What types of models and augmentations are available to build in One AI?

Answer: One AI capabilities are divided into three types: machine learning, data augmentations, and integrated services.  

In the machine learning category, users can create classification (binary and multi-class) and regression models at the moment, and soon will be able to build time to event models as well. One AI Recipes, a guided workflow for easily creating machine learning models, allows you to predict Voluntary Attrition, Involuntary Attrition, or perform Binary Promotion Analysis.  If you are interested in other types of models and predictions, you can work with your CS lead on creating a custom or advanced model. Our One AI team is always working on adding more model types to the recipes page, so please continue to read release notes and check back for more.

Moving on to data augmentations, commute time and distance is available.  This data is obtained by passing zip code combinations from your data to a mapping service and returning the times and distances. This data can then be integrated into your data model.

Finally, integrated services are statistical capability integrated directly into One Model storyboard tiles.  Current integrated services include trend forecasting and scatterplot correlations with line of best fit.  Significance of rates and averages with smart sorting is coming soon.

Was this article helpful?

0 out of 0 found this helpful



Please sign in to leave a comment.