The Relevance of AWS Chronos: An Evaluation of Standard Methods for Time Series Forecasting with Limited Tuning
This work addresses the problem of time series forecasting for practitioners needing robust models with minimal tuning, though it is incremental as it evaluates an existing framework against standard benchmarks.
The study compared the transformer-based Chronos framework against traditional time series forecasting methods like ARIMA and Prophet, finding that Chronos outperforms for longer-term predictions and maintains accuracy with increased historical context, while traditional models degrade significantly.
A systematic comparison of Chronos, a transformer-based time series forecasting framework, against traditional approaches including ARIMA and Prophet. We evaluate these models across multiple time horizons and user categories, with a focus on the impact of historical context length. Our analysis reveals that while Chronos demonstrates superior performance for longer-term predictions and maintains accuracy with increased context, traditional models show significant degradation as context length increases. We find that prediction quality varies systematically between user classes, suggesting that underlying behavior patterns always influence model performance. This study provides a case for deploying Chronos in real-world applications where limited model tuning is feasible, especially in scenarios requiring longer prediction.