Edward Apeh

Customer profile classification using transactional data

Customer profiles are by definition made up of factual and transactional data. It is often the case that due to reasons such as high cost of data acquisition and/or protection, only the transactional data are available for data mining operations. Transactional data, however, tend to be highly sparse and skewed due to a large proportion of customers engaging in very few transactions. This can result in a bias in the prediction accuracy of classifiers built using them towards the larger proportion of customers with fewer transactions. This paper investigates an approach for accurately and confidently grouping and classifying customers in bins on the basis of the number of their transactions. The experiments we conducted on a highly sparse and skewed real-world transactional data show that our proposed approach can be used to identify a critical point at which customer profiles can be more confidently distinguished.

Change Mining of Customer Profiles Based on Transactional Data

Customer transactions tend to change overtime with changing customer behaviour patterns. Classifier models, however, are often designed to perform prediction on data which is assumed to be static. These classifier models thus deteriorate in performance overtime when predicting in the context of evolving data. Robust adaptive classification models are therefore needed to detect and adjust to the kind of changes that are common in transactional data. This paper presents an investigation into using change mining to monitor the adaptive classification of customers based on their transactions through a moving time window. Results from our experiments show that our approach can be used for learning and adapting to changing customer profiles.

Customer profile classification: To adapt classifiers or to relabel customer profiles?

Customer profiles are, by definition, made up of factual and transactional data. It is often the case that due to reasons such as high cost of data acquisition and/or protection, only the transactional data are available for data mining operations. Transactional data, however, tend to be highly sparse and skewed due to a large proportion of customers engaging in very few transactions. This can result in a bias in the prediction accuracy of classifiers built using them. The problem is even more so when identifying and classifying changing customer profiles whose classification may change either due to a concept drift or due to a change in buying behaviour. This paper presents a comparative investigation of 4 approaches for classifying dynamic customer profiles built using evolving transactional data over time. The changing class values of the customer profiles were analysed together with the challenging problem of deciding whether to change the class label or adapt the classifier. The results from the experiments we conducted on a highly sparse and skewed real-world transactional data show that adapting the classifiers leads to more stable classification of customer profiles in the shorter time windows; while relabelling the changed customer profile classes leads to more accurate and stable classification in the longer time windows.

Predicting Multi-class Customer Profiles Based on Transactions: a Case Study in Food Sales

Predicting the class of customer profiles is a key task in marketing, which enables businesses to approach the customers in a right way to satisfy the customer’s evolving needs. However, due to costs, privacy and/or data protection, only the business’ owned transactional data is typically available for constructing customer profiles. We present a new approach that is designed to efficiently and accurately handle the multi-class classification of customer profiles built using sparse and skewed transactional data. Our approach first bins the customer profiles on the basis of the number of items transacted. The discovered bins are then partitioned and prototypes within each of the discovered bins selected to build the multi-class classifier models. The results obtained from using four multi-class classifiers on real-world transactional data consistently show the critical numbers of items at which the predictive performance of customer profiles can be substantially improved.

Using Human Factor Approaches to an Organisation’s Bring Your Own Device Scheme

Bring Your Own Device (BYOD) is an emerging trend that is being adopted by an increasing number of organisations due to the benefits it provides in terms of cost efficiency, employee productivity, and staff morale. However, organisations who could benefit from implementing BYOD remain sceptical, due to the increasing threats and vulnerabilities introduced by mobile technology, which are amplified due to the human element (insider threats, non-security savvy employees). In this context, this paper investigates the application of human factor techniques to the BYOD scheme of an anonymised, real-life organisation (referred to as “Globex”). Questionnaires and Interactive Management are two Human Factor methods used in this case study to help determine areas for improvement. Results from the experiment highlight an issue with employee satisfaction towards their employers’ BYOD scheme, which could negatively impact their organisational culture. The paper concludes with recommendations for additional information within the BYOD policy and the review of reimbursement eligibility and entitlements.

A resilient cybersecurity framework for Mobile Financial Services (MFS)

ABSTRACT Cybercrime has astronomically risen with technological advancements alongside the business opportunities in cyberspace. Cybercrime is now viewed as one of the top 10 global risks. In recognition of the threat posed by cybercrime, organisations are investing in controls and countermeasures that would combat the threat of cybercrime and its impact. However, incidences of successful cyberattacks are still on the rise. The advent of mobile devices has created a means of providing financial services to over two billion people globally that hitherto had no access to formal banking services. Also, banks and other financial institutions use mobile platforms as an alternative delivery channel for financial services. However, the dark side of using mobile devices to bridge the banking gap is that mobile devices are now an added vector for cybersecurity threats. This has affected trust in the use of the system and consequently slowed down the uptake of mobile financial services (MFS). This article presents an in-depth analysis of the opportunities mobile platforms provide for the unbanked and how cybersecurity is hampering the uptake of MFS. Furthermore, the article proposes an approach for mitigating cybercrime in the complex MFS ecosystem and presents preliminary results from the research conducted so far.

An Effective Immersive Cyber Security Awareness Learning Platform for Businesses in the Hospitality Sector

The rapid digitalisation of the hospitality industry over recent years has brought forth many new points of attack for consideration. The hasty implementation of these systems has created a reality in which businesses are using the technical solutions, but employees have very little awareness when it comes to the threats and implications that they might present. This gap in awareness is further compounded by the existence of preestablished, often rigid, cultures that drive how hospitality businesses operate. Potential attackers are recognising this and the last two years have seen a huge increase in cyber-attacks within the sector.Attempts at addressing the increasing threats have taken the form of technical solutions such as encryption, access control, CCTV, etc. However, a high majority of security breaches can be directly attributed to human error. It is therefore necessary that measures for addressing the rising trend of cyber-attacks go beyond just providing technical solutions and make provision for educating employees about how to address the human elements of security. Inculcating security awareness amongst hospitality employees will provide a foundation upon which a culture of security can be created to promote the seamless and secured interaction of hotel users and technology.One way that the hospitality industry has tried to solve the awareness issue is through their current paper-based training. This is unengaging, expensive and presents limited ways to deploy, monitor and evaluate the impact and effectiveness of the content. This leads to cycles of constant training, making it very hard to initiate awareness, particularly within those on minimum waged, short-term job roles.This paper presents a structured approach for eliciting industry requirement for developing and implementing an immersive Cyber Security Awareness learning platform. It used a series of over 40 interviews and threat analysis of the hospitality industry to identify the requirements for designing and implementing cyber security program which encourage engagement through a cycle of reward and recognition. In particular, the need for the use of gamification elements to provide an engaging but gentle way of educating those with little or no desire to learn was identified and implemented. Also presented is a method for guiding and monitoring the impact of their employee’s progress through the learning management system whilst monitoring the levels of engagement and positive impact the training is having on the business.

Resilience of the Internet of Things (IoT) from an Information Assurance (IA) perspective

Internet infrastructure developments and the rise of the IoT Socio-Technical Systems (STS) have frequently generated more unsecure protocols to facilitate the rapid intercommunication between the plethoras of IoT devices. Whereas, current development of the IoT has been mainly focused on enabling and effectively meeting the functionality requirement of digital-enabled enterprises we have seen scant regard to their IA architecture, marginalizing system resilience with blatant afterthoughts to cyber defence. Whilst interconnected IoT devices do facilitate and expand information sharing; they further increase of risk exposure and potential loss of trust to their Socio-Technical Systems. A change in the IoT paradigm is needed to enable a security-first mind-set; if the trusted sharing of information built upon dependable resilient growth of IoT is to be established and maintained. We argue that Information Assurance is paramount to the success of IoT, specifically its resilience and dependability to continue its safe support for our digital economy.

A model for social engineering awareness program for schools

Advancements in security has over the years of technological growth been mainly focused on providing secured technological infrastructure. The developed security measures and counter-measures have played a major role in reducing the surge of cyber-attacks. However, hackers have continued to exploit vulnerabilities due to the human element to gain access into otherwise secured systems. Risks and potential for exploits are more so in schools where the human vulnerability is enhanced by young impressionable pupils. Social engineering, the art of manipulating people so they give up confidential information, is increasingly the approach of choice for hackers who exploit the human element. Social engineers bypass secured systems in schools by directing targeting and exploiting the human vulnerabilities of schools students and staff. Education through awareness campaigns are typically used in countering the threat from social engineering. Such awareness campaigns tend to however be too holistic in focus to lead to the significant and sustainable change in behaviour required to counter social engineering. This paper presents a model for designing and implementing social engineering awareness programmes aimed at fostering behaviour change in schools. It demonstrates the process of designing a social engineering awareness program to meet all types of learning styles by using different multiple communication methods. Evaluation and continuous reinforcement approaches are also presented. A pilot implementation of our proposed model for social engineering awareness programme shows a significant change in behaviour of schools teaching staff.

Automatically Predicting Quiz Difficulty Level Using Similarity Measures

In this paper, we present a semi-automatic system (Sherlock) for quiz generation using Linked Data and textual descriptions of RDF resources. Sherlock is distinguished from existing quiz generation systems in its ability to control the difficulty level of the generated quizzes. We cast the problem of perceiving the level of knowledge difficulty as a similarity measure problem and propose a novel hybrid semantic similarity measure using linked data. Extensive experiments show that the proposed similarity measure outperforms four strong baselines in both the pilot evaluation using a synthetic gold standard as well as with human evaluation, giving more than 47% gain in clustering accuracy over the baselines.