Our Technology
Data Mining
Models
Our underlying models include decision trees, linear and logsitic regression, FPGrowth and many more
Parameters
Model parameters can be manually tuned or automatically optimised using heuristics
Algorithms
Our bespoke algorithms offload filtering and aggregation onto your data store, minimising data transfer and maximising build speed
Predictions
Predictions can be made in the UI or via a high-performance API.
CI / CD for Data Pipelines
Github Actions
- Build and maintain Data Mining models directly from your CI/CD pipelines in Github Actions
- Create cloud data infrastructure for testing or deployment within Github Actions
- S3, SNS, SQS, Glue Databases, Glue Tables
- GCS, PubSub
- Upload data from any URL into S3/GCS
GATE – Github Actions Editor
- Visual editor for Github Actions
- Discovery of pre-build Actions
- Directly from organisations
- From Github Marketplace
- From locally provided actions
- Discovery of available variables and secrets across organisation, repository and user settings
- Validation of settings prior to making a commit
