Long-Distance Travel Demand Modeling Through Rare Event Modeling Approach
Long-distance (LD) or intercity travel is getting less attention by researchers than usual daily trips. There is no specific definition for this kind of trip at the national, provincial, and inter-regional levels. At the same time, it has a high contribution to transportation in terms of distance travelled. This paper presents a model comparison method for (LD) trip generation model for LD trips performed by residents of Canada. The terms of "long-distance" trip based on Travel Survey for Residents in Canada (TSRC) survey is considered as non-frequent overnight and day trip. This study compared several machine learning methods for the trip generation model. Since LD trip is relatively rare, the data set of TSRC is considered imbalanced data, three different techniques on the data preparation level as part of rare event modelling (over, under, and synthetically oversampling) employed to handle the issue of imbalanced data. TSRC data from 2012 to 2017 was used for model estimation.Among the random forest, CART, CTree, and logit models, it was found that the random forest has the best performance in prediction, and decision tree models have the best overall accuracy. Also, Income level and educational level play an essential role in the occurrence of an intercity trip. The paper highlights the importance of improvement in intercity travel survey methods and other data collection methods
Year of publication: |
[2022]
|
---|---|
Authors: | Alizadeh, Hamed ; Morency, Catherine ; TRÉPANIER, Martin |
Publisher: |
[S.l.] : SSRN |
Saved in:
freely available
Saved in favorites
Similar items by person
-
Nazem, Mohsen, (2015)
-
Páez, Antonio, (2011)
-
Walking to transit: An unexpected source of physical activity
Morency, Catherine, (2011)
- More ...