Leveraging the Strengths of Choice Models and Neural Networks: A Multiproduct Comparative Analysis*

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, we test two hypotheses: (i) choice models and neural network models are equal in performance, and (ii) hybrid models consisting of a combination of choice and neural network models perform better than each stand-alone model. We perform statistical tests for two classes of linear and nonlinear hybrid models and compute the empirical integrated rank (EIR) indices to compare the overall performances of the models.We test the above hypotheses by using data for various brand and store choices for three consumer products. Extensive jackknifing and out-of-sample tests for four different model specifications are applied for increasing the external validity of the results. Our results show that using neural networks has a higher probability of resulting in a better performance. Our findings also indicate that hybrid models outperform stand-alone models, in that using hybrid models guarantee overall results equal or better than the two stand-alone models. The improvement is particularly significant in cases where neither of the two stand-alone models is very accurate in prediction, indicating that the proposed hybrid models may capture aspects of predictive accuracy that neither stand-alone model is capable of on their own. Our results are particularly important in brand management and customer relationship management, indicating that multiple technologies and mixture of technologies may yield more accurate and reliable outcomes than individual ones.

A comparison between Fama and French's model and artificial neural networks in predicting the Chinese stock market

“…ANN has been successfully used in prediction or forecasting studies in all functional areas of business, including accounting [25], economics [26], ÿnance [27][28][29][30][31][32][33][34], management information systems [35], marketing [36], and production management [37]. In one comparative analysis study after another (see [38][39][40]) ANN consistently outperformed or is more accurate at predicting or forecasting than other more traditional quantitative methods.…”

The three-factor model and artificial neural networks: predicting stock price movement in China

“…ANN models have been successfully applied in a variety of business fields including accounting (Lenard et al 1995), economics (Hu et al 1999), finance (Etheridge et al 2000;Bruce and Michael 1998), management information systems (Zhu et al 2001), marketing (Papatla et al 2002;Thieme et al 2000), and production management (Kaparthi and Suresh 1994). Popular applications include a wide range of forecasting tasks, and the literature in this area is growing (see Zhang et al 1998).…”

A comparative predictive analysis of neural networks (NNs), nonlinear regression and classification and regression tree (CART) models

“…The idea behind combined (Hybrid) models is to derive advantages of individual model's best features to obtain the best possible results in a given problem/situation (Papatla, Zahedi, & Zezic-Susac, 2002;Mojirsheibani, 1999). The practice of mixing models (classifiers) is not new, and have also been suggested by Xu, Kryzak, and Suen (1992).…”

“…Results from these studies suggest that hybrid statistical models improve predictive performance when compared against the predictive performances of standalone models. The recent trend in hybrid model development is to mix classical statistical models with NNs models (Papatla et al, 2002). Papatla et al proposed two classes of hybrid models: linear and nonlinear.…”