Berlin Tech Meetup: The Future of Relational Foundation Models, Systems, and Real-World Applications
For Heads of Recommendations
Collaborative filtering flattens user-item relationships into a matrix, missing the rich entity graph. KumoRFM sees user-product-category-location-time relationships natively, capturing signals your rec engine can't. It's also pre-trained on thousands of relational datasets, bringing pattern knowledge that gives it an additional accuracy edge, especially for cold-start users and new items. And it ships new recommendation models in hours, not the months your current pipeline requires.
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 Recommendation Leaders choose Kumo
Here's exactly how Kumo transforms your recommendation stack.
$100M+
GMV driven at DoorDash
Kumo-powered restaurant recommendations drive hundreds of millions in GMV. The model sees user-restaurant-cuisine-location-time relationships that matrix factorization misses.
Cold start
Problem solved
New users and new items get accurate recommendations from day one. KumoRFM transfers knowledge from billions of relational patterns — no interaction history needed.
10–50%
Accuracy improvement
Fine-tuning KumoRFM on your interaction graph delivers 10-50% accuracy gains over traditional collaborative filtering and content-based methods.
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 — Collaborative filtering: It only sees the user-item interaction matrix, missing rich entity relationships like product categories, seller reputation, geographic context, and temporal patterns. Cold start remains unsolved, and accuracy plateaus because the model is structurally blind to relational signals.
Path 2 — LLM-based recommendations: They generate plausible-sounding recommendations but lack grounding in your actual catalog data. They hallucinate products, ignore inventory constraints, and have no concept of the relational structure that connects users, items, and context.
KumoRFM natively understands multi-hop relational patterns across your entire database. It learns that a user who bought running shoes from a premium brand in winter, in a cold-weather city, with high review engagement, is likely to respond to specific recommendations — without a single hand-crafted feature.
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
