The electronic logging device mandate was implemented with the intention of keeping truck drivers in compliance with the hours of service regulations to reduce driver fatigue and trucking accidents. Two years after the electronic logging device mandate became law, there have not been many studies that use trucking operational data such as the newly available electronic logs to look for efficiency gain. Our team received six months newly available raw logging data. This paper aims to use different analysis techniques in machine learning on the raw electronic logging data to find areas of opportunity that can be used by management to control and improve driver utilization. The three significant factors that we investigated for on the amount of time a driver spends at each freight location are: the time of day the driver arrives at a shipper location, the impact from a specific location, and the frequency that the carrier visits a specific shipper. Each of the three factors were found to imply a statistically significant impact on the stop duration. This study shows the usefulness of using electronic logging data to identify the underlying factors on stop time so that managers can schedule truck drivers more efficiently. This will allow for higher driving hours during the day, which translates to higher income for the drivers. Since the raw electronic logging device data is readily available for all On The Road carriers, we hope to inspire further data analysis on electronic logging device data to help improve the lives of truck drivers.