Title
Second Dinner optimizes in-game experiences with personalization on Databricks
Second Dinner optimizes in-game experiences with personalization | Databricks Skip to main content Login Why Databricks Discover For App Develop…
← Back to Second Dinner optimizes in-game experiences with personalization on Databricks
Source proof for Second Dinner optimizes in-game experiences with personalization on Databricks
Source-bound proof
Verified source excerpts for every supported field
Each colour maps a published value to the exact source passage used to support it. Only bounded excerpts are public; administrators can inspect the complete captured source.
11 fields supported
derived · high
Description
Marvel Snap developer Second Dinner built real-time, one-to-one shop personalization models using Databricks MLflow and Delta Lake, cutting feature launches from 10 per year to more than 50 (a 400% increase) and reducing model development and training time from months to weeks.
…ond Dinner CUSTOMER STORY Reaching new levels of in-game engagement during play 400% faster feature launches, from 10 per year to more than 50 Months to weeks faster model development and training Second Dinner, the studio…
Company
Second Dinner
…per year to more than 50 Months to weeks faster model development and training Second Dinner, the studio behind Marvel Snap, a competitive, fast-paced card battle game based on the popular Marvel Universe, relies on a small team and collaboration for rapid feature iterations. Second…
Industry
Media & Entertainment
…earn more about Databricks Data + AI Platform for Games Share this post Details Industry : Marketing , Media & Entertainment Use Case : Data Science Cloud : AWS Product : Delta Lake Ready to get started?…
Problem
Second Dinner relied on manual, heuristic-driven processes to collect player data and generate dashboards; a single feature iteration could take a month, limiting the team to 10 personalization use cases yearly, and personalization lagged behind player interest since it was based on aggregate statistics rather than true personalization.
…lizations and continuously push code created numerous opportunities for errors. A single feature iteration could take a month, limiting us to 10 use cases yearly. Personalization lagged behind player interest, so they were no longer desired b…
Solution
Second Dinner built an ML model in Databricks using MLflow, ingesting customer engagement data through Delta Lake to feed the models, and used PyFunk (a light wrapper from MLflow) to let data users add logic via Python; pre-calculated shop recommendations are now globally deployed using a low-latency, model-serving endpoint.
…of the game to speed up insights. Instead of manually reviewing dashboard data, the team built an ML model in Databricks using MLflow. The teams build and ingest customer engagement data through Delta Lake to feed their models. Using PyFunk, a light wrapper from MLflow, the data team can easily add logic v…
Business value
Second Dinner increased feature launches 400%, from 10 per year to more than 50, and cut model development and training time from months to weeks, enabling real-time, one-to-one shop personalization for every active player globally.
…ond Dinner CUSTOMER STORY Reaching new levels of in-game engagement during play 400% faster feature launches, from 10 per year to more than 50 Months to weeks faster model development and training Second Dinner, the studio…
AI capabilities
Recommendation & Personalization, Machine Learning
…and real-time recommendations. By removing manual interventions and inference, pre-calculated shop recommendations are now globally deployed using a low-latency, model-serving endpoint. Predicting player preferences and delivering in-game personalization Second Din…
Technology
Databricks Data + AI Platform, MLflow, Delta Lake
…of the game to speed up insights. Instead of manually reviewing dashboard data, the team built an ML model in Databricks using MLflow. The teams build and ingest customer engagement data through Delta Lake to feed their models. Using PyFunk, a light wrapper from MLflow, the data team can easily add logic v…
Headline outcome
…ond Dinner CUSTOMER STORY Reaching new levels of in-game engagement during play 400% faster feature launches, from 10 per year to more than 50 Months to weeks faster model development and training Second Dinner, the studio…
Use case type
Personalisation
…niverse, relies on a small team and collaboration for rapid feature iterations. Second Dinner significantly improved the personalization of their shop experience by centralizing on the Databricks Data + AI Platform, progressing from manual p…
Capture details
- Captured
- 09 Sept 2026, 06:07 UTC
- Extractor
- fetch-strip@1
- Snapshot hash
- 50c1dd84a96c65347d02e12e533b14da89bc2379f285456cb3f59818e8c37bce