ForecastPFN: Synthetically-Trained Zero-Shot Forecasting
This addresses the challenge of data-sparse commercial applications where traditional forecasting methods are restricted due to insufficient training data.
The paper tackles the problem of time-series forecasting with very limited initial data by introducing ForecastPFN, a zero-shot model trained purely on synthetic data, which achieves more accurate and faster predictions than state-of-the-art methods even when they are allowed additional training data.
The vast majority of time-series forecasting approaches require a substantial training dataset. However, many real-life forecasting applications have very little initial observations, sometimes just 40 or fewer. Thus, the applicability of most forecasting methods is restricted in data-sparse commercial applications. While there is recent work in the setting of very limited initial data (so-called `zero-shot' forecasting), its performance is inconsistent depending on the data used for pretraining. In this work, we take a different approach and devise ForecastPFN, the first zero-shot forecasting model trained purely on a novel synthetic data distribution. ForecastPFN is a prior-data fitted network, trained to approximate Bayesian inference, which can make predictions on a new time series dataset in a single forward pass. Through extensive experiments, we show that zero-shot predictions made by ForecastPFN are more accurate and faster compared to state-of-the-art forecasting methods, even when the other methods are allowed to train on hundreds of additional in-distribution data points.