---
title: "Unlock powerful insights and forecasts with Predictive AI Functions"
description: "Data teams frequently field questions about future sales, metric movements, and anomalous data, but answering them typically requires data science teams to build and manage models, creating a bottleneck. Predictive AI Functions, now in Beta, remove that bottleneck by providing SQL-native functions for forecasting, driver analysis, and anomaly detection, backed by state-of-the-art ML models maintained centrally by Databricks. The launch includes ai_forecast for time series projection, ai_top_drivers for segment driver analysis, ai_detect_anomalies for outlier detection, and ai_predict_value and ai_predict_class for regression and classification. These functions can be called directly in SQL, invoked through Genie with plain-language questions, or embedded in dashboards, delivering consistent, high-quality answers without infrastructure management. Benchmarking on fev-bench shows ai_forecast outperforms forecasting functions from leading cloud data warehouses, achieving industry-leading accuracy out of the box with no tuning required."
---

# Unlock powerful insights and forecasts with Predictive AI Functions

[Databricks](https://yomu.fyi/company/databricks) · Jonathan Brito, Gary Shambat · Oct 15, 2026

**Type:** Announcement

## Summary

Data teams frequently field questions about future sales, metric movements, and anomalous data, but answering them typically requires data science teams to build and manage models, creating a bottleneck. Predictive AI Functions, now in Beta, remove that bottleneck by providing SQL-native functions for forecasting, driver analysis, and anomaly detection, backed by state-of-the-art ML models maintained centrally by Databricks. The launch includes ai\_forecast for time series projection, ai\_top\_drivers for segment driver analysis, ai\_detect\_anomalies for outlier detection, and ai\_predict\_value and ai\_predict\_class for regression and classification. These functions can be called directly in SQL, invoked through Genie with plain-language questions, or embedded in dashboards, delivering consistent, high-quality answers without infrastructure management. Benchmarking on fev-bench shows ai\_forecast outperforms forecasting functions from leading cloud data warehouses, achieving industry-leading accuracy out of the box with no tuning required.

## Context

Databricks announces Predictive AI Functions, a set of SQL-native functions for advanced analytics, now in Beta. The functions aim to democratize forecasting, driver analysis, and anomaly detection by making them accessible to analysts and business users without data science expertise.

## Approach / What changed

Databricks provides SQL-native Predictive AI Functions backed by centrally maintained ML models. Users call ai\_forecast, ai\_top\_drivers, ai\_detect\_anomalies, ai\_predict\_value, and ai\_predict\_class directly in SQL, through Genie with plain-language questions, or embedded in dashboards, without building or managing infrastructure.

## Takeaways

- Predictive AI Functions include ai\_forecast, ai\_top\_drivers, ai\_detect\_anomalies, ai\_predict\_value, and ai\_predict\_class, all callable as native SQL functions.
- ai\_forecast uses a transformer-based time series foundation model pretrained on diverse time series, requiring no tuning and supporting holiday effects and external covariates.
- In fev-bench benchmarking, ai\_forecast outperformed forecasting functions from a leading cloud data warehouse, achieving a higher task win rate.

## FAQ

### How do Predictive AI Functions work?

Predictive AI Functions are SQL-native functions backed by ML models maintained centrally by Databricks. Users call them directly in SQL, through Genie with plain-language questions, or embedded in dashboards, without building or managing any infrastructure.

### What functions are included?

The launch includes ai\_forecast for time series projection, ai\_top\_drivers for segment driver analysis, ai\_detect\_analytics for outlier detection, ai\_predict\_value for regression, and ai\_predict\_class for classification.

### How does ai\_forecast compare to other cloud data warehouse forecasting?

In fev-bench benchmarking, ai\_forecast outperformed forecasting functions from a leading cloud data warehouse, achieving a higher task win rate with no tuning required.

**Tags:** [Anomaly Detection](https://yomu.fyi/topic/anomaly-detection), [Databricks](https://yomu.fyi/topic/databricks), [Forecasting](https://yomu.fyi/topic/forecasting), [Machine Learning](https://yomu.fyi/topic/machine-learning), [SQL](https://yomu.fyi/topic/sql)

- Source: [Databricks](https://www.databricks.com/blog/unlock-powerful-insights-and-forecasts-predictive-ai-functions)
- Source URL: https://www.databricks.com/blog/unlock-powerful-insights-and-forecasts-predictive-ai-functions
- Ingested by Yomu: 2026-10-15T00:00:19.414Z

[Read original post](https://www.databricks.com/blog/unlock-powerful-insights-and-forecasts-predictive-ai-functions)