SmartAnalytics AI-Powered Software Improves Fleet Safety and Driver Behavior

SmartWitness is launching SmartAnalytics, its new analytics software powered by artificial intelligence (AI) and machine learning to provide better insights and actionable data for fleet managers.

The UK launch of SmartAnalytics follows a successful pilot scheme in the United States involving 10,000 trucks, which brought about a 15% average reduction in vehicle accidents, 30% increase in efficiency and productivity, and a 7% reduction in fuel and maintenance costs.

SmartAnalytics is a software upgrade to any SmartWitness video telematics solution that encompasses broader sources of data, simplifies fleet management, and lowers risk. With the use of artificial intelligence and machine learning, large amounts of data are processed and contextualized to create a better understanding of driver behavior in any fleet.

The AI software requires little to no human intervention and can process large amounts of data to provide the context and insights that fleet managers need to make better business decisions, reduce costs, improve driver safety, and run their operation more efficiently.

SmartWitness VP Aaron Kim said: “Fleet managers are currently facing a significant data overload. With the myriad number of connected devices on trucks plus the various compliance, regulatory and business intelligence software, there is simply too much data to be processed by organizations.

SmartAnalytics boils down thousands of hours of drive data each week into reports and league tables, which can be quickly and easily read. Only relevant videos are shared with fleet managers to act upon.

As well as cutting down hours of manual checking of data, the AI algorithm reduces false positives via improved contextual analysis. For example, if a driver triggered a harsh acceleration event, that would show up as negative feedback for their behavior. But in the case this event was triggered by entering a freeway, this behavior should actually be considered “safe” as a necessary maneuver to enter the flow of faster-moving traffic. This is the value of an increased number of contextual data sources, and unlike traditional telematics software that just use two key data sources, G-sensor and GPS, Smart Analytics is able to take into account factors such as road type, elevation, weather conditions, traffic patterns, and differentiate between city and rural traffic density.

How the SmartAnalytics Data Filtering Funnel Works

Data – G-sensor, GPS are the start points just as with standard telematics, but SmartAnalytics also includes weather conditions, traffic patterns and density, road type, and elevation.

The AI Filter – scrubs, cleans, and filters the raw data and eliminates false positives by analyzing and comparing with our sources.

The Machine Learning Filter – identifies trends and patterns in driver behavior, compares risk across your fleet, and creates league tables. Over time, with the comparison of historical information, the identification of events becomes even more accurate and predictive risk modelling assigns priority around the most at-risk drivers.

Relevant Actionable Data - The delivery of concise and easy to digest league tables becomes the first stage at which a fleet manager becomes involved. At this point in the funnel, they are receiving relevant actionable insights that can then be used to help train drivers and identify risk factors in the business. And because this is all done using artificial intelligence that is completely objective, the results are consistent every time and delivered instantly.

In 2020, SmartAnalytics deployment — which was initially on 10,000 drivers but in Q3 rose to 25,000 — reduced accidents by 15%, improved productivity by 30%, reduced fuel and maintenance costs by 7%, improved compliance involvement by 50%, and improved accountability by 20%. In addition, driving behavior scores rose 14%, workplace satisfaction rose 15%, and workplace engagement rose 25%.

Originally posted on Government Fleet