LLM Driven AutoForecasting with Sktime’s `craft()`

Graphical An LLM is proposing blueprints, these are passed to the sktime’s craft method and evaluated iteratively during fit. Predict is using the best estimator found during fit to create the forecast. AutoML is relying in many cases on some kind of grid searches. This is expensive. However, if humans are selecting hyperparameters, they often have some feeling about a good choice based on previous experiences. So I wondered, if LLM can act like an human expert and determine the parameters by considering the problem and using the knowledge d in its weights.