Search

Nowadays, many businesses are resorting to data mining techniques on their data, to save costs and time, as well as to understand customers’ needs. Analysing such data can leader to higher profits and higher customer satisfaction. This paper presents a data mining study that is applied on millions of transactional records collected for a number of years, by a leading virtual credit card company based in Malta. In this study, 2 machine learning techniques, namely Artificial Neural Networks (ANN) and Gradient Boosting (GBM), are analysed to identify the best modelling framework that predicts the churning behaviour of this company’s customers. Apart from helping the marketing department of this firm by providing a model that predicts churning customers, we contribute to literature by identifying the minimum amount of customer activity needed to predict churn. In addition, we also analyse the “cold start” problem by performing a time-series experiment based on the few data available at the beginning of the customer purchase history., peer-reviewed

The music industry has evolved significantly over the last few decades, from cassette to compact disk to MP3 and now to subscription-based streaming. Simultaneously, there has been a return to analogue, especially to vinyl records. In 2021, a major record label will introduce a new kind of vinyl. From the original master tapes, one-of-a-kind copies will be made. These will be manufactured in very limited quantities and sold exclusively as collectors' items. In a world where purchasing these collectibles is as simple as tapping the screen and where there are also numerous trading markets between private individuals, new creative ways to protect consumers and digitally protected analogue collectibles must be found. This relates to both the product's authenticity and the legitimate possession of the valuable vinyl. This work in progress paper aims to determine whether digital identities of suppliers, distributors, and consumers on the one hand, and decentralized encrypted data storage on the other, can be potentially the future technology to safeguard collectibles that the creative industry should be more than just looking at., peer-reviewed

In addition to the general intentional scattering of fake news and its conscious or unconscious sharing on social media networks, the problem of checking the origin of source material from the perspective of the consumer is evident. This is especially the case if the original material was not created and registered with great care by established and trustworthy media companies. In the fast-paced world of real-time reporting, even professional media houses have to rely on cell phone videos or other user-created material. Furthermore, it is also possible that source material only appears to have been produced by an established media company, but instead journalists who work with this material fall victim to well-crafted forgery. The aim of this research study is to discuss Blockchain technologies and their adoption to store a verification hash of source material, the proof of authorship and sources used in a forgery-proof way. Furthermore, the authors investigate whether journalists and media producers see a need in this technology. The discussion centres around the consumers’ perception of such possible verification as an improvement and something they recognize as a “trust amplifier” if embedded in the newspaper, journal, blog, social media platform, or messenger tool of their choice. Finally, the sociological and ethical dimensions are briefly discussed - whether and how verified material can ultimately be fake news once again, and if the perception of what one believes, does not depend at the end on the recipient's basic attitude and perception. This work in progress paper describes the current status of the research work and outlines the envisaged further procedure., peer-reviewed

Software components are expected to communicate according to predetermined protocols and APIs. Numerous methods have been proposed to check the correctness of communicating systems against such protocols/APIs. Session types are one such method, used both for static type-checking as well as for run-time monitoring. This work takes a fresh look at the run-time verification of communicating systems using session types, in theory and in practice. On the theoretical side, we develop a formal model of session-monitored processes. We then use this model to formulate and prove new results on the monitorability of session types, defined in terms of soundness (i.e., whether monitors only flag ill-typed processes) and completeness (i.e., whether all ill-typed processes can be flagged by a monitor). On the practical side, we show that our monitoring theory is indeed realisable: we instantiate our formal model as a Scala toolkit (called STMonitor) for the automatic generation of session monitors. These executable monitors can be used as proxies to instrument communication across black-box processes written in any programming language. Finally, we evaluate the viability of our approach through a series of benchmarks., peer-reviewed

Software components are expected to communicate according to predetermined protocols and APIs. Numerous methods have been proposed to check the correctness of communicating systems against such protocols/APIs. Session types are one such method, used both for static type-checking as well as for run-time monitoring. This work takes a fresh look at the run-time verification of communicating systems using session types, in theory and in practice. On the theoretical side, we develop a formal model of session-monitored processes. We then use this model to formulate and prove new results on the monitorability of session types, defined in terms of soundness (i.e., whether monitors only flag ill-typed processes) and completeness (i.e., whether all ill-typed processes can be flagged by a monitor). On the practical side, we show that our monitoring theory is indeed realisable: we instantiate our formal model as a Scala toolkit (called STMonitor) for the automatic generation of session monitors. These executable monitors can be used as proxies to instrument communication across black-box processes written in any programming language. Finally, we evaluate the viability of our approach through a series of benchmarks., This work has been partly supported by: the project MoVeMnt (No: 217987-051) under the Icelandic Research Fund; the BehAPI project funded by the EU H2020 RISE under the Marie Skłodowska-Curie action (No: 778233); the EU Horizon 2020 project 830929 CyberSec4Europe; the Danish Industriens Fonds Cyberprogram 2020-0489 Security-by-Design in Digital Denmark., peer-reviewed

Once information is stored on the Blockchain, it cannot be altered retroactively. This immutability makes Blockchain technology an ideal candidate to secure learning achievements and educational credentials. Keeping data trustworthy, secure and manipulation-proof has become an increasing issue in education due to the rise of digital learning environments, which often combine learning experiences, testing procedures and educational credential management. Currently, most digital learning environments safeguard their data using traditional safety systems (e.g. password protection), which in turn are not Blockchain-based, but controlled by a centralized authority. While these centralized systems provide a certain level of security against unauthorized access from outside the system, manipulation from within the system cannot be excluded. Users with high enough access rights (teachers, administrators, system managers) can still add, change or delete entries. This becomes an even greater problem when learning achievements are to be reflected in fair and transparent credit systems, and especially when these educational credits are to be valid across different institutions or even countries. Due to their ability to store data in a decentralized, transparent and manipulation-proof way, Blockchain-based technologies can provide solutions to this problem. The aim of this paper is to describe the status quo of Blockchain technologies in the educational sector, including the expected merits and drawbacks., peer-reviewed