A Machine Learning-based Approach for Failure Prediction at Cell Level based on Wafer Acceptance Test Parameters

Wafer Acceptance Test (WAT) or commonly known as Process Control Monitoring (PCM) includes numerous testing items that have many important applications, such as yield improvement and production cost control. The prediction of wafer yield based on WAT parameters has been successfully employed to reduce production costs spent on the circuit probing process. However, the relationship between WAT and subsequent diagnosis reports has not been sufficiently explored yet. This paper proposes a learning-based framework for failure prediction at cell level from WAT data, including various techniques for feature selection and handling imbalanced classes. Based on the selected parameters, machine learning models are employed to predict the failure of a given cell. The potential of the proposed methodology is evaluated over a set of industrial data. Experimental results demonstrate that our methodology can provide accurate test predictions (0.95+ accuracy, F1-score, and Area Under the Receiver Operating Characteristic curve (AUCROC)).