Predicting arterial breakdown probability: A data mining approach

Predicting the probability of traffic breakdown can be used as an important input for creating advanced traffic management strategies that are specifically implemented to reduce this probability. However, most, if not all, past research on the probability of breakdown has focused on freeways. This study focuses on the prediction of arterial breakdown probability based on archived traffic data for use in real-time transportation system operations. The breakdown of an arterial segment is defined in this study as a segment's operating condition under the level of service F according to the highway capacity manual threshold, although any other level of service could be used. Data from point detection and automatic vehicle identification matching technologies are aggregated in space and time to allow their use as inputs to the prediction model. A decision tree approach, combined with binary logistic regression, is used in this study to predict the breakdown probability based on these inputs. The model is validated using data not used in the development of the model. The research shows that the root mean square error and the mean absolute error of the prediction was 13.6 and 11%, respectively. The analysis also shows that the best set of parameters used in the prediction can be different for different links, due to the various causes of breakdown and characteristics of different links. Predicting the probability of breakdown in ahead of time will allow the agencies to change the signal-timing plan that can delay or eliminate the breakdown.