We’re building:

  • A package that helps you deploy your fold pipelines.

  • Our own implementation of new and classic time series models, providing an additional order of magnitude speedup during backtesting (while supporting online updates when deployed).

  • Time Series AutoML without lookahead bias, to get accurate simulated performance on past data that you can rely on.

  • Training models on multiple time series at the same time, with synchronized Adaptive Models.

  • Full support for Uncertainty Quantification, making it an internal part of Fold.

And many more…