1 / 22

Sponsored Search

Sponsored Search. Cory Pender Sherwin Doroudi. Optimal Delivery of Sponsored Search Advertisements Subject to Budget Constraints. Zoe Abrams Ofer Mendelevitch John A. Tomlin. Introduction.

whitcomb
Download Presentation

Sponsored Search

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. Sponsored Search Cory Pender Sherwin Doroudi

  2. Optimal Delivery of Sponsored Search Advertisements Subject to Budget Constraints Zoe Abrams Ofer Mendelevitch John A. Tomlin

  3. Introduction • Search engines (Google, Yahoo!, MSN) auction off advertisement slots on search page related to user’s keywords • Pay per click • Earn millions a day through these auctions • Auction type is important

  4. Sponsored search parameters • Bids • Query frequencies • Not controlled by advertisers or search engine • Few queries w/ large volume, many with low volume • Advertiser budgets • Pricing and ranking algorithm

  5. Solution • Focus on small subset of queries • Predictable volumes in near future • Constitute large amount of total volume

  6. Sponsored search parameters • Bids • Query frequencies • Advertiser budgets • Controlled by advertisers • Pricing and ranking algorithm • Generalized second price (GSP) auction • Rankings according to (bid) x (quality score) • Charged minimum price needed to maintain rank • Goal: take these parameters into account, maximize revenue

  7. Motivating example Reserve price is 

  8. Problem Definition • Queries Q = {q1, q2, q3, ..., qN} • Bidders B = {b1, b2, b3, ..., bM} • Bidding state A(t);Aij(t) is j’s bid for i-th query • djis j’s daily budget • viis estimate of query frequency • Li = {jp : jp B, p = 1, ..., Pi} • Lik = {jik : jik Li, l ≤ Lik ≤ P}

  9. Ranking and revenue • Bid-ranking - • Revenue-ranking - • So, for slate k, • Price per click: • Independent click through rates • Revenue-per-search: • Total revenue:

  10. Bidder’s cost • Total spend for j:

  11. Linear program • Queries i = 1, ..., N • Bidders j = 1, ..., M • Slates k = 1, ..., Ki • Data: dj, vi, cijk, rik • Variables: xik • Constraints: • Budget: • Inventory:

  12. Objective function • Maximize revenue: • Value objective: • Clicks objective:

  13. Column Generation • Each column represents a slate • Could make all possible columns • But for each query, exponential in number of bidders • Start with some initial set of columns • j: Marginal value for j’s budget • i: Marginal value for ithkeyword • Profit if • Maximize

  14. ebay.com nextag.com ? tigerdirect.com priceline.com How to maximize? • If small number of bidders for a query, enumerate all legal subsets Lik, find maxima, see if adding increases profit • Otherwise, use algorithm described in another paper

  15. Summary (so far) • Various bidders vying for spots on the slate for each query • Constrained by budget, query frequencies, ranking method • Solve LP for some initial set of slates • Check if profit can be made by adding new slates • Re-solve LP, if necessary • Can be applied to maximize revenue or efficiency

  16. Simulation Methodology • Compare this method to greedy algorithm • For greedy, assign what gets most revenue at the time; when bidder’s budget is reached, take them out of the pool • Used 5000 queries • For 11 days, retrieved hourly data on bidders, bids, budgets • To determine which ads appear, assign based on frequencies fik = xik/vi • After each hour, see if anyone has exceeded budget

  17. Simulation Results • Current method better than greedy method, when optimizing over revenue or efficiency • Larger gain for revenue when revenue optimized • Revenue and efficiency are closely tied

  18. Gains when efficiency is maximized

  19. Gains when revenue is maximized

  20. Impact on bidders

  21. Limitations • Illegitimate price hikes for other bidders if one person exceeds budget in middle of hour • Assumption that expected number of clicks are correct • For the purposes of the simulation, expect these to affect greedy and LP optimization similarly

  22. Future work • Focus on less frequent queries • Frequencies harder to predict • Some work has been done (doesn’t incorporate pricing and ranking) • Keywords with completely unknown frequencies • Parallel processing for submarkets • Investigate how advertisers might respond to this method • Potential changes in reported bids/budgets

More Related