Identification of Working Trucks and Critical Path Nodes for Construction Waste Transportation Based on Electric Waybills: A Case Study of Shenzhen, China

Table 5

Results of parameter tuning with variations in max_depth and min_child_weight.

Number	Parameters	Mean_validation_score	Cv_validation_scores
0	{′max_depth′:3, ′min_child_weight′: 1}	0.90196681	[0.90126997 0.90266393]
1	{′max_depth′: 3, ′min_child_weight′: 2}	0.901761934	[0.90147481 0.90204918]
2	{′max_depth′: 3, ′min_child_weight′: 3}	0.90196681	[0.90106514 0.90286885]
3	{′max_depth′: 4, ′min_child_weight′: 1}	0.904118009	[0.90434248 0.90389344]
4	{′max_depth′: 4, ′min_child_weight′: 2}	0.903605818	[0.90311348 0.90409836]
5	{′max_depth′: 4, ′min_child_weight′: 3}	0.902581438	[0.90208931 0.90307377]
6	{′max_depth′: 5, ′min_child_weight′: 1}	0.903708257	[0.90434248 0.90307377]
7	{′max_depth′: 5, ′min_child_weight′: 2}	0.903196066	[0.90372798 0.90266393]
8	{′max_depth′: 5, ′min_child_weight′: 3}	0.902376562	[0.90229414 0.90245902]
9	{′max_depth′: 6, ′min_child_weight′: 1}	0.90299119	[0.90331831 0.90266393]
10	{′max_depth′: 6, ′min_child_weight′: 2}	0.902888752	[0.90290864 0.90286885]
11	{′max_depth′: 6, ′min_child_weight′: 3}	0.903093628	[0.90270381 0.90348361]