# Databricks expands predictive AI functions in beta

> Databricks announced its Predictive AI Functions in beta for forecasting, anomaly detection, driver analysis and prediction through SQL. The set includes an updated ai_forecast plus ai_top_drivers, ai_detect_anomalies, ai_predict_value and ai_predict_class. Functions can be called in SQL; some are also exposed through the Genie interface.

- Canonical URL: https://newsverum.com/en/news/databricks-predictive-ai-functions-forecast-anomaly-beta
- Publisher: Newsverum
- Section: Technology
- Published: 2026-10-15T22:00:39+00:00
- Updated: 2026-10-15T22:00:39+00:00
- Event / data period: 2026-10-14
- Other editions: [Türkçe](https://newsverum.com/tr/news/databricks-predictive-ai-functions-forecast-anomaly-beta.md), [العربية](https://newsverum.com/ar/news/databricks-predictive-ai-functions-forecast-anomaly-beta.md), [Français](https://newsverum.com/fr/news/databricks-predictive-ai-functions-forecast-anomaly-beta.md), [Español](https://newsverum.com/es/news/databricks-predictive-ai-functions-forecast-anomaly-beta.md), [Deutsch](https://newsverum.com/de/news/databricks-predictive-ai-functions-forecast-anomaly-beta.md), [Português](https://newsverum.com/pt/news/databricks-predictive-ai-functions-forecast-anomaly-beta.md)

Examples use New York taxi trips to analyze daily revenue and passenger series. Databricks says it compared ai_forecast with a rival warehouse function on FEV-Bench. That performance claim comes from the company’s own benchmark; the APIs are in beta, and not every function is yet available in every interface.

## Data

### Databricks expands predictive AI functions in beta

Databricks announced its Predictive AI Functions in beta for forecasting, anomaly detection, driver analysis and prediction through SQL. The set includes an updated ai_forecast plus ai_top_drivers, ai_detect_anomalies, ai_predict_value and ai_predict_class. Functions can be called in SQL; some are also exposed through the Genie interface. Examples use New York taxi trips to analyze daily revenue and passenger series. Databricks says it compared ai_forecast with a rival warehouse function on FEV-Bench. That performance claim comes from the company’s own benchmark; the APIs are in beta, and not every function is yet available in every interface.

Methodology: This record summarizes the named primary source and its reported measurements; no independent test or survey verification was performed.

| date | label | description | status |
|---|---|---|---|
| 2026-10-14 | Databricks announced its Predictive AI Functions in beta for forecasting, anomaly detection, driver analysis and prediction through SQL. The set includes an updated ai_forecast plus ai_top_drivers, ai_detect_anomalies, ai_predict_value and ai_predict_class. Functions can be called in SQL; some are also exposed through the Genie interface. | Databricks announced its Predictive AI Functions in beta for forecasting, anomaly detection, driver analysis and prediction through SQL. The set includes an updated ai_forecast plus ai_top_drivers, ai_detect_anomalies, ai_predict_value and ai_predict_class. Functions can be called in SQL; some are also exposed through the Genie interface. Examples use New York taxi trips to analyze daily revenue and passenger series. Databricks says it compared ai_forecast with a rival warehouse function on FEV-Bench. That performance claim comes from the company’s own benchmark; the APIs are in beta, and not every function is yet available in every interface. | occurred |

Sources: <https://www.databricks.com/blog/unlock-powerful-insights-and-forecasts-predictive-ai-functions> · Download data: [JSON](https://newsverum.com/api/v1/articles/databricks-predictive-ai-functions-forecast-anomaly-beta/data/source-report?lang=en&format=json) · [CSV](https://newsverum.com/api/v1/articles/databricks-predictive-ai-functions-forecast-anomaly-beta/data/source-report?lang=en&format=csv)

## Sources

- [Databricks](<https://www.databricks.com/blog/unlock-powerful-insights-and-forecasts-predictive-ai-functions>) (Source checked: 2026-10-15; Published: 2026-10-14)

---

Cite the canonical URL above. [Editorial standards and corrections](https://newsverum.com/en/editorial)