← All applications
Case studyTools

The Oracle

Forecast Any Time Series, Privately

Upload a CSV, pick the columns and get a forecast with confidence bands from a foundation model for time series. The model runs on your own machine, so your data never leaves it.

Preview of The Oracle

Screenshots

The problem

Forecasting a time series usually means sending your data to a cloud service or writing modelling code.

What it does

  • Local AI time-series forecasting with confidence bands
  • Covariates, calendar features and holidays
  • Backtest accuracy metrics and CSV export

Technical highlights

  1. Local foundation model

    A time-series foundation model runs on your own machine, so the data never leaves it.

  2. Covariates and calendar

    Covariates, calendar features and holidays can be added to improve the forecast.

  3. Backtests

    Backtest accuracy metrics, confidence bands and CSV export help you judge and reuse the results.

Interested in working together?

I'm open to new opportunities. Let's talk about how I can help your team.

Get in touch