Spark/Scala/MLib : Collobrative Filter To Predict Incident Types And Severity Of The Incidents
Sunday, November 12, 2017
As part of incident response function,attaining capabilities to predict the incidents on different assets based on historical data of incidents and their severity will be a useful tool for proactive incident prevention.
Below Spark code utilizes the collaborative filter to predict the incident types and severity levels based on the historical data.A further augmentation of the model will be to include content based filtering capabilities to include similarities between assets also to be considered.
Output of the model given below predicts various incident types and severity of the incidents for application where the output format is in the form of Rating (App ID predicted,Incident Type ID predicted,Severity predicted)