TimeGPT vs TiDE: Is Zero-Shot Inference the Future of Forecasting or Just Hype?

#TimeGPT #TiDE #ZeroShot #Inference #Future #Forecasting #Hype

Foundational models: A comprehensive comparison of TimeGPT and TiDE in time series forecasting

Luís Roque
Towards Data Science

This post was co-authored with Rafael Guedes.

Forecasting is one of the core domains of Artificial Intelligence (AI) in academic research and industrial applications. In fact, it is probably one of the most ubiquitous challenges we can find across all industries. Accurately predicting future sales volumes and market trends is essential for businesses to optimize their planning processes. This includes enhancing contribution margins, minimizing waste, ensuring adequate inventory levels, optimizing the supply chain, and improving decision-making overall.

Developing a forecast model represents a complex and multifaceted challenge. It requires a deep understanding of State-Of-The-Art (SOTA) forecasting methodologies and the specific business domain to which they are applied. Furthermore, the forecast engine will act as a critical infrastructure within an organization, supporting a broad spectrum of processes across various departments. For instance:

  • The Marketing team leverages the model to inform strategic decisions regarding investment allocations for upcoming periods, such as the next month or quarter.
  • The Procurement team utilizes the model to make informed decisions about purchase quantities and timing from suppliers, optimizing inventory levels and reducing waste or shortages.
  • The Operations team uses the forecasts to optimize the production lines. They can deploy resources and workforce to meet expected demand while minimizing operational costs.
  • The Finance team relies on the model for budgeting purposes, using forecast data to project monthly financial requirements and allocate resources accordingly.
  • The Customer Service team uses the forecast to anticipate customer inquiry volumes, allowing the team to right-size staffing levels while ensuring high-quality customer service and minimizing wait times.

Recent advancements in forecasting have also been shaped by the successful development of foundational models across various domains, including text (e.g., ChatGPT), text-to-image (e.g., Midjourney), and text-to-speech (e.g., Eleven Labs). The wide…