SPARK + AI SUMMIT 2020
Retail and CPG sessions

We are delighted to bring you the best Retail and CPG sessions from Spark + AI Summit 2020, the virtual event for data teams. Watch the selected sessions and relive the Retail and CPG forums below.

Catch up on some of the outstanding keynotes featuring luminaries like Matei Zaharia, Adam Pazske, Reynold Xin, and more.

To explore all Spark + AI Summit session recordings, click here.

Operationalizing Machine Learning at Scale at Starbucks

Speakers:
Balaji Venkataraman, Engineering Manager, Starbucks
Denny Lee, Sr. Director of Engineering, Capital One

This talk is the journey of a team in using the Starbucks AI foundational capabilities in EDAP to deploy, manage and operate ML models as secure and scalable cognitive services that have the potential of powering internet-scale inferences for use cases and applications.

Building a Real-Time Feature Store at iFood

Speakers:
Balaji Venkataraman, Engineering Manager, Starbucks
Daniel Galinkin, Technical Leader, ML Platform Team, iFood

In this talk, we will present how iFood built a real-time feature store, using Databricks and Spark Structured Streaming in order to process events streams, store them to a historical Delta Lake Table storage and a Redis low-latency access cluster, and how we structured our development processes in order to do it with production-grade, reliable and validated code.

Building Identity Graphs over Heterogeneous Data

Speakers:
Sudha Viswanathan, Senior Software Engineer, Walmart Labs
Saigopal Thota, Principal Data Scientist, Walmart Labs

In this talk you will takeaway the feasibility of building a highly scalable Graph framework using Spark and The idea of building and leveraging Graph in real-time to achieve freshness.

Columbia Migrates from Legacy Data Warehouse to an Open Data Platform with Delta Lake

Speakers:
Bilal Obeidat, Solution Architect, Databricks
Lara Minor, Senior Enterprise Data Manager, Columbia Sportswear

In this presentation, we’ll walk through how we achieved a 70% reduction in pipeline creation time and reduced ETL workload times from four hours with previous data warehouses to minutes using Azure Databricks, hence enabling near real-time analytics. We migrated from multiple legacy data warehouses, run by individual lines of business, to a single scalable, reliable, performant data lake on top of Azure and Delta Lake.

Retail and Consumer Packaged Goods Industry Forum

Speakers:
Ojas Nivsarkar | Brad Kent | Saritha Ivaturi | Rob Saker | Monzy Merza

In this forum, learn from industry leaders on how data and machine learning are driving innovation across the entire retail value chain.