Demands placed on dissimilar metals joints have increased from various viewpoints, such as, environmental concerns, energy saving, high performance, cost saving and so on. The aim of this research is to predict and optimize laser welding of some economically important dissimilar materials in industry through applying a Taguchi orthogonal array design as a DOE approach to design the experiments, develop mathematical models and optimize the welding operation. This was achieved by controlling selected welding parameters; laser power, welding speed and focus position, to relate the mechanical properties, weld bead geometry, principal residual stress and unit operating cost to the selected input welding parameters. The dissimilar materials studied in this work are low carbon steel, 316 stainless steel, titanium G2, different types of aluminium alloys such as (6082, 5251H22 and 1050H24) with different thicknesses and different joint designs. For each dissimilar welded material, mathematical models were developed to predict the required responses. Moreover, the main effects and the interaction effects of the process parameters on the responses were discussed and presented graphically for all dissimilar materials and joint designs. Furthermore, the developed models were optimized by determining the best combinations of input process parameters in order to produce an excellent weld quality.