Decision intelligence for machine learning

Build models that make better decisions.

Understand your dataset, select appropriate models, and evaluate predictions by real-world utility, not prediction error alone.

Try the tools without an account: 5 successful runs per rolling week.

Evidence, with the caveats visible

Observed facts
Shape, missingness, types, target, and feature diagnostics
Directly calculated from the uploaded dataset
Interpretable guidance
Statistical diagnostics are separated from heuristic recommendations
No model family is presented as a performance guarantee

One workflow, before and after training

Live

Before training: Decision Intelligence

Inspect dataset health, target and feature signals, leakage warnings, preprocessing guidance, and suitable model families.

  • Dataset health score
  • Automated model recommendations
  • EDA + preprocessing automation
Analyze Dataset
In development

AutoML for Trading

A future execution layer for training and benchmarking candidates. It is not currently available for live model training or deployment.

  • Candidate benchmarking is being designed
  • No launch date is being promised
  • Decision Intelligence remains available now

From dataset to defensible decision

1

Diagnose the dataset

Upload a CSV, confirm the target, and review quality, leakage, feature, and validation warnings before training.

2

Train outside Quantsynth

Use the suggested baselines and model families in your own reproducible training pipeline.

3

Evaluate held-out predictions

Upload predictions with actual outcomes, compare statistical quality and decision utility, then validate assumptions before deployment.

Raw dataset

Diagnostics and model guidance

→
Your training pipeline

Baselines, challengers, validation

→
Quantsynth Evaluation

Error, utility, risk, limitations

Simple Pricing

Start free

10 evaluations/month

No credit card required

Trader starts at EUR29/month

Clear boundaries

Plan limits and included features are published before checkout.

Anonymous tools share 5 successful runs per rolling week.

Frequently Asked Questions

Any models you've already trained. Upload predictions from LSTM, Prophet, ARIMA, XGBoost, N-BEATS, or any other architecture. Quantsynth evaluates predictions, not model training.
RMSE measures the scale of prediction errors. FIS is QuantSynth's proprietary decision-oriented evaluation metric. Treat both as diagnostics: the appropriate ranking depends on the task, validation design, and costs.
No. Just upload model predictions + actual prices. You keep your training data and model architectures private.
Yes. No long-term contracts.
Uploads are sent over HTTPS on the production site and processed for analysis. Saved reports may retain derived results when you are signed in. Review the privacy policy before uploading sensitive data.