Dynamic Differential Pricing of High-Speed Railway Based on Improved GBDT Train Classification and Bootstrap Time Node Determination

Jing, Yun; Guo, Siye; Chen, Fangqiu; Wang, Xuan; Li, Kaixuan

doi:10.1109/tits.2021.3106042

Cited by 10 publications

(4 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Su et al [17] built an optimization model for train ticket pricing decision variables based on a timedependent demand model and a passenger allocation method considering departure time and capacity constraints. Jing [18] constructed a dynamic simulation mechanism and dynamic differential pricing solution framework for passenger selection under differential pricing conditions based on an improved machine learning gradient boosting decision tree model. Wang et al [19] applied dynamic pricing to the pricing for refund service fees, dynamically charging for refunds based on the expected revenue produced by each ticket cancellation behavior, in order to compensate for the losses as much as possible.…”

Section: Literature Reviewmentioning

confidence: 99%

Pricing Analysis for Railway Multi-Ride Tickets: An Optimization Approach for Uncertain Demand within an Agreed Time Limit

Wang,

Zhu

2023

Mathematics

View full text Add to dashboard Cite

A multi-ride ticket with a certain period of validity and maximum number of uses has been introduced into railway transport. The key to pricing the railway multi-ride ticket is determining the uncertain demand within an agreed time limit. Unfortunately, limited studies have focused on this pricing issue. Therefore, we focused on railway multi-ride ticket pricing optimization in two different scenarios: a single train with multiple stops and multiple trains with multiple stops. First, the expected coefficient and incentive coefficient were introduced to describe the decision-making process for multi-ride tickets and simulate the change in passengers’ travel behavior after purchasing multi-ride tickets. Then, passenger demand functions based on a normal distribution were developed to establish the pricing models with maximized revenue. Finally, we adopted improved particle swarm optimization (PSO) to solve the models. Two numerical cases were used to verify the models separately for two application scenarios. The results revealed that the multi-ride ticket pricing problem is not a simple summation of pricing for one-time travel of passengers. In the situation of a single train with multiple stops, the expected coefficient is positively related to the total income, whereas the incentive coefficient has limited influence on the optimal price and total revenue. Furthermore, a multi-ride ticket should allow the passenger to take trains eight times at most in 8 days at the price of CNY 4922 (abbreviated as 4922 (8, 8)) rather than 3785 (8, 6). Railway enterprises should cautiously limit the scope of trains available for multi-ride tickets in the case of multiple trains with multiple stops.

show abstract

Section: Literature Reviewmentioning

confidence: 99%

Pricing Analysis for Railway Multi-Ride Tickets: An Optimization Approach for Uncertain Demand within an Agreed Time Limit

Wang,

Zhu

2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…Du et al used the combined model of XGBoost and LSTM in the short-term traffic prediction of the base station [20]. Yun et al built a local optimal fusion model based on LSTM, LightGBM, and dynamic regression device [21]. Wang et al took Multivariable Linear Regression (MLR), K-Nearest Neighbor (KNN), XGBoost, and Gated Recurrent Unit (GRU) as four seed models to establish a regression integration model to accurately predict short-term passenger flows of urban public transport [22].…”

Section: Research On Xgboost Modelmentioning

confidence: 99%

XGBoost-Based Travel Time Prediction between Bus Stations and Analysis of Influencing Factors

Zhu

Zou

2022

Wireless Communications and Mobile Computing

View full text Add to dashboard Cite

Real-time and accurate travel time information between bus stations is critical for passengers to make suitable travel plans to reduce waiting time at the stops. By mining and analyzing bus operational data, it can be obtained that factors such as the variation of vehicle speed in adjacent sections and the proportion of bus lanes between stations have affected the travel time between bus stations. Therefore, considering the temporal feature, spatial feature, and weather feature as the prediction model’s input, travel time between bus stations prediction model based on eXtreme Gradient Boosting (XGBoost) was trained and established. The 28-day bus operation data of a certain bus line in Guangzhou was used for training and verification, and they were compared with the prediction models based on K -Nearest Neighbors (KNN), BP neural network, and Light Gradient Boosting Machine (LightGBM). In comparison with other models, the lowest MAPE of 11.96% was found for the XGBoost prediction model, which is 9.30% lower than other models on average. The sensitivity analysis of the proposed prediction model was further conducted: temporally, the accuracy of the prediction model was best during the flat peak hours; spatially, the MAPE of the model gradually decreased as the number of line units increased, and when the number of line units exceeded 18, the accuracy of the prediction model stabilized and was lower than 7%. The results confirm that the XGBoost model outperforms the KNN, BP, and LightGBM in terms of fitting, accuracy, and stability.

show abstract

“…The advantage of this algorithm is that it has high accuracy and is not easy to overfit, and it has achieved good results on learning tasks such as multiclassification, prediction and ranking. To obtain high accuracy, the GBDT method needs to traverse all data for each split point of each feature to calculate the information gain, i.e., each iteration needs to traverse all data several times, and the computational complexity will be affected by both the amount of data and the number of features, which makes it difficult for the GBDT method to meet the computational requirements in the face of high-dimensional features and a large amount of data [33].…”

Section: A Light Gradient Boosting Machinementioning

confidence: 99%

An Expressway Driving Stress Prediction Model Based on Vehicle, Road and Environment Features

Zhong

Lü³

et al. 2022

IEEE Access

View full text Add to dashboard Cite

Driving stress is the demand for reserved cognitive space after a driver perceives changes in vehicle, road and environmental factors during driving, which has been proven to affect driving behaviour, interfering with driving safety. Traditional stress prediction relies extensively on psychological data and is limited by the unpopularity of psychological data collection technology, which cannot be applied in daily life on a large scale. In recent years, advances in high-precision visual analysis technology represented by deep learning have laid the foundation for automated and large-scale visual environment analysis. This study proposes a framework for the quantitative analysis of highway driving stress based on multiple vehicle, road, and environmental factors. A dilated residual network model and other methods were used to extract visual environmental indexes. Combined with multisource data such as traffic volume and road design parameters, the LightGBM method was used to construct an expressway driving stress prediction model with high accuracy. The MAE, RMSE and R 2 values of the proposed model are 0.042, 0.004 and 0.881, respectively, demonstrating the usefulness for scaled and efficient assessment of expressway stress loads. The SHAP method was used to explore the relationship between different influencing factors and driving stress to quantify the mechanism of vehicle, road and environment influences on stress load, and to propose recommendations for highway design and planning from the perspective of reducing stress load. This study provides a new way of thinking to quantitatively investigate the link between multiple road traffic factors and driving stress, providing efficient and large-scale assessment of expressway driving stress, as well as proposing some suggestions for highway design and planning to enhance stress reduction.INDEX TERMS Expressway, prediction model, driving stress, LightGBM method, SHAP method.

show abstract

Dynamic Differential Pricing of High-Speed Railway Based on Improved GBDT Train Classification and Bootstrap Time Node Determination

Cited by 10 publications

References 21 publications

Pricing Analysis for Railway Multi-Ride Tickets: An Optimization Approach for Uncertain Demand within an Agreed Time Limit

Pricing Analysis for Railway Multi-Ride Tickets: An Optimization Approach for Uncertain Demand within an Agreed Time Limit

XGBoost-Based Travel Time Prediction between Bus Stations and Analysis of Influencing Factors

An Expressway Driving Stress Prediction Model Based on Vehicle, Road and Environment Features

Contact Info

Product

Resources

About