Artificial neural network (ANN) based decision support model for alternative workplace arrangements (AWA): Readiness assessment and type selection

A growing body of evidence shows that globalization and advances in information and communication technology (ICT) have prompted a revolution in the way work is produced. One of the most notable changes is the establishment of the alternative workplace arrangement (AWA), in which workers have more freedom in their work hours and workplaces. As more and more businesses have begun to adopt AWA, the number of employees who are working away from a permanently assigned office space and those who are geographically and virtually distributed has been increasing throughout the world (Venezia et al., 2007).;The goal of this dissertation is to provide an understanding of the assessment of the initial readiness for AWA adoption and to develop a decision support model which can predict an appropriate AWA type and satisfaction level to assist the process of decision-making for AWA adoption from an organizational perspective. The specific objectives are: (1) To develop Readiness Level Assessment Indicators (RLAI) for assessing the extent of an organization's readiness for the adoption of an AWA. RLAIs can be used to predict the potential successfulness of AWA adoption from an organizational perspective and (2) Based on actual AWA adoption cases from high-tech companies, to develop an AWA decision model that allows decision makers to select an appropriate AWA type and predict the satisfaction level.;The hypothesis of this dissertation is that: A positive rank correlation exists between organizational readiness level for AWA adoption and organization's satisfaction with AWA. (Independent variables which can be used for measuring an organization's readiness level for AWA adoption and dependent variable which can be used for measuring the organization's satisfaction with AWA are described in detail in Chapter 4).;An extensive review of literature on a wide range of AWA issues is presented, and expert surveys are conducted to identify major business reasons, significant factors and relevant attributes. The findings from the review of the literature and an evaluation from the expert panel are combined to finalize the assessment indicators for developing RLAI. A total of 64 real adoption cases have been collected using RLAI from high-tech companies that have already adopted any of six AWA types: Hoteling, group address, shared office, satellite office, home office, and virtual office.;The predictive data mining techniques are reviewed since the main goal of predictive data mining is to identify a statistical or artificial neural network (ANN) model that can be used to predict the outcomes in business. Regression technique is abandoned for developing decision model because it is not very useful for small data samples, and it performs better for the output variables containing continuous data.;Additionally, two outputs, type selection (Y1) and satisfaction level (Y2) can not be investigated at the same time using the regression technique. The artificial neural network (ANN) technique is selected to develop a decision model, and the ANN-based decision model reliably suggests an AWA type and an anticipated satisfaction level given the objectives and the readiness level of high-tech companies. As for the first ANN model validation, predictive performance of the ANN model is evaluated by comparing the predicted outputs and the actual outputs in the testing sets. Additionally, as for the second validation, this research also adopts a case-based reasoning (CBR) technique to develop the second decision model. Predictive performances of the two decision models are compared. Consequently, it is validated that the ANN model is more effective and robust in predictive performance than the CBR model is.;This research resulted in the development of readiness level assessment indicators (RLAI), which measure the initial readiness of high-tech companies for adopting AWAs and the ANN based decision model, which allows decision makers to predict not only an appropriate AWA type, but also an anticipated satisfaction level considering the objectives and the current readiness level. This research has identified significant factors and relative attributes for decision makers to consider when measuring their organization's readiness for AWA adoption. Robust predictive performance of the ANN model shows that the main factors or key determinants have been correctly identified in RLAI and can be used to predict an appropriate AWA type as well as a high-tech company's satisfaction level regarding the AWA adoption. (Abstract shortened by UMI.)...