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

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.     

Developing an African research network and research agenda on work–family interface

In this article we aim to provide a narrative of the critical engagement on work–family issues in Africa that took place during the inaugural workshop of the African Research Network on Work–Family held at the University of Pretoria, South Africa in September 2015. The inter-disciplinary experts at the workshop agreed that with funding and appropriate local data, the Network has the potential to make a substantial contribution to strengthening and amplifying African voices in the global work–family discourse, which is currently dominated by research findings and literature from the Global North. A future research agenda was also proposed.     

Building Bridges into the Community: Social Capital in a Volunteering Project for Care Leavers

Volunteering to address poor life outcomes often experienced by care leavers is emphasised in UK policy. Although volunteering is credited with the ability to generate social capital, there is limited research on the impact of volunteering on the social capital of care leavers. This article re‐examines data from an evaluation of a volunteering project for care leavers. It explores in what ways young people's participation in the project constitutes social capital. The findings support the importance of regular face‐to‐face contact and co‐production for young people to become creators of their own social capital.