Stay in the loop
From technical deep-dives to real-world case studies, discover how teams put Synthefy's foundation models for structured data into production.
Predicting NFL Passing Yards with Nori: A 24% Backtest Return
We used Nori to predict NFL passing yards and price Kalshi bets. A 2025 quote-based backtest returned 24.1% after fees and modeled execution costs.
Read more
Synthefy's 2026 Fantasy Football Rankings: Predictions from 1,900 Player-Seasons of Data
Synthefy used Nori and 1,900 historical player-seasons to forecast and rank the top 200 fantasy football players for 2026.
Read more
From Time Series to Operational Intelligence: Synthefy Nori Tabular Foundation Model on InfluxDB
Time series data runs the operational world. Organizing it is the first step. Intelligence is the next step.
Read more
Nori-Rel, Scaling Beyond a Million Rows, Explainability, and Nori on Mac
Nori leads RelArena with Nori-Rel, scales beyond a million rows, adds feature importance, and now runs on Apple Silicon GPUs.
Read more
Building Foundation Models for the World's Structured Data
We're announcing our $6.5M seed round, led by Wing Venture Capital, to build Structured Data Foundation Models for the numerical data that runs the world.
Read more
From Black Box to Glass Box: Extracting Interpretability from Nori
Nori is a black-box tabular foundation model, but it separates each feature's contribution so cleanly that we can extract its reasoning and rebuild it as a transparent glass-box model you can read.
Read more
Better Predictive Maintenance with Nori
Learn what predictive maintenance is and how to use Nori to predict whether equipment will fail within an upcoming maintenance window.
Read more
Better Remaining Useful Life Prediction with Nori
Learn how to use Nori to estimate how much operating life remains from a machine's sensor history.
Read more
Better Cold-Start Forecasting with Nori: New and Short-History SKUs
Forecasting a product that has no sales history of its own, by borrowing demand patterns from the SKUs it resembles.
Read more
Introducing Nori Flash: Nori's Accuracy, Now in Microseconds on CPU
Nori Flash distills our tabular foundation model into a compact MLP — keep Nori's zero-training accuracy, but run inference on CPUs in microseconds, thousands of times faster and cheaper than a foundation-model forward pass.
Read more
Introducing Nori Embeddings: Representations That Know What You Care About
We're releasing programmatic access to Nori's embeddings: target- and context-aware vectors for tabular rows, pulled straight from the pretrained foundation model. They unlock search, retrieval, interpretability, and more, far beyond regression.
Read more
Synthefy-Nori: The Foundation Model That Replaces XGBoost
Train nothing, predict anything. Synthefy-Nori-V1 is the only fully open-source tabular foundation model — 6M parameters, zero training, and #1 mean R² across a 96-dataset regression benchmark.
Read more
Synthefy MUSEval: The Largest Multivariate Evaluation Benchmark for Time Series Foundation Models
MUSEval is the first large-scale benchmark (45 datasets, 19B points, 16 domains) built to measure multivariate gain — how much better models get when given related signals.
Read more
Why LLMs Can't Solve Time Series
Discover why Large Language Models struggle with time series forecasting and what the industry needs instead.
Read more
"DALL-E" for Timeseries: Scaling Time Series ML with Synthetic Data Generation
Learn how synthetic data generation is revolutionizing time series machine learning, just like "DALL-E" transformed image generation.
Read more
Introducing Synthefy API: State-of-the-Art Time Series Forecasting for Everyone
Discover how Synthefy API brings cutting-edge time series forecasting capabilities to developers and businesses of all sizes.
Read more
Data Enrichment: The Missing Ingredient in Time Series Modeling
Explore why data enrichment is crucial for improving time series model accuracy and how to implement it effectively.
Read more
Recognition & milestones
One of the best on leading time series benchmarks for univariate forecasting
Best performer on multivariate and multimodal time series benchmarks (Coming Soon)
US Army Phase 2 SBIR award recipient
Advancing time series AI for defense and national security applications