An advanced bidding agent for advertisement selection on public displays

Abstract

In this paper we present an advanced bidding agent that participates in first-price sealed bid auctions to allocate advertising space on BluScreen -an experimental public advertisement system that detects users through the presence of their Bluetooth enabled devices. Our bidding agent is able to build probabilistic models of both the behaviour of users who view the adverts, and the auctions that it participates within. It then uses these models to maximise the exposure that its adverts receive. We evaluate the effectiveness of this bidding agent through simulation against a range of alternative selection mechanisms including a simple bidding strategy, random allocation, and a centralised optimal allocation with perfect foresight. Our bidding agent significantly outperforms both the simple bidding strategy and the random allocation, and in a mixed population of agents it is able to expose its adverts to 25% more users than the simple bidding strategy. Moreover, its performance is within 7.5% of that of the centralised optimal allocation despite the highly uncertain environment in which it must operate.

MyAds: A system for adaptive pervasive advertisements

“…Finally, we found in the approach of Rogers et al [14], named Bluescreen, the one that shares our vision the most. Similarly to our work, in fact, this approach presents an environment where a public-display advertisement scenario is governed by an auction-based allocation system.…”

[Invited Paper] Content Scheduling and Adaptation for Networked and Context-Aware Digital Signage: A Literature Survey

“…"reach", by reducing the number of people who watch the same content multiple times; it uses Bluetooth device ID to identify viewers near a display and and selects the content item suitable for the largest number of viewers who see the item first time under a budget constraint using a second price seal auction. Rogers et al 73) also maximized reach. The difference is that (a) the number of viewers is predicted by a probabilistic model using a Poisson distribution and (b) the proba- …”

Evaluating BluScreen: Usability for Intelligent Pervasive Displays

“…This research begins with a user study designed to evaluate the effectiveness of intelligent pervasive displays. The work we present in this paper extends our ongoing research on BluScreen [9], [10], an intelligent public display framework that utilises a novel wireless approach to detecting nearby users to improve the selection of adverts for display. …”

“…Moreover, unlike interactive public displays, our detection technology facilitates an awareness of several devices simultaneously. Previous publications describing the BluScreen system [9], [10], [13] have examined gametheoreic approaches for selecting adverts using mechanisms such as Agent-based Auction Theory [14] or Queueing Theory [15]. Whilst such techniques can be shown to yield optimal (or near-optimal) results through simulation, the evaluations used do not consider how human subjects react to situated displays in a working environment.…”