ForecastPFN: Synthetically-Trained Zero-Shot Forecasting

Samuel Dooley, Gurnoor Singh Khurana, Chirag Mohapatra, Siddartha Venkat Naidu, Colin White

Keywords: Forecasting, Zero-shot, Synthetic Data

TL;DR: We design the first synthetically-trained zero-shot forecasting model, which can outperform state-of-the-art approaches even without seeing training data.

Abstract: 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.

Submission Number: 82