Building a Neural Network to Detect Ad Fraud

Too Long; Didn't Read

Building a neural network to Detect Ad Fraud involves finding attacks before they hit ad budgets. CHEQ built a service in python language and Google’s tensorflow deep learning library. The model is a recurrent neural network with double stacked Long Short Term Memory (LSTM) layers which predict the signals values for the next time step, in our case we used 10 minutes time steps with a data set of our 30 days historical network traffic segmented into online ad fraud types. The anomalies, once found, are fed to an explanatory module which by query the database for different fields at and around the anomalous timestamp, sends an alert to the team's slack channel containing the anomaly.