First Notification of Loss (FNOL) Machine Learning Process Used for Telematics

Machine Learning (ML) is a subfield of computer science that evolved from the study of pattern recognition and computational learning theory in Artificial Intelligence (AI). Machine learning explores the study and construction of algorithms that can learn from and make predictions on data. Such algorithms operate by building a model from example inputs in order to make data-driven predictions or decisions, rather than following strictly static program instructions. [1]. When a vehicle (car) comes across an accident, telematics device associated with it will send the accident information (crash or the impact data) to a system. This alert notification (FNOL � Fist Notification of Loss alert) will be send to the recipients. Later this data is stored for analysis, reporting and for claiming the insurance. As data from an accident is understood, reconstruction tools will revolutionize fault allocation, with early intervention transforming FNOL activity and situation control; delivering cost reductions throughout the process. This will help the telematics industries to claim the insurance for their vehicle (which is met with an accident)[2]. FNOL ML API (Application Programming Interface) will identify if FNOL message which is received from the device is a genuine accident message and its value is greater than or equal to configured threshold. If so, it will send an email about that incident (impact) to all the email recipients configured in the system with the accident information[2]. In the present investigation, an attempt was made to analyze FNOL ML process. Computer program (code) was written to develop the Machine Learning capability. This is to understand and predict the accident data which is very useful for telematics industry to process the motor insurance claims. The FNOL ML will receive the accident data from the device (fitted to the vehicle), do the calculation for machine learning process and finally send the mail to the respective mail distribution list informing about the accident and the accident data.