# Extending Relational Query Processing with ML Inference

arXiv: https://arxiv.org/abs/1911.00231 · HTML: https://mlsanity.com/paper/1911.00231/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Nov 2019.

## Built on by (most cited first, 15 of 15)

- [tf.data: A Machine Learning Data Processing Framework](https://mlsanity.com/paper/2101.12127/) (2021)
- [Production Machine Learning Pipelines: Empirical Analysis and Optimization Opportunities](https://mlsanity.com/paper/2103.16007/) (2021)
- [End-to-end Optimization of Machine Learning Prediction Queries](https://mlsanity.com/paper/2206.00136/) (2022)
- [Query Processing on Tensor Computation Runtimes](https://mlsanity.com/paper/2203.01877/) (2022)
- [On Efficient Approximate Queries over Machine Learning Models](https://mlsanity.com/paper/2206.02845/) (2022)
- [Functional Collection Programming with Semi-Ring Dictionaries](https://mlsanity.com/paper/2103.06376/) (2021)
- [NeurDB: On the Design and Implementation of an AI-powered Autonomous Database](https://mlsanity.com/paper/2408.03013/) (2024)
- [Analytical Engines With Context-Rich Processing: Towards Efficient Next-Generation Analytics](https://mlsanity.com/paper/2212.07517/) (2022)
- [The Tensor Data Platform: Towards an AI-centric Database System](https://mlsanity.com/paper/2211.02753/) (2022)
- [A Comparison of Decision Forest Inference Platforms from A Database Perspective](https://mlsanity.com/paper/2302.04430/) (2023)
- [Serving Deep Learning Model in Relational Databases](https://mlsanity.com/paper/2310.04696/) (2023)
- [Bullion: A Column Store for Machine Learning](https://mlsanity.com/paper/2404.08901/) (2024)
- [Personalized Top-k Set Queries Over Predicted Scores](https://mlsanity.com/paper/2502.12998/) (2025)
- [Towards Effective Orchestration of AI x DB Workloads](https://mlsanity.com/paper/2603.03772/) (2026)
- [MLSkip: Data Skipping for ML Filters via Lightweight Metadata](https://mlsanity.com/paper/2606.03946/) (2026)

## Abstract (arXiv)

The broadening adoption of machine learning in the enterprise is increasing the pressure for strict governance and cost-effective performance, in particular for the common and consequential steps of model storage and inference. The RDBMS provides a natural starting point, given its mature infrastructure for fast data access and processing, along with support for enterprise features (e.g., encryption, auditing, high-availability). To take advantage of all of the above, we need to address a key concern: Can in-RDBMS scoring of ML models match (outperform?) the performance of dedicated frameworks? We answer the above positively by building Raven, a system that leverages native integration of ML runtimes (i.e., ONNX Runtime) deep within SQL Server, and a unified intermediate representation (IR) to enable advanced cross-optimizations between ML and DB operators. In this optimization space, we discover the most exciting research opportunities that combine DB/Compiler/ML thinking. Our initial evaluation on real data demonstrates performance gains of up to 5.5x from the native integration of ML in SQL Server, and up to 24x from cross-optimizations--we will demonstrate Raven live during the conference talk.