Abstract
LED manufacturing has several production processes. At the end of each process, the operator of that process will perform simple test to verify whether the product is qualified to proceed with next step. After completion of the whole processes, the wafer acceptance test will be carried out for probing yield. If the probing yield is decreased, it indicates an error occurred at the front-end tools during operation, thereby affecting product output. In the past, engineers retrieve the data of wafer probing yield through MES system on their own. Only when the data shows declining yield, the engineers start to analyze the production information to rule out possible abnormal processes or tools. By doing so, it spends too much time and can’t accumulate experiences. The study will use Association Rule and Decision Tree in data mining techniques to solve the above problems based on a case study of a Taiwan LED manufacturer.