Results 1 -
5 of
5
Optimal real-time bidding for display advertising
- In KDD
, 2014
"... In this paper we study bid optimisation for real-time bid-ding (RTB) based display advertising. RTB allows adver-tisers to bid on a display ad impression in real time when it is being generated. It goes beyond contextual advertising by motivating the bidding focused on user data and it is different ..."
Abstract
-
Cited by 3 (1 self)
- Add to MetaCart
(Show Context)
In this paper we study bid optimisation for real-time bid-ding (RTB) based display advertising. RTB allows adver-tisers to bid on a display ad impression in real time when it is being generated. It goes beyond contextual advertising by motivating the bidding focused on user data and it is different from the sponsored search auction where the bid price is associated with keywords. For the demand side, a fundamental technical challenge is to automate the bid-ding process based on the budget, the campaign objective and various information gathered in runtime and in histo-ry. In this paper, the programmatic bidding is cast as a functional optimisation problem. Under certain dependen-cy assumptions, we derive simple bidding functions that can be calculated in real time; our finding shows that the optimal bid has a non-linear relationship with the impres-sion level evaluation such as the click-through rate and the conversion rate, which are estimated in real time from the impression level features. This is different from previous work that is mainly focused on a linear bidding function. Our mathematical derivation suggests that optimal bidding strategies should try to bid more impressions rather than focus on a small set of high valued impressions because ac-cording to the current RTB market data, compared to the higher evaluated impressions, the lower evaluated ones are more cost effective and the chances of winning them are relatively higher. Aside from the theoretical insights, of-fline experiments on a real dataset and online experiments on a production RTB system verify the effectiveness of our proposed optimal bidding strategies and the functional op-timisation framework.
A Lattice Framework for Pricing Display Ad Options with the Stochastic Volatility Model. Working Paper (2014
- In arXiv: http://arxiv. org/abs/1409.0697
, 2014
"... Ad options are a recent development in online advertising which provide advertis-ers with greater flexibility related to buying their guaranteed deliveries in the future. In short, an ad option is a contract in which an online publisher (or search engine) grants an advertiser the right but not oblig ..."
Abstract
-
Cited by 1 (1 self)
- Add to MetaCart
(Show Context)
Ad options are a recent development in online advertising which provide advertis-ers with greater flexibility related to buying their guaranteed deliveries in the future. In short, an ad option is a contract in which an online publisher (or search engine) grants an advertiser the right but not obligation to enter into transactions to purchase impressions or clicks from a specific online ad slot at a pre-specified price on a specific delivery date. Previous studies on the ad option pricing models are mostly restricted to the situation where the underlying price follows a geometric Brownian motion (GBM). However, it has been shown that GBM only happens in less than 20 % of the stochastic movements of ad auction prices. In this paper, we address this issue by employing a stochastic volatility (SV) model to describe the evolution of the underlying price which does not rely on the assumption of GBM. The computational tractability is solved by approximating the SV model with a proposed censored binomial lattice. Our develop-ments are validated by experiments with the real advertising data. We find that the SV model has a better fitness to the real adverting data; with the real data, we demonstrate that advertisers are able flexibly to manage their guaranteed deliveries by using the pro-posed options. We also demonstrate that publishers will have increased revenue when some of their inventories are sold via ad options.
Tie-Yan LiuTable of Contents Workshop Description Organizing Committee Invited Talk 1: Financial Methods in Computational Advertising
"... held in conjunction with ..."
(Show Context)
xMulti-Keyword Multi-Click Advertisement Option Contracts for Sponsored Search
"... In sponsored search, advertisement (shortly ad) slots are usually sold by a search engine to an advertiser ..."
Abstract
- Add to MetaCart
In sponsored search, advertisement (shortly ad) slots are usually sold by a search engine to an advertiser
Adaptive Keywords Extraction with Contextual Bandits for Advertising on Parked Domains
"... Domain name registrars and URL shortener service providers place advertisements on the parked domains (Internet do-main names which are not in service) in order to generate profits. As the web contents have been removed, it is criti-cal to make sure the displayed ads are directly related to the inte ..."
Abstract
- Add to MetaCart
(Show Context)
Domain name registrars and URL shortener service providers place advertisements on the parked domains (Internet do-main names which are not in service) in order to generate profits. As the web contents have been removed, it is criti-cal to make sure the displayed ads are directly related to the intents of the visitors who have been directed to the parked domains. Because of the missing contents in these domains, it is non-trivial to generate the keywords to describe the pre-vious contents and therefore the users intents. In this paper we discuss the adaptive keywords extraction problem and introduce an algorithm based on the BM25F term weight-ing and linear multi-armed bandits. We built a prototype over a production domain registration system and evaluated it using crowdsourcing in multiple iterations. The prototype is compared with other popular methods and is shown to be more effective. 1.
