Designing an Integrative Model for Evaluation and Selection of Six Sigma Projects Using Artificial Neural Networks

Six sigma is one of the most popular tools to eliminate waste in organizations, reduce the cost and improve quality. The process of creating and evaluating projects is an initial activity in implementing six sigma. This paper aims at proposing a comprehensive methodology for the evaluation and selection of the six sigma projects based on level of sigma and productivity. So, this research provides the identification of important inputs and outputs for six sigma projects that are then analyzed using Artificial Neural Networks which are capable to consider non-liner interrelations among criteria. In order to evaluate the projects, six criteria have been identified. For deriving the overall utility of projects, we designed an adaptive two neural networks with 6 inputs and one output and multilayer perceptron with 5 and 4 hidden layers for forecasting production and level of sigma respectively. Finally, we use sensitive analysis for identification effect of every inputs on outputs.