Travel Time Prediction and Explanation with Spatio-Temporal Features: A Comparative Study
, Vahideh Reshadat 3, A. S. M. Kayes 4,*, Willem-Jan van den Heuvel 1,2 and Damian A. Tamburri 1,3
Round 1
Reviewer 1 Report
The manuscript is a novel contribution to travel-time prediction. The authors use three data sets, and compare three types of travel-time prediction methods within the framework of a comparative analysis. Following minor revisions must be considered.Although the paper has appropriate length and informative content, several parts must be improved and written in better grammar and syntax.
It would be essential if authors would consider revising the organization and composition of the manuscript, in terms of the definition/justification of the objectives, description of the method, the accomplishment of the objective, and results.
The paper is generally difficult to follow. Paragraphs and sentences are not well connected. Furthermore, I advise considering using standard keywords to better present the research. improve the keywords to ML/DL methods, also use the standard keywords.
Please revise the abstract according to the journal guideline. It must be under 200 words. The research question, method, and the results must be briefly communicated. The abstract must be more informative.
I suggest having four paragraphs in the introduction for; describing the concept, research gap, contribution, and the organization of the paper. The motivation has the potential to be more elaborated. You may add materials on why doing this research is essential, and what this article would add to the current knowledge, etc.
Elaborate on the XGBoost and LightGBM implementation and their descriptions with extra reference/citations.
The originality of the paper is not discussed well. The research question must be clearly given in the introduction, in addition to some words on the testable hypothesis. Please elaborate on the importance of this work. Please discuss if the paper suitable for broad international interest and applications or better suited for the local application? Elaborate and discuss this in the introduction.
State of the art needs improvement. A detailed description of the cited references is essential. Several recently published papers are not included in the review section. In fact, the acknowledgment of the past related work by others, in the reference list, is not sufficient. Further reading on XGboost include: Modeling hydrogen solubility in hydrocarbons using extreme gradient boosting and equations of state, and, "Hybrid XGboost model with various Bayesian hyperparameter optimization algorithms for flood hazard susceptibility modeling". Consequently, the contribution of the paper can be clear. Furthermore, consider elaborating on the suitability of the paper and relevance to the journal. Kindly note that references cited must be up to date.
Elaborate on the method used and why used this method.
Limitations and validation are not discussed adequately. The research question and hypothesis must be answered and discussed clearly in the discussion and conclusions. Please communicate the future research. The lessons learned must be further elaborated in the conclusion by discussing the results to the community and the future impacts. What is your perspective on future research?
Author Response
Please see the attachment.
Author Response File: 
Author Response.pdf
Reviewer 2 Report
In this paper, travel time prediction in the logistic industry for improving the delivery time are explored. Overall, the authors have carried out a lot of exploratory research. However, there are some problems for improvement by authors. Some specific suggestions and comments are as follows.
(1) Only data-driven methods are used to predict travel time. Why are model-based methods not used? The model-based methods may be better.
(2) Do the authors consider developing a more optimized model? Otherwise, it is difficult for us to evaluate the academic contribution of the authors.
(3) Data used in the paper: Are logistics companies' data representative?
(4) line 182: What is the basis for the division of the three data sets (60% training, 20% validation, and 20% test)?
(5) Table 4 and Figure 3 express similar content, and I suggest keeping only one.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Reviewer 3 Report
The paper considers an important practical problem: Travel-time prediction (TTP) that can help to predict and explain travel time in the logistics domain. The paper empirically evaluates many different TTP models and predictive algorithms over three different data sets.
Predictive methods are evaluated using the standard machine learning
performance measurement metrics for regression problems: MAE, R2 score, RMSE.
Explanations are provided by SHAP and LIME, visualized using different plots.
The paper is clear and well-constructed.
The literature is up-to-date and relevant to the analyzed problem.
Author Response
Please see the attachment.
Author Response File: Author Response.pdf
Round 2
Reviewer 2 Report
The authors have responded to my questions seriously. I would like to see the paper published.
