Customer Case Study is the premier online destination for furniture and home décor, using technology to help savvy shoppers find the best prices on top styles to create their dream homes.

Vertical Use Case

Identifying unique patterns and tendencies that indicate a user is ready to purchase

Technical Use Case

• Data Ingest and ETL
• Machine Learning

The Challenges

  • Many new website visitors (billions of unique pay views/year), but very low conversion.
  • ETL took an enormous amount of resources which were already scarce and stretched to their limits.
  • Data science teams were just spending too much time on DevOps and not iterating on models.
  • Team has experience in different programming languages which made it difficult to share data and collaborate on insights.

The Solution

Databricks has greatly simplified the ETL process while increasing performance and scalability. They have significantly closed the gap from development to production. And model training in Databricks is also more efficient as teams can work in the same notebooks with different languages and quickly train models.

  • Decreased cost of moving models to production by nearly 50%
  • Able to stand up new models 5x faster than the time previously required.
  • Can make inter-day improvements on existing models without new deploys
  • Able to quickly spin up/down clusters through self-service, cluster management, resulting in actionable insights when our business partners need them.
  • In-notebook version control allows to roll-back single moves inside a notebook — making exploration and general trial/error approach to exploratory analysis seamless.

Working in Databricks is like getting a seat in first class. It’s just the way flying (or data science-ing) should be.

Mary Clair Thompson Data Scientist,