Heterogeneous Ensemble Learning for Enhanced Crash Forecasts -- A Frequentest and Machine Learning based Stacking Framework

TL;DR

This study demonstrates that a stacking ensemble method combining various machine learning models significantly improves crash frequency prediction accuracy on urban and suburban road segments compared to traditional statistical and individual machine learning models.

Contribution

The paper introduces a heterogeneous ensemble stacking framework for crash prediction, showing its superiority over traditional models and single ML techniques in accuracy and robustness.

Findings

Stacking outperforms Poisson, negative binomial, decision tree, random forest, and gradient boosting models.

Optimal weighting in stacking reduces bias from individual base learners.

Enhanced prediction accuracy can inform better traffic safety countermeasures.

Abstract

A variety of statistical and machine learning methods are used to model crash frequency on specific roadways with machine learning methods generally having a higher prediction accuracy. Recently, heterogeneous ensemble methods (HEM), including stacking, have emerged as more accurate and robust intelligent techniques and are often used to solve pattern recognition problems by providing more reliable and accurate predictions. In this study, we apply one of the key HEM methods, Stacking, to model crash frequency on five lane undivided segments (5T) of urban and suburban arterials. The prediction performance of Stacking is compared with parametric statistical models (Poisson and negative binomial) and three state of the art machine learning techniques (Decision tree, random forest, and gradient boosting), each of which is termed as the base learner. By employing an optimal weight scheme to combine individual base learners through stacking, the problem of biased predictions in individual base-learners due to differences in specifications and prediction accuracies is avoided. Data including crash, traffic, and roadway inventory were collected and integrated from 2013 to 2017. The data are split into training, validation, and testing datasets. Estimation results of statistical models reveal that besides other factors, crashes increase with density (number per mile) of different types of driveways. Comparison of out-of-sample predictions of various models confirms the superiority of Stacking over the alternative methods considered. From a practical standpoint, stacking can enhance prediction accuracy (compared to using only one base learner with a particular specification). When applied systemically, stacking can help identify more appropriate countermeasures.