DataRobot benchmarking¶
DataRobot's cloud product has extensive scale, managing thousands of deployments and 11B predictions in the US, and thousands more deployments in the EU. In terms of benchmarks, DataRobot can handle scalable ingest for up to 100GB of data per single table, build thousands of models in parallel, run 10k+ deployments and handle tens of billions of predictions and up to 1TB per prediction job. Scale is no problem for DataRobot.
Insurance¶
Use case 1¶
A large multinational insurance company headquartered in Brussels uses DataRobot across the business for a number of use cases including within fraud detection, claims processing, and underwriting. For model development they are very actively experimenting, testing models, and performing explainability checks on the DataRobot platform. Using DataRobot they are able to bring these models successfully through their risk management process and once in production have realized massive value.
Fast facts/2023
- Projects/experiments: 1,438
- ML models built: 29,410
- Models in production: 4,436
- Predictions: 524 million (average of 43 million per month)
Use case 2¶
Another multinational insurer uses DataRobot in EMEA and Japan at considerable scale. DataRobot is key for their retention use cases, lead scoring and underwriting practice across the business.
Fast facts/2023
- Projects/experiments: 682
- ML models built: 31,720
- Models in production: 1456
- Predictions: 258M prediction rows from 8804 prediction requests
Use case 3¶
A large re-insurer is impressed with how DataRobot removes friction from building models and serving predictions. Use cases include predicting unpaid invoices to optimize overdue invoice collections and predicting market prices, taking quotes from quote aggregators to determine when competitors implemented pricing changes. They have used DataRobot's managed SaaS product, so they do not have to think about compute availability and can instead focus on data science outcomes for 157 users.
Fast facts/2023
- Projects/experiments: 14,481
- ML models built: 177,475
- Predictions: 1.991 Billion on DataRobot's high-performance prediction servers
Healthcare¶
A global pharmaceuticals giant uses DataRobot to improve business efficiency. They use DataRobot to:
- Forecast demand in North America and EMEA
- Predict propensity to buy in the US
- Predict IT tickets
- Perform content recommendations.
Fast facts
- Projects/experiments: 3000+ per month
- ML models built: 30,000+ per month
- Models in production: 150
- Predictions: 3,000-7,000 per quarter
Manufacturing¶
One of the world’s largest building materials manufacturers uses DataRobot. They have more than 2000 plants globally and employ 60k+ employees. They deploy models to production in 60 of their manufacturing plants in order to predict equipment failure: kilns, fans, vertical roller mills, crushers etc. They leverage DataRobot MLOps possibility to deploy models outside of the platform in air-gapped environments, deploying using the Portable Prediction Server container to edge devices on-premise. Their predictive maintenance use cases help avoid stoppages along their production lines--critical because any stoppage leads to significant financial losses.
Fast facts/2023
- Projects/experiments: 1000+
- ML models built: 15,000+
- Models in production: 150
Retail¶
Use case 1¶
A freight company uses DataRobot to assist their freight, supply chain, and forwarding businesses, with 170+ active users on the platform from multiple divisions. They use DataRobot to forecast incoming calls and improve workforce planning, predict possible thefts in parcel centers, forecast total volume of packages entering certain countries, and predict financial KPIs. They have seen how the experiments and models built on DataRobot outperform forecasting models built outside the platform. They have experienced a 50%+ error reduction on key use cases. Accuracy improvements have allowed them to move from monthly to weekly—and even daily—predictions with granular breakdowns.
Fast facts/2023
- Models in production: 200-250 models
Use case 2¶
One of Europe’s largest media companies has been a DataRobot customer since 2018. They use their deployed models for demand optimization, targeted advertising, and content management. They recently extended their prediction environment to support large-scale batch predictions for audience segmentation and ad targeting. The team is leveraging the DataRobot/Snowflake integration capabilities to maintain a computationally intensive predictive pipeline and complete weekly scoring on time. DataRobot enables the small data science team to work more efficiently and with greater accuracy, bringing models live faster than before and achieving incremental revenue gain with optimized inventory management.
Fast facts
- Models in production: 20+
- Predictions: 160m+ rows weekly