search query: @indexterm Neural networks / total: 121
reference: 26 / 121
| Author: | Papatla, P. Zahedi, M. Zekic-Susac, M. |
| Title: | Leveraging the strengths of choice models and neural networks: a multiproduct comparative analysis |
| Journal: | Decision Sciences
2002 : SUMMER, VOL. 33:3, p. 433-468 |
| Index terms: | Artificial intelligence Brand choice Choice theory Models Neural networks |
| Language: | eng |
| Abstract: | Choice models and neural networks are two approaches used in modeling selection decisions. Defining model performance as the out-of-sample prediction power of a model, the authors test two hypotheses: 1) choice models and neural network models are equal in performance, and 2) hybrid models consisting of a combination of choice and neural network models perform better than each stand-alone model. The authors perform statistical tests for two classes of linear and nonlinear hybrid models and compute the empirical integrated rank (EIR) indicies to compare the overall performances of the models. |
SCIMA