Developing an integrated model for evaluation and selection of six sigma projects using ANN

Abstract

Six Sigma is one of the most popular systems for eliminating waste, reducing cost and improving quality in organizations. The process of evaluation and selection of projects is the first step towards implementing Six Sigma and many researchers believe that these are important for the success of such projects. Respectively, in this paper, a model has been proposed based on artificial neural network (ANN) as an effective tool for non-linear information processing . In this model, six criteria of project cost, project duration, number of Black and Green Belts, improving customer satisfaction, impact on business strategy and financial impact have been identified as input factors and productivity and sigma level of improvement projects have been estimated using multi-layer perception (MLP). Finally, sensitivity analysis has been used for evaluation of the influence of inputs on outputs. The findings imply that 'business strategy' and 'financial impact' have the most and the least influence on model's outputs, including productivity and Sigma level, respectively. .

Keywords

• Six Sigma
• Improvement projects
• Artificial Neural Network (ANN)
• Multi-Layer Perceptron (MLP)
• Sensitivity analysis