Travel Time Prediction using Tree-Based Ensembles

@inproceedings{Huang2020TravelTP,
  title={Travel Time Prediction using Tree-Based Ensembles},
  author={He Huang and Martin Pouls and Anne Meyer and Markus Pauly},
  booktitle={ICCL},
  year={2020}
}
In this paper, we consider the task of predicting travel times between two arbitrary points in an urban scenario. We view this problem from two temporal perspectives: long-term forecasting with a horizon of several days and short-term forecasting with a horizon of one hour. Both of these perspectives are relevant for planning tasks in the context of urban mobility and transportation services. We utilize tree-based ensemble methods that we train and evaluate on a dataset of taxi trip records… 

Machine Learning Based Short-Term Travel Time Prediction: Numerical Results and Comparative Analyses

TLDR
Numerical results suggest that RF can achieve a better prediction performance result than any of the other methods not only in accuracy but also with stability.

Travel Time Prediction and Route Performance Analysis in BRTS based on Sparse GPS Data

TLDR
Alongside improving the experience of commuters, the proposed XGB-based TTP method also improves the estimation of intersection crossing time (ICT), which potentially leads to efficient traffic policy making.

A Travel Time Prediction by Applying Ensemble Machine Learning Techniques

TLDR
The proposed model divides the prediction work into two parts by first forecasting the clusters of the two step clustering model and then forecast the tendency of forecast using the ARIMA and XGBoost model for the linear and the non-linear segments.

Travel Time Prediction Using Hybridized Deep Feature Space and Machine Learning Based Heterogeneous Ensemble

Travel Time Prediction (TTP) has become an essential service that people use in daily commutes. With the precise TTP, individuals, logistic companies, and transport authorities can better manage

Predicting Taxi Travel Time Using Machine Learning Techniques Considering Weekend and Holidays

  • Bholanath RoyD. Rout
  • Computer Science
    Proceedings of the 13th International Conference on Soft Computing and Pattern Recognition (SoCPaR 2021)
  • 2022

Machine Learning for Multi-Output Regression: When should a holistic multivariate approach be preferred over separate univariate ones?

TLDR
This work compares tree-based ensembles used for predicting univariate responses in extensive simulations to help in answering the primary question when to use multivariate ensemble techniques.

References

SHOWING 1-10 OF 29 REFERENCES

On Limits of Travel Time Predictions: Insights from a New York City Case Study

TLDR
A simple travel-time predictor is demonstrated, whose error approaches the uncertainty bound, that predicts delay based only on total distance traveled and time-of-day and is close to the optimal solution.

Long-term travel time prediction using gradient boosting

TLDR
This paper introduces key variables, regarded as multiple factors, from various sources into a Gradient boosting model and applies the Fourier filtering process to reduce noise, and demonstrates that the prediction ability of the GB model with Fouriers filtering is the best.

Travel time prediction with LSTM neural network

  • Y. DuanYisheng LvFeiyue Wang
  • Computer Science, Business
    2016 IEEE 19th International Conference on Intelligent Transportation Systems (ITSC)
  • 2016
TLDR
A deep learning model, the LSTM neural network model, is explored for travel time prediction by employing the travel time data provided by Highways England and obtains the optimal structure within the setting range for each link.

Dynamic multi-interval bus travel time prediction using bus transit data

TLDR
A dynamic model to forecast multi-interval path travel times between bus stops of origin and destination based on the Nearest Neighbour Non-Parametric Regression using historical and current data collected by the Automatic Vehicle Location technology is developed.

Prediction of Bus Travel Time Using Random Forests Based on Near Neighbors

TLDR
The random forests based on the near neighbor (RFNN) method is proposed in this article to predict bus travel time, which has been calibrated and validated with real‐world data and indicates that the proposed model achieves high accuracy.

Research on Travel Time Prediction Model of Freeway Based on Gradient Boosting Decision Tree

TLDR
Compared with the back propagation neural network model and the support vector machine model, the proposed GBDT model can produce more accurate prediction results, especially in multi-step prediction, indicating that GBDT is a promising method in travel time prediction.

Travel-time prediction with support vector regression

TLDR
The feasibility of applying SVR in travel-time prediction is demonstrated and it is proved that SVR is applicable and performs well for traffic data analysis.

Modeling of Travel Time Variations on Urban Links in London

TLDR
The results indicate that nonlinear latent variable regression models can effectively explain travel time variations on a regular day by using variables related to vehicle type, traffic density, and traffic composition.