SWOT analysis, a commonly used tool for strategic planning, is traditionally a form of brainstorming. Hence, it has been criticised that it is likely to hold subjective views of the individuals who participate in a brainstorming session and that SWOT factors are not prioritized by their significance thus it may result in an improper strategic action.While most studies of SWOT analysis have only focused on solving these shortcomings separately, this study offers an approach to diminish both shortcomings by applying Importance-Performance Analysis (IPA) to identify SWOT based on customer satisfaction surveys which produces prioritized SWOT corresponding to the customers' perception. Through the use of IPA based SWOT analysis, it is expected that a organisation can efficiently formulate strategic planning as the SWOT factors that should be maintained or improved can be clearly identified based on customers' viewpoints. The application of the IPA based SWOT analysis was illustrated and evaluated through a case study of Higher Education Institutions in Thailand. The evaluation results showed that SWOT analysis of the case study accurately reflected the organisation s' situations thereby demonstrating the validity of this study.

Over the years, many different importance-performance analysis (IPA) variations have emerged as it is a primary tool for analyzing customer satisfaction. One of the recent IPA variations is back-propagation neural network based importance-performance analysis (BPNN based IPA) that utilizes BPNN to measure Importance. To investigate the performance of the BPNN based IPA, the authors compared two types of BPNN models that have one and multiple output neurons referred as BPNN (regression) and BPNN (classification) respectively, with multiple linear regression (MLR). This comparison demonstrates that the BPNN (regression) does not outperform MLR in term of model accuracy and training time, yet BPNN (classification) is superior to MLR and BPNN (regression) in term of model accuracy and predictive power. This finding leads to a reconsideration of the BPNN model used in the present BPNN based IPA.

Strengths, Weaknesses, Opportunities and Threats (SWOT) analysis is one of the most commonly used tools for strategic planning. It helps organizations gain a better insight of their internal and external business environment when making strategic plans and decisions. Although SWOT analysis has been widely accepted as a tool for strategic planning, the traditional method of conducting SWOT analysis does not prioritize and is likely to hold subjective views that may result in an improper strategic action. One way to make better use of the SWOT framework is to take the customer's perspective in to account which helps the companies to ensure that their perceived capabilities are also recognized and valued by their customer. This work proposes a combination of Back Propagation Neural Network based Importance-Performance Analysis (BPNN-IPA) and SWOT analysis. The 'Importance' is derived by applying BPNN on a customer satisfaction survey and 'Performance' is computed as the mean value of customer' s satisfaction rating. The intersection of these two components creates a two-dimensional matrix termed, IPA matrix, which can be identified as strengths and weaknesses of the company. Base on the same principle, opportunities and threats are obtained through the IPA matrix of the company's competitor. The BPNN-IPA yields significant improvement in estimating of attribute importance compared to conventional IPA and regression-based IPA approach, thereby generating effective SWOT analysis. It is expected that this approach will provide more accurate information for strategic planning as it generates prioritized SWOT factors based on the customer's perception.

No abstract