Jason K. Deane

Hybrid genetic algorithm and augmented neural network application for solving the online advertisement scheduling problem with contextual targeting

Worldwide growth of the online community continues to push the popularity of internet marketing. Fueled by this trend, the online advertising industry is experiencing unprecedented revenue growth. One of the most important drivers of this revenue is banner advertising, which has long been a staple of the online advertising industry. Previous research has introduced quantitative models and solution approaches for the challenging basic scheduling optimization problem. We extend this work by incorporating the most common and popular trend in the in the industry, online advertisement targeting. In addition, motivated by the NP-hard nature of the resulting problem, we propose and test several heuristic and metaheuristic based solution techniques for the proposed problem.

NeuroGenetic approach for combinatorial optimization: an exploratory analysis

Given the NP-Hard nature of many optimization problems, it is often impractical to obtain optimal solutions to large-scale problems in reasonable computing time. For this reason, heuristic and metaheuristic search approaches are used to obtain good solutions fast. However, these techniques often struggle to develop a good balance between local and global search. In this paper we propose a hybrid metaheuristic approach which we call the NeuroGenetic approach to search for good solutions for these large scale optimization problems by at least partially overcoming this challenge. The proposed NeuroGenetic approach combines the Augmented Neural Network (AugNN) and the Genetic Algorithm (GA) search approaches by interleaving the two. We chose these two approaches to hybridize, as they offer complementary advantages and disadvantages; GAs are very good at searching globally, while AugNNs are more proficient at searching locally. The proposed hybrid strategy capitalizes on the strong points of each approach while avoiding their shortcomings. In the paper we discuss the issues associated with the feasibility of hybridizing these two approaches and propose an interleaving algorithm. We also provide empirical evidence demonstrating the effectiveness of the proposed approach.

Assessing the information technology security risk in medical supply chains

Many medical organisations around the world have connected themselves in supply chains, and are exploring the strategic utilisation of information technology (IT) throughout their chains to improve their overall efficiency and effectiveness. Although these efforts may reduce health costs, both the current status of IT security risk and the potential consequences of interconnectedness are largely unknown. This research examines medical supply chain risk exposure. In particular, data from six pharmaceutical companies and eight healthcare organisations is combined with input from security experts to determine the current degree of IT security risk. In addition, we examine an optimal strategy to reduce overall risk and the amount of supply chain risk due to partnering. We find, for the surveyed organisations, a dramatic under-deployment of controls, resulting in huge risk exposure.

Behavioural Targeting in online advertising using web surf history analysis and contextual segmentation

The online advertisement publishing industry is a rapidly growing multi-billion dollar industry. Organisations in this industry generate revenue by creating and/or acquiring online advertising space that they can sell at a profit. Their success is directly dependent on the effectiveness of their publishing strategy in terms of its ability to create traffic and interest for their clients by delivering advertisements which are closely in line with the recipients interests. We propose a supervised learning based ad targeting technique which will help online advertisement publishers achieve this goal. Empirical tests of the new technique are very promising.

A longitudinal analysis of web surf history to maximise the effectiveness of behavioural targeting techniques

Yearly revenue generation for the online advertising industry has increased exponentially from approximately

Mitigating environmental and density risk in global sourcing

7 billion in 2001 to approximately

Managing supply chain risk and disruption from IT security incidents

23 billion in 2008. This rapid growth in revenue has spawned a very competitive online advertisement publishing industry. Ad publishers are paid to deliver ads to potential online customers in an attempt to influence their buying patterns and purchasing decisions. Eager to gain market share, online advertisement publishers are constantly attempting to improve their ability to efficiently target ads to interested online consumers and web surfers. While analysing users’ web surf history is one of the most popular methods of gaining this type of actionable information, the potential value of this information is unclear as one moves further back in time in analysing a user’s historical data. The purpose of this research is to gain insight into what time frame of a user’s surf history is useful. In this paper, we provide a detailed longitudinal application analysis of OAWSH, a powerful behavioural targeting technique, in an effort to determine the optimal range of web surfing time upon which organisations should base their advertisement targeting decisions.