Next at Web Science 2016 [3] is Sergej Sizov, who focusses on the economic value of Web advertising. This is surprisingly difficult to calculate, and Sergej begins with the hypothetical example of a small Web advertising campaign. We may make a range of assumptions about click-through and purchase rates, but variance matters: in a substantial number of cases, campaigns may generate no profit whatsoever.

Each campaign constitutes a large number of small events (clicks, conversions, ...), and these can be modelled computationally; from these emerge certain predictions about the probability to make a given profit from the campaign.