search query: @indexterm EXPERT SYSTEMS / total: 141
reference: 17 / 141
| Author: | Callahan, J.D. Sorensen, S.W. |
| Title: | Rule induction for group decisions with statistical data - an example |
| Journal: | Journal of the Operational Research Society
1991 : MAR, VOL. 42:3, p. 227-234 |
| Index terms: | INDUCTION TRAINING KNOWLEDGE-BASED SYSTEMS EXPERT SYSTEMS DECISION MAKING |
| Language: | eng |
| Abstract: | Classification and regression trees /CART/ was found a reasonable analysis technique of deriving decision rules for an expert system that was desired for a group decision-making process. A highly variable data set from previous groups' decisions was available to simulate past group decisions. This data set has much missing information and contains many possible errors. Errors from Cart colutions were comparable to errors from a discriminant analysis and smaller than errors from multiple regression. Cart was found superior because it uses all information, it can classify observations with missing data, and because the resulting decision rules are easy to implement in an expert system. |
SCIMA