2022
DOI: 10.1016/j.tbs.2022.07.003
|View full text |Cite
|
Sign up to set email alerts
|

Predicting the travel mode choice with interpretable machine learning techniques: A comparative study

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
1
1
1

Citation Types

0
25
2

Year Published

2022
2022
2024
2024

Publication Types

Select...
8
1

Relationship

0
9

Authors

Journals

citations
Cited by 63 publications
(27 citation statements)
references
References 78 publications
0
25
2
Order By: Relevance
“…Concerning recent studies that employed optimized models to predict general mode choice, the present study achieved better results than those of. Kashifi et al [59] who used EDT and SDT.…”
Section: Results and Discussion A Development And Evaluation Of The O...mentioning
confidence: 99%
“…Concerning recent studies that employed optimized models to predict general mode choice, the present study achieved better results than those of. Kashifi et al [59] who used EDT and SDT.…”
Section: Results and Discussion A Development And Evaluation Of The O...mentioning
confidence: 99%
“…Based on the randomness, the model has good flexibility and generalization ability, which can eliminate the overfitting of the data to a certain extent and reduce the mean square error. Compared with traditional statistical models, although the random forest model cannot generate t-statistics, p-values and other significant indicators [ 48 ], this algorithm is more inclusive to the endogenous problems of variables [ 49 ]. The algorithm has the advantages of non-parametric characteristics, high accuracy, can handle high-dimensional data and large data sets, and can also evaluate the relative importance of feature variables.…”
Section: Methodsmentioning
confidence: 99%
“…This technique has been used extensively in traffic safety studies, including crash injury prediction, to better interpret risk factors ( 45 , 46 ). In recent years, SHAP has also been used to estimate and interpret transportation mode preferences from a variety of data sources, including smart cards and travel surveys ( 47 , 48 ).…”
Section: Literature Reviewmentioning
confidence: 99%