Create your own predictive models or connect to external AI models using Data 360.
- Use Clustering to Uncover Hidden Patterns in Structured Data (Generally Available)
Automatically group similar data into meaningful cohorts with clustering models in Data 360. Train the model on structured data and run inferences through a batch data transform or streaming predict job to assign new records to saved clusters. This feature, which is now generally available, includes some changes since the last release. - Build Predictive Models with the New Default Runtime
Use the new default runtime when building predictive models in Data 360. The new runtime supports new algorithms, such as clustering and forecasting, and is the foundation for long-term model building capabilities. - Deliver Richer Outcomes with Multiclass Models
Make highly targeted data-driven decisions in Data 360 by using multiclass models. Unlike binary models that predict only two outcomes, multiclass models classify data into up to 50 distinct categories. This capability, which is now generally available, includes enhancements since the beta release. - Predict Future Trends with Time Series Forecasting (Generally Available)
Improve demand planning and revenue estimates by identifying trends and seasonality in your data with forecasting in Data 360. This capability is now generally available.. - Improve Engagement with Sentiment Analysis (Generally Available)
Gain deeper insights into customer feedback with sentiment analysis in Data 360 to analyze text, such as reviews, surveys, emails, and chat transcripts. Uncover how customers feel about your brand, products, and experiences. This feature is now generally available and includes some changes since the beta release. - Drive Actionable Insights with Topic Classification (Generally Available)
Extract meaningful insights from unstructured text by using a pre-trained model in Data 360 for zero-shot topic classification. This capability is now generally available and includes some changes since the beta release. - Get Deeper Insights with Structured Clustering (Beta)
Go beyond basic segmentation with clustering models in Data 360. Automatically group customers, uncover patterns in structured data, and validate results with built-in metrics. - Monitor Predictive Model Drift (Beta)
Use predictive model drift monitoring (beta) in Data 360 to track deviations in live inferences compared to training data. You can detect shifts, understand contributing variables, and retrain a model before accuracy drops.