Research Article

Predicting Subcontractor Performance Using Web-Based Evolutionary Fuzzy Neural Networks

Table 1

Subcontractor performance historical records.

Pattern no.PerformanceInputOutput
Last 3Last 2Last 1Normalized performance

Input patterns
1807276760.8333
2867676800.8958
3748076760.7708
4707676740.7292
5685662660.7083
6666066680.6875
7667072680.6875
8586266600.6042
9566660580.5833
10807674760.8333
11867476800.8958
12887680860.9167
13768680800.7917
14706668660.7292
15706866700.7292
16766670700.7917
17746670760.7708
18767076740.7917
19807476760.8333
20666258620.6875
21685862660.7083
22767674760.7919

Test patterns
23666256600.6875
24685660660.7083
25666066680.6875
26666668660.6875
27706866660.7292
28766666700.7917
29746670760.7708
30767076740.7917
31767674760.7917
32807476760.8333
33867676800.8958
34887680860.9167

Note: Last 1 denotes the subcontractor’s latest performance, and so forth. Normalized performance is divided by 96.