ForecastPFN: Synthetically-Trained Zero-Shot Forecasting

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 commerc...

Full description

Saved in:
Bibliographic Details
Published in:arXiv.org 2023-11
Main Authors: Dooley, Samuel, Gurnoor Singh Khurana, Mohapatra, Chirag, Naidu, Siddartha, White, Colin
Format: Article
Language:English
Subjects:
Bayesian analysis
Data points
Datasets
Forecasting
Statistical inference
Synthetic data
Time series
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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.
ISSN:2331-8422