Berlin Tech Meetup: The Future of Relational Foundation Models, Systems, and Real-World Applications
For Heads of Data Science
Your team's models flatten relational data into feature tables, losing the multi-hop signals that drive accuracy. KumoRFM learns from that structure directly. It's also pre-trained on thousands of relational datasets, providing pattern knowledge your team has never had and delivering an additional 10-50% accuracy boost on RelBench. And it eliminates months of feature engineering, letting your data scientists ship predictions in hours.
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 Data Science Leaders choose Kumo
Your team is brilliant but bottlenecked. Here's how Kumo changes the math.
50+
Models per quarter
One team went from 5 models per year to 50+ per quarter. Same team, same budget. Feature engineering eliminated entirely.
Zero
Feature engineering needed
Your data scientists stop writing SQL joins and aggregations. They define predictions in a query language. The foundation model discovers features automatically.
10–50%
Accuracy improvement
KumoRFM consistently beats hand-tuned XGBoost and LightGBM baselines by learning directly from relational structure.
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 — Junior members blocked on plumbing: Your newest data scientists spend 80% of their time on feature engineering, data wrangling, and pipeline glue code instead of actual modeling. Senior members get pulled into reviews and debugging instead of tackling high-impact problems.
Path 2 — Accuracy capped by flat feature tables: Hand-crafted features from flat tables can only capture so much signal. The richest predictive patterns live in the relationships across your relational database — joins your team never has time to explore.
Kumo lets your data scientists write prediction queries directly against your data warehouse. The foundation model automatically learns from the full relational structure — no feature engineering, no pipeline work, just predictions that ship in hours.
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
