@misc{cogprints2891,
           title = {Data Engineering for the Analysis of Semiconductor Manufacturing Data},
          author = {Peter Turney},
            year = {1995},
           pages = {50--59},
             url = {http://cogprints.org/2891/},
        abstract = {We have analyzed manufacturing data from several different semiconductor 
manufacturing plants, using decision tree induction software called 
Q-YIELD. The software generates rules for predicting when a given product 
should be rejected. The rules are intended to help the process engineers 
improve the yield of the product, by helping them to discover the causes 
of rejection. Experience with Q-YIELD has taught us the importance of 
data engineering -- preprocessing the data to enable or facilitate 
decision tree induction. This paper discusses some of the data engineering
problems we have encountered with semiconductor manufacturing data.
The paper deals with two broad classes of problems: engineering the features 
in a feature vector representation and engineering the definition of the 
target concept (the classes). Manufacturing process data present special 
problems for feature engineering, since the data have multiple levels of 
granularity (detail, resolution). Engineering the target concept is important, 
due to our focus on understanding the past, as opposed to the more common 
focus in machine learning on predicting the future.}
}

<script src="//archive-bar.soton.ac.uk/archive-bar.js"></script>