A Neural Network-Based Approach to Multi-Attribute Group Decision-Making with Heterogeneous Preference Information

Table 12

Comparison based on expert e¹’s decision information.

Methods	Attribute weights	Consider attribute values?	Consider experts’ preference Information?	Both attribute values and experts’ preference	Overall values of alternatives
Maximum deviation method	= 0.2319; = 0.2503; = 0.2473; = 0.2705	consider	Not consider	ONLY consider attribute values	Need calculate
Neural network approach	= 0.2384; = 0.3516; = 0.1159; = 0.2941	consider	consider	Both	Neural network outputs