Berlin Tech Meetup: The Future of Relational Foundation Models, Systems, and Real-World Applications
For Heads of Analytics
Your team needs predictions that the business trusts, and trust requires accuracy. KumoRFM delivers better results by learning from relational data structure instead of flat tables. It's also pre-trained on thousands of datasets, providing additional knowledge that boosts accuracy 10-50% on RelBench. And your analysts can define predictions in a SQL-like language, shipping in hours with no ML expertise needed.
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 Analytics Leaders choose Kumo
Your analysts know the business better than anyone. Now they can make predictions too.
PQL
SQL-like prediction language
Kumo's Predictive Query Language reads like SQL. Your analysts can define predictions directly — 'predict customer churn in 30 days' — without learning Python or ML frameworks.
Hours
Not months per model
No more waiting 6 months for the ML team to deliver a single model. Your analytics team can generate predictions on their own timeline.
Explainable
Scores stakeholders trust
Every prediction includes feature importance. Your business stakeholders can understand why a customer is flagged, not just that they are.
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.
Your team knows the business. Now they can predict it.
Path 1 — Depend on the ML team: Every prediction request goes into a queue. Months-long wait times for feature engineering, model training, and deployment. Your analysts are blocked, and the business decisions they support are delayed.
Path 2 — Self-service BI tools: Dashboards and reports tell you what happened, but they can't tell you what will happen. Traditional BI tools weren't built for predictive analytics — they stop at descriptive and diagnostic.
Kumo's Predictive Query Language lets your analysts write predictions like SQL queries. Connect to your data warehouse, define a prediction task in PQL, and get results in hours — no ML expertise required, no pipeline to maintain.
SQL-like
Query language
Predictive Query Language
Zero
ML expertise required
No ML pipelines to learn
10–50%
Accuracy improvement
Over traditional ML (RelBench)
Hours
Not months
From idea to production predictions
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
