free and source available platform released on May 8!
3
You can access our repository at https://github.com/featurebyte/featurebyte and our documentation at
https://docs.featurebyte.com/0.2/. Please check it out and give us your feedback! We're eager to hear your thoughts and
improve FeatureByte to better suit your needs.

4. Agenda
4
● Quick introduction to FeatureByte Architecture
● Introduction to the Grocery dataset
● Transform 9 Features Ideas
● Get training data and deploy our new features in production!

5. FeatureByte
Architecture

6. 6
Your DataBricks, Snowflake or Spark data warehouse is used as:
● data source
● compute engine
● feature store
The FeatureByte Service, which runs on Docker, acts
as the interface between the SDK and your data
warehouse.
It automatically manages tasks like validating
requests, scheduling and executing tasks, and storing
metadata.
This Python module transpiles the feature logical plan
to platform-specific SQL
Light-weight installation that leverages your Data Warehouse
You interact with the tool through the SDK, which
provides an intuitive framework for creating, sharing,
experimenting, deploying, and managing features.

7. Grocery dataset
Note: To access the Grocery dataset or play with FeatureByte's tutorials - you can install a pre-built local Spark data warehouse with pre-populated data, via
the command featurebyte.playground().

8. 8
We will work with a Catalog where 4 tables were registered from a grocery dataset.
Dimension table with
static description on
products
Item table with details on
purchased products in
customer invoices
Event table where each
row indicates an invoice
Slowly Changing Dimension table that contains data
on customers that change over time.
A catalog is an object that help organize your
feature engineering assets by domain

9. Simple observation set to preview features
9
Observation sets are used to materialize historical
feature values. They combine entity values and
historical points-in-time that you want to learn from.
We will work here with a small Pandas DataFrame to
preview features when customers are doing a purchase.
The observation set is retrieved from a sample of the
GROCERYINVOICE table’s view.
The column containing points-in-time must be named
‘POINT-IN-TIME’
The column containing entity values must be named
with an accepted serving name as defined during the
entity registration.
View objects are used to prepare data. Work like SQL
views but with a syntax similar to Pandas!

10. 9 Feature ideas for the
Grocery dataset

11. 9 feature ideas for the Customer entity
1. Frequency: the count of invoices by Customer in the past 12 weeks
2. Monetary: the amount spent by Customer in the past 12 weeks
3. Recency: the time since the Customer’s last invoice
4. Basket: the sum spent by Customer per Product Group in the past 12 weeks
5. Diversity: the entropy of the Customer’s basket per Product Group in the past 12 weeks
6. Stability: the cosine similarity of the Customer’s basket in the past 2 weeks compared to their
basket in the past 12 weeks
7. Similarity: the cosine similarity of the Customer’s basket compared to the baskets of Customers
living in the same state in the past 12 weeks
8. Regularity: the entropy of weekdays of the customer invoices in the past 12 weeks
9. Change: whether the Customer’s Address changed in the past 12 weeks
11

12. Feature Idea 1: Frequency
Count of invoices by Customer in the past 12 weeks
12
The groupby() method enables to group a view by
columns representing entities.
The aggregate_over() method enables aggregation
operation over a window prior to the observation point,
here 12 weeks.
Feature objects contain the logical plan to compute a feature

13. Feature Idea 2: Monetary
Amount spent by Customer in the past 12 weeks
13
Aggregation operations include latest, count, sum,
average, minimum, maximum, and standard deviation.

14. Feature Idea 3: Recency
Time since Customer last invoice
14
RequestColumn.point_in_time() enables the creation of
features that compare the value of an other feature with
the observation point
Another example of using this method would be to
derive a customer's age from their birth date and the
observation point.

15. Feature Idea 4: Basket
Sum spent by Customer per Product Group in the past 2 and 12 weeks
15
Aggregation can be done across a categorical column,
here ProductGroup.
When the feature is materialized, a dictionary is
returned.
In our example, the keys represent the ProductGroup,
and their corresponding values represent the total
amount spent on each Product Group.

16. Feature Idea 5: Diversity
Entropy of the Customer’s basket in the past 12 weeks
16
A dictionary feature can be transformed into another
feature. We apply here the entropy.

17. Feature Idea 6: Stability
Cosine Similarity of the Customer’s basket in the past 2 weeks vs their
basket in the past 12 weeks
17
2 dictionary features with different
windows can be compared using the cosine
similarity.

18. Feature Idea 7: Similarity
Cosine Similarity of the Customer’s basket in the past 12 weeks
vs the baskets of Customers living in the same state
18
When 2 dictionary features are grouped with 2 different
entities,
● they can be still compared using the cosine similarity.
● the entity of the resulting feature is determined based
on the relationship between the 2 entities.
In our example, the primary entity of
“Customer_Similarity_with_State_12w” is
grocerycustomer because grocerycustomer
is a child of the frenchstate entity.
The feature can be served by providing only
the grocerycustomer entity values. Values
for frenchstate entity are derived
automatically by FeatureByte.

19. Feature Idea 8: Regularity
Entropy of weekdays of the Customer’s invoices in the past 12 weeks
19
In this example, the keys of the dictionary will represent
the weekday, and their corresponding values will
represent the total amount spent on each weekday.
The weekdays dictionary feature is here transformed
into another feature by applying the entropy.

20. Feature Idea 9: Change
Whether Customer’s Address Changed in the past 12 weeks
20
Change View can be created from a Slowly Changing Dimension
(SCD) table to analyze changes that occur in an attribute, here the
StreetAddress of the grocerycustomer.

21. Get training data and
deploy our 9 features in
production!

22. Audit one feature via its Definition file
22
The feature definition file is critical for maintaining the integrity
of a feature. It serves as the single source of truth for the feature,
providing an explicit outline of the intended operations of the
feature declaration, including inherited operations.
The file is automatically generated when a feature is declared or a
new version is derived. It is used to generate the final logical
execution graph, which is then transpiled into platform-specific
SQL for feature materialization.

23. Create feature list
23

24. Compute training data
24
You can choose to store your training data in the feature store for
reuse or audit.
If you connect FeatureByte to your data warehouse, the
computation of features is performed in the data warehouse,
taking advantage of its scalability, stability, and efficiency.
In this case, you can work with much larger observation tables with
millions of rows.

25. Deploy and get shell template for REST API
25

26. Thank You!
To get started, check out
Repo: https://github.com/featurebyte/featurebyte
Documentation: https://docs.featurebyte.com/0.2/

27. 27
Catalog objects help organize
assets by domain
View objects are used to prepare data. Work like SQL
views but with a syntax similar to Pandas!
Table objects centralize essential
metadata for feature engineering.
4 types: event table, item table,
SCD table and dimension table.
Entity objects and relationships facilitate
feature organization and serving Feature objects contain the logical plan to compute a feature
Python SDK to register, share and manage tables, features and
more…