Recommending signals to monitor in a fraud prevention application

A method for recommending signals to monitor in a fraud prevention application, the method comprising

• receiving a request for signal recommendations for a first client;
• calculating a similarity score for one or more clients different from the first client;
• for one or more signals, determining, for each of the one or more clients, a signal weight associated with the signal;
• multiplying the signal weight by the similarity score associated with the client to generate a weighted similarity score associated with the signal and the client;
• generating a total similarity score and, for each signal, a total weighted similarity score;
• for each signal, generating a recommendation score based on the total weighted similarity score for the signal and the total similarity score for the signal;
• and
• based on the recommendation scores, generating one or more recommended signals for the first client.

A non-transitory computer-readable medium with computer-executable instructions stored thereon executed by an electronic processor included in a server to perform the method of recommending signals to monitor in a fraud prevention application, comprising

• receiving a request for signal recommendations for a first client;
• calculating a similarity score for one or more clients different from the first client;
• for one or more signals, determining, for each of the one or more clients, a signal weight associated with the signal;
• multiplying the signal weight by the similarity score associated with the client to generate a weighted similarity score associated with the signal and the client;
• generating a total similarity score and, for each signal, a total weighted similarity score;
• for each signal, generating a recommendation score based on the total weighted similarity score for the signal and the total similarity score for the signal;
• and
• based on the recommendation scores, generating one or more recommended signals for the first client.