Berlin Tech Meetup: The Future of Relational Foundation Models, Systems, and Real-World Applications
For Principal Data Scientists
You know flat feature tables leave signal on the table, specifically the multi-hop relational patterns that drive real prediction accuracy. KumoRFM learns directly from that relational structure. It's also pre-trained on thousands of proprietary and public datasets, capturing patterns no amount of manual feature engineering can replicate. That translates to an additional 10-50% accuracy boost verified on Stanford RelBench. And it eliminates the months of feature engineering entirely, delivering production models 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 Principal Data Scientists choose Kumo
Built on open research, validated on public benchmarks, and shipping in production at scale.
40+
Peer-reviewed papers
Built on research published at NeurIPS, ICML, and KDD. The methodology is open, reproducible, and benchmarked against the best methods in the field.
10–50%
Over your best XGBoost model
KumoRFM consistently outperforms hand-tuned XGBoost and LightGBM baselines on RelBench — by learning directly from relational structure instead of flat feature tables.
PQL
Predictive Query Language
Define predictions declaratively: 'predict customer churn in 30 days.' The foundation model discovers features automatically from your relational schema. No manual feature engineering.
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 already know
Path 1 — Manual feature engineering: It can only capture what you think to encode — you miss the multi-hop relational patterns that drive real prediction accuracy. Weeks of work per model, and you still leave signal on the table.
Path 2 — LLMs on tabular data: They tokenize tables as text, destroying the relational structure that matters most. No concept of primary keys, foreign keys, or the join paths that encode the most predictive patterns.
KumoRFM learns directly on relational databases, capturing patterns across joins that no amount of feature engineering can replicate. It operates on your schema as a graph — discovering multi-hop features automatically that you'd never encode by hand.
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, reproducible, and benchmarked against the best methods in the field.
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
