Diagnostic and forecasting methods feed back in very direct ways to decision-making environments. Knowing what determines the past, as well as what gives good predictions for the future, gives decision makers better information for making optimal decisions over time. Until recently, most of the control or decision-making analysis has been based on linear dynamic models with normal or log-normal distributions. Of course, when we let go of normality, we must get our hands dirty in numerical approximation, and can no longer plug numbers into quick formulae based on normal distributions, but there are clear returns from this extra effort. we can go beyond linearity and normality in our assumptions with the use of neural networks. Business and financial decision makers now have available the computatioanl power and methods for more accurate diagnostics, forecasting, and control in volatile, increasingly complex, multidimensional environments. Researchers need no longer confine theselves to linear or loglinear models. Supervisor:- Dr. AttiyaYasmeen Javaid