Can we Estimate Truck Accident Risk from Telemetric Data using Machine Learning?
This addresses the problem of reducing societal costs from road accidents for transportation companies, but the result is negative and incremental as it highlights challenges in using telemetric data for risk prediction.
The study investigated whether telemetric data from long-distance trucks could predict driver accident risk using machine learning, but found that both Random Forests with FRESH features and convolutional neural networks failed to estimate risk successfully on a dataset of 1,141 drivers over 18 months.
Road accidents have a high societal cost that could be reduced through improved risk predictions using machine learning. This study investigates whether telemetric data collected on long-distance trucks can be used to predict the risk of accidents associated with a driver. We use a dataset provided by a truck transportation company containing the driving data of 1,141 drivers for 18 months. We evaluate two different machine learning approaches to perform this task. In the first approach, features are extracted from the time series data using the FRESH algorithm and then used to estimate the risk using Random Forests. In the second approach, we use a convolutional neural network to directly estimate the risk from the time-series data. We find that neither approach is able to successfully estimate the risk of accidents on this dataset, in spite of many methodological attempts. We discuss the difficulties of using telemetric data for the estimation of the risk of accidents that could explain this negative result.