Fuzzy regression model based on geometric coordinate points distance and application to performance evaluation

In order to increase the explanatory performance of fuzzy regression model, the least square method usually is applied to determine the numeric coefficients based on the concept of distance. In this paper, we consider the fuzzy linear regression model with fuzzy input, fuzzy output and crisp parameters and combine centroid point and radius of gyration point for defuzzification from the viewpoint of geometric quality. A new distance is introduced based on the geometric coordinate points (GCP) of triangular fuzzy number. In order to estimate of regression coefficients, we merge least square method with the new GCP distance and propose least square GCP distance method. Finally, an example of employee job performance is given to illustrate the effective and feasibility of the method. Comparisons with existing methods show that total estimation error using the same distance criterion, the explanatory performance of the GCP method is satisfactory, and the calculation is relatively simple.