A Predictive Integrated Genetic-Based Model for Supplier Evaluation and Selection

Abstract

Supplier evaluation and selection is a complicated multiple criteria decision-making process which affects supply chain management (SCM) directly. Recent studies emphasize that artificial intelligence approaches obtain better performance than conventional methods in evaluating the suppliers’ performance and determining the best suppliers. Hence, this study proposes a new robust genetic-based intelligent approach, namely gene expression programming (GEP), to improve the supplier selection process for a supply chain and to cope with the drawback of the other intelligent approaches in this area. The applicability of this method was exhibited by a case study in the textile manufacturing industry. To show the performance of the mathematical-genetic model, comparisons with four intelligent techniques, namely multi-layer perceptron (MLP) neural network, radial basis function (RBF) neural network, adaptive neuro-fuzzy inference system (ANFIS) and support vector machine (SVM), were performed. The results derived from the intelligent approaches were compared by using a collected dataset from a textile factory. The obtained results demonstrated that first the GEP-based model provides a mathematical model for the suppliers’ performance based on the determined criteria, and the developed GEP model is more accurate than the four other intelligent models in terms of accuracy in performance estimation. In addition, to verify the validity of the developed model, different statistical tests were used and the results showed that the GEP model is statistically powerful.

Appendix

Note that in the MATLAB codes, d(1),…d(6) are C, D, F, QM, S and TC, and in the C ++ codes, d(0),…, d(5) are C, D, F, QM, S and TC, respectively.

The MATLAB codes of the model:

Function result = gepModel(d)

G1C0 = −5.029235;

G1C1 = 8.91211;

G2C0 = −7.345825;

G2C1 = −1.151367;

G3C0 = −1.060913;

G3C1 = −4.018219;

G4C0 = −7.345825;

G4C1 = 2.207885;

varTemp = 0.0;

varTemp = (((d(1)/(exp(G1C0) + (d(1) + d(4))))^2)*d(2));

varTemp = varTemp + d(4);

varTemp = varTemp + exp((((d(6)−(d(2)^3))−(G3C0 + d(2)))−d(2)));

varTemp = varTemp + tan(((d(4) + (d(5)/d(3)))/G4C0));

result = varTemp;

The C ++ codes of the model:

double gepModel(double d[]);

double gepModel(double d[])

{

const double G1C0 = −5.029235;

const double G1C1 = 8.91211;

const double G2C0 = −7.345825;

const double G2C1 = −1.151367;

const double G3C0 = −1.060913;

const double G3C1 = −4.018219;

const double G4C0 = −7.345825;

const double G4C1 = 2.207885;

double dblTemp = 0.0;

dblTemp = (pow((d[0]/(exp(G1C0) + (d[0] + d[3]))),2)*d[1]);

dblTemp + = d[3];

dblTemp + = exp((((d[5]-pow(d[1],3))−(G3C0 + d[1]))−d[1]));

dblTemp + = tan(((d[3] + (d[4]/d[2]))/G4C0));

return dblTemp;

}