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

Table 7

Results of parameter tuning with variations in subsample and colsample_bytree.

Number	Parameters	Mean_validation_score	Cv_validation_scores
0	{′colsample_bytree′: 0.7, ′subsample′: 0.7}	0.904322885	[0.90311348 0.90553279]
1	{′colsample_bytree′: 0.7, ′subsample′: 0.8}	0.903913133	[0.90249898 0.90532787]
2	{′colsample_bytree′: 0.7, ′subsample′: 0.9}	0.904322885	[0.90393281 0.90471311]
3	{′colsample_bytree′: 0.7, ′subsample′: 1}	0.903913133	[0.90352315 0.90430328]
4	{′colsample_bytree′: 0.8, ′subsample′: 0.7}	0.904322885	[0.90311348 0.90553279]
5	{′colsample_bytree′: 0.8, ′subsample′: 0.8}	0.903913133	[0.90249898 0.90532787]
6	{′colsample_bytree′: 0.8, ′subsample′: 0.9}	0.904322885	[0.90393281 0.90471311]
7	{′colsample_bytree′: 0.8, ′subsample′: 1}	0.903913133	[0.90352315 0.90430328]
8	{′colsample_bytree′: 0.9, ′subsample′: 0.7}	0.903810695	[0.90290864 0.90471311]
9	{′colsample_bytree′: 0.9, ′subsample′: 0.8}	0.903913133	[0.90372798 0.90409836]
10	{′colsample_bytree′: 0.9, ′subsample′: 0.9}	0.904732637	[0.90393281 0.90553279]
11	{′colsample_bytree′: 0.9, ′subsample′: 1}	0.90299119	[0.90311348 0.90286885]
12	{′colsample_bytree′: 1, ′subsample′: 0.7}	0.903810695	[0.90290864 0.90471311]
13	{′colsample_bytree′: 1, ′subsample′: 0.8}	0.904118009	[0.90434248 0.90389344]
14	{′colsample_bytree′: 1, ′subsample′: 0.9}	0.904732637	[0.90413765 0.90532787]
15	{′colsample_bytree′: 1, ′subsample′: 1}	0.903298504	[0.90393281 0.90266393]