Science-to-Practice Initiative PROSAD: A Bidding Decision Support System for PRofit Optimizing Search Engine ADvertising Bernd Skiera, Nadia Abou Nabout skiera@wiwi.uni-frankfurt.de abounabout@wiwi.uni-frankfurt.de Availability of video presentation and additional exercises Paper "PROSAD: A Bidding Decision Support System for PRofit Optimizing Search Engine Advertising" was a finalist of "The Gary L. Lilien ISMS-MSI Practice Prize.“ A video presentation and the original PowerPoint slides of the presentation are available at http://techtv.mit.edu/videos/18315-prosad. Instructors can also contact the authors (skiera@skiera.de or abounabout@wiwi.unifrankfurt.de) for a larger deck of slides and an exercise (including teaching note) that can be taught and that involves two small data sets to further illustrate the decision support system. Search Engine Advertising 2 What is search engine advertising (SEA)? Paid search results Keyword Rank 1 2 3 4 5 6 Organic search results Search Engine Advertising 3 Decision making after cooperation Rules-based decision making 1. If then keyword profit after acquisition costs > 10€ increase bid by 30% Profit maximization 2. If then rank > 5 increase bid by 20% 3. If keyword profit after acquisition costs < 0 & number of clicks > 100 & rank <= 3 decrease bid by 20% then Search Engine Advertising 4 PROSAD (PRofit Optimizing Search Engine ADvertising) Transactional profit Profit contribution per conversion Max! Acquisition costs per conversion Search Engine Advertising Number of conversions 5 How does the bid influence transactional profit? 1 Profit contribution per conversion Acquisition costs per conversion Number of conversions Transactional profit 2 Conversion rate Clickthrough rate Number of searches 4 Rank 3 Bid Quality Score Decision variable Search Engine Advertising 6 Optimal bid 1 PCk Profit contribution per conversion 2 Conversion rate CRk 3 ' k 4 ' k Optimal bid Percentage increase in prices per click Percentage increase in clickthrough rates Bid = PCk CRk * k Search Engine Advertising k' + ' k ' k . 7 Learnings from field experiment LOWER BIDS Profit improvement per keyword per year: ROI for lower budget: +33.12€ +21% Profit improvement potential of PROSAD for SoQuero and its clients: Search Engine Advertising 2.7€ million 8 Summary Rules-based decision making difficult • • • Number of rules grows quickly Likelihood of contradicting bidding suggestions high Choice of specific parameter values in rules difficult Profit optimizing search engine advertising easily feasible • • Profit function equals number of conversions times profit per conversion after acquisition costs Estimation of functional relations between rank and bid rank and clickthrough rate Results of field experiment support profit optimizing SEA • • Reduction of SEA budget by 38% Increase in ROI by 21 percentage points Search Engine Advertising 9