Zero-Shot Learning for Obsolescence Risk Forecasting
This addresses the challenge of obsolescence forecasting for industries reliant on electronic components, but it is incremental as it applies existing ZSL and LLM methods to a new domain-specific problem.
The paper tackles the problem of predicting component obsolescence risk in industries using electronic components by proposing a zero-shot learning approach with large language models to overcome data limitations, demonstrating effective prediction on two real-world datasets.
Component obsolescence poses significant challenges in industries reliant on electronic components, causing increased costs and disruptions in the security and availability of systems. Accurate obsolescence risk prediction is essential but hindered by a lack of reliable data. This paper proposes a novel approach to forecasting obsolescence risk using zero-shot learning (ZSL) with large language models (LLMs) to address data limitations by leveraging domain-specific knowledge from tabular datasets. Applied to two real-world datasets, the method demonstrates effective risk prediction. A comparative evaluation of four LLMs underscores the importance of selecting the right model for specific forecasting tasks.