Modeling and evaluating the strategic effects of improvement programs on the manufacturing performance using neural networks

Selecting the most effective improvement programs is the main challenge of business managers to achieve superior operational performances. This paper, in an effort to develop new insights into practice-performance relationships, investigates improvement programs, strategic priorities, environmental factors, manufacturing performance dimensions and their interactions via a data mining approach. The results of implementing improvement programs in 91 Iranian small and medium sized companies were gathered by means of a questionnaire-based survey and an artificial neural network was trained to model the relationships between input and output variables. Using a series of regression analysis on the same data shows that the proposed model outperforms all estimated regression models. Also, to understand and evaluate the strength of strategic effects on performance dimensions, a sensitivity analysis method was conducted on the trained model which indicates that implementing a program may be supportive of some performance dimensions and simultaneously incompatible with the others. The results are aimed at providing guidance for decision makers using the prediction power of the proposed model to estimate performance changes before investment in implementing programs.