Berlin Tech Meetup: The Future of Relational Foundation Models, Systems, and Real-World Applications
For VPs & SVPs of AI
LLMs tokenize tables as text. Traditional ML flattens them. Both destroy the relational structure that encodes your most valuable signals. KumoRFM learns from that structure natively, and it's also pre-trained on thousands of relational datasets, bringing pattern knowledge that gives it an additional accuracy edge no in-house or LLM-based approach can match. Production-ready in hours, not months.
Book a demo and get a free trial of the full platform: research agent, fine-tune capabilities, and forward-deployed engineer support.
By submitting, you accept the Terms and Privacy Policy.
Why AI Leaders choose Kumo
LLMs transformed unstructured data. KumoRFM does the same for the relational databases where your most valuable predictions live.
10–50%
More accurate than LLMs on tables
LLMs tokenize your relational data as text and lose the structure. KumoRFM understands primary keys, foreign keys, and multi-hop relationships natively.
Pre-trained
On billions of relational patterns
Like GPT for text, KumoRFM is pre-trained on thousands of relational datasets. Fine-tune on your schema for 30-50% accuracy gains.
API-first
Production-grade predictions
REST API, Python SDK, MCP server for agentic workflows. Integrate predictions into any product or workflow your AI team builds.
Loved by data scientists, ML engineers & CXOs at
In production today
Enterprise Customer
Went from 3 models in production to over 50 in a single quarter with the same team. Feature engineering eliminated, pipeline complexity reduced by 95%.
Databricks
Lead-scoring models delivering dramatic improvement in conversion rates. Deployed in days instead of months, with zero feature engineering.
DoorDash
Restaurant recommendations driving hundreds of millions in GMV. Expanded to notification reranking and send-time optimization using the same foundation.
The challenge you know too well
Path 1 — LLMs on tables: They tokenize your relational data as text, losing the structure that encodes your most valuable predictions. Foreign keys, multi-hop relationships, temporal patterns — all flattened into token sequences that GPT was never designed to reason over.
Path 2 — Traditional ML: Each use case requires months of feature engineering, custom pipelines, and dedicated infrastructure. Your team ships 3–5 models per year while the business asks for 50+.
KumoRFM is purpose-built for relational prediction. It connects directly to your data warehouse, understands schema relationships natively, and delivers production-grade predictions via API — no feature engineering, no custom pipelines.
95%
Less data preparation
Feature engineering eliminated
10–50%
Accuracy improvement
Over traditional ML (RelBench)
20x
Faster time-to-value
From months per model to hours
55+
Use cases
Validated in production
KumoRFM isn't limited to your data alone. Pre-trained on billions of relational patterns across diverse datasets and fine-tuned to your schema, it sees what no in-house model can. As per the SAP SALT benchmark.
LLM
GPT4 + AutoML
PhD Data Scientist
Feature eng. + XGBoost
KumoRFM
Relational Foundation Model
17x
increase in models shipped per quarter
“Beating internal XGBoost model on key metrics with far less data and features. We went from three models in production to over fifty in a single quarter, with the same team.”
Matt Loskamp
GTM Data Science Leader, Enterprise Customer
From startups to enterprises, leading organizations rely on Kumo to deliver predictive insights at scale.
Peer-reviewed
Kumo is built on 40+ peer-reviewed papers at NeurIPS, ICML, and KDD. The methodology is public and reproducible.
K. Huang, M. Fey, J. Leskovec et al.
A foundation model for relational data - pre-trained across schemas, it delivers accurate predictions out of the box and improves with fine-tuning on your specific data.
Read paperM. Fey, W. Hu, K. Huang, J. Leskovec et al.
Introduces learning predictive models directly on relational databases, eliminating the feature engineering pipeline that has historically bottlenecked enterprise ML.
Read paperJ. Robinson, R. Miao, K. Huang et al.
An open benchmark for evaluating relational prediction methods across 11 databases and 30 tasks. Kumo consistently outperforms traditional ML baselines.
Read paper
