Berlin Tech Meetup: The Future of Relational Foundation Models, Systems, and Real-World Applications
For Chief Technology Officers
Your ML pipelines flatten relational data into feature tables, losing the multi-hop relationships between entities that drive prediction accuracy. KumoRFM learns from that relational structure directly, so nothing is lost. It's also pre-trained on thousands of proprietary and public relational datasets, adding pattern knowledge no in-house model has ever seen for an additional 10-50% accuracy boost (proven on Stanford RelBench). And where each model today takes months of pipeline work, KumoRFM replaces it all in hours. One platform, zero new infrastructure to deploy, secure, or maintain.
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 CTOs choose Kumo
Kumo consolidates your entire ML prediction stack into a single platform that connects to your existing warehouse and runs in your cloud. No new infrastructure to provision, secure, or maintain.
Zero
New infrastructure to deploy
Kumo connects natively to Snowflake, Databricks, BigQuery. Runs in your VPC. No new stack to provision, secure, or maintain.
SOC 2 Type II
Enterprise security certified
Private cloud deployment on AWS, Azure, or GCP. Your data never leaves your environment. SSO, audit logs, role-based access built in.
50+
Use cases, one platform
Replace dozens of custom ML pipelines — churn, fraud, recommendations, LTV, demand — with a single platform your team already knows how to query.
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 — Custom pipeline per model: Every prediction requires its own ETL, feature store, training infrastructure, serving layer, and monitoring stack. Your platform team spends more time maintaining ML infrastructure than building products. Models take months to reach production, and most never do.
Path 2 — LLMs for structured data: They're expensive to run at scale and fundamentally inaccurate for relational predictions. LLMs tokenize your tables as text — they have no understanding of primary keys, foreign keys, or the relationships between entities that encode your most valuable signals.
KumoRFM connects directly to your existing data warehouse — Snowflake, Databricks, or BigQuery. One platform replaces dozens of custom pipelines across churn, fraud, recommendations, LTV, and demand. Deployed in your VPC, secured to your standards, with no new infrastructure to manage.
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
