Berlin Tech Meetup: The Future of Relational Foundation Models, Systems, and Real-World Applications
For Chief Innovation Officers
Real innovation requires better predictions AND faster delivery. Traditional ML flattens relational data into feature tables, losing the multi-hop relationships that hold the most predictive power. KumoRFM learns from that relational structure directly, beating flat-table approaches on every benchmark. It's also pre-trained on thousands of proprietary and public relational datasets, adding pattern knowledge no POC has ever had access to and delivering an additional 10-50% accuracy boost (proven on Stanford RelBench). And where traditional models take months of feature engineering, KumoRFM goes from hypothesis to production in hours, turning your innovation portfolio into shipped results.
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 Innovation Leaders choose Kumo
Here's exactly how Kumo accelerates your innovation portfolio.
Days
From idea to production model
Test any predictive hypothesis on your actual data in hours. No 6-month proof-of-concept. No waiting for ML engineering bandwidth.
55+
Validated use cases across industries
Churn, fraud, recommendations, LTV, demand forecasting — pre-validated patterns you can deploy immediately across business units.
30–50%
Accuracy gain over base model
Fine-tuning KumoRFM on your specific data delivers 30-50% accuracy improvement. Beat any hand-built model your team has today.
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 — Internal ML teams are backlogged: Every business unit wants predictive AI, but your ML engineering team has a 6-month wait per proof-of-concept. By the time a model reaches production, the business opportunity has moved on.
Path 2 — Off-the-shelf AI tools: They don't understand your relational data. They flatten multi-table schemas into feature vectors and lose the relationships between customers, transactions, and products that encode your most valuable predictions.
Kumo lets you test predictions on real data immediately. Define what you want to predict in a query language, point it at your data warehouse, and get production-grade models — no feature engineering, no custom pipelines, no 6-month wait.
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
