Machine learning techniques that identify attribution of small signal stimulus in noisy response channels

A computer program product embodied in a non-transitory computer readable medium, the computer readable medium having stored thereon a sequence of instructions which, when executed by a processor causes the processor to execute a process, the process comprising:

• receiving electronic data records of stimuli data associated with at least one channel, wherein the stimuli data comprises a plurality of event notifications for an event propagated through the channel over a period of time to a plurality of users, the event notifications being associated with a plurality of small signal attributes specified at a sub-channel level of the channel;
• receiving electronic data records of aggregated response data associated with the event, that captures a plurality of responses, elicited over time, from the users to the event;
• generating, in a computer, from the stimuli data, a plurality of time series stimuli data vectors from the event notifications propagated over time, and generating, from the aggregated response data, a plurality of time series response data vectors from the responses elicited over time;
• generating, using machine-learning techniques in a computer, a small signal correlation engine, to correlate at least one of the time series stimuli data vectors to one of the time series response data vectors, and to generate a plurality of correlation coefficients that identify contributions of the event notifications, including at least one of the small signal attributes, to the aggregated response data;
• and
• generating, using machine-learning techniques in a computer, a learning model to receive electronic data records of stimuli and aggregated response data and to simulate variations of the stimuli data to predict user responses using the correlation coefficients, Including computing a contribution of at least one of the small signal attributes of at least one of the event notifications.

A computer system comprising:

• a computer processor to execute a set of program code instructions;
• and
• a memory to hold the program code instructions, in which the program code instructions comprises program code to perform:
• receiving electronic data records of stimuli data associated with at least one channel, wherein the stimuli data comprises a plurality of event notifications for an event propagated through the channel over a period of time to a plurality of users, the event notifications being associated with a plurality of small signal attributes specified at a sub-channel level of the channel;
• receiving electronic data records of aggregated response data associated with the event, that captures a plurality of responses, elicited over time, from the users to the event;
• generating, in a computer, from the stimuli data, a plurality of time series stimuli data vectors from the event notifications propagated over time, and generating, from the aggregated response data, a plurality of time series response data vectors from the responses elicited over time;
• generating, using machine-learning techniques in a computer, a small signal correlation engine, to correlate at least one of the time series stimuli data vectors to one of the time series response data vectors, and to generate a plurality of correlation coefficients that identify contributions of the event notifications, including at least one of the small signal attributes, to the aggregated response data;
• and
• generating, using machine-learning techniques in a computer, a learning model to receive electronic data records of stimuli and aggregated response data and to simulate variations of the stimuli data to predict user responses using the correlation coefficients, including computing a contribution of at least one of the small signal attributes of at least one of the event notifications.