Causal multi-touch attribution

An apparatus comprising:

• a time series component configured to generate an ordered series representing a plurality of precursor events corresponding to a result event, wherein each of the precursor events is associated with an event category from a set of event categories;
• a first temporal convolution network having a dilation factor which increases exponentially with respect to layer depth, which is configured to generate a first series of predictive values corresponding to the plurality of precursor events by computing a plurality of hidden vector representations for a first set of one or more of the precursor events;
• a second temporal convolution network, which is configured to generate a second series of predictive values corresponding to the plurality of precursor events by computing a plurality of hidden vector representations for a second set of one or more of the precursor events which is different from the first set of one or more of the precursor events;
• a combiner which concatenates the first series of predictive values and the second series of predictive values to produce a combined series, and
• an attribution component configured to compute an attribution value for each of the event categories based on the combined series.