CAARL: In-Context Learning for Interpretable Co-Evolving Time Series Forecasting

TL;DR

CAARL introduces an interpretable, LLM-based framework for forecasting complex, coevolving time series by decomposing data into segments, constructing dependency graphs, and serializing reasoning paths for transparent predictions.

Contribution

The paper presents CAARL, a novel approach that combines time series decomposition with LLM reasoning to improve interpretability and accuracy in forecasting coevolving series.

Findings

CAARL achieves competitive forecasting accuracy on real-world datasets.

The method provides transparent reasoning paths for interpretability.

Experiments validate CAARL's effectiveness compared to state-of-the-art methods.

Abstract

In this paper we investigate forecasting coevolving time series that feature intricate dependencies and nonstationary dynamics by using an LLM Large Language Models approach We propose a novel modeling approach named ContextAware ARLLM CAARL that provides an interpretable framework to decode the contextual dynamics influencing changes in coevolving series CAARL decomposes time series into autoregressive segments constructs a temporal dependency graph and serializes this graph into a narrative to allow processing by LLM This design yields a chainofthoughtlike reasoning path where intermediate steps capture contextual dynamics and guide forecasts in a transparent manner By linking prediction to explicit reasoning traces CAARL enhances interpretability while maintaining accuracy Experiments on realworld datasets validate its effectiveness positioning CAARL as a competitive and interpretable alternative to stateoftheart forecasting methods