Communicating mobile security threats and best practices has become a central objective due to the ongoing discovery of new vulnerabilities of mobile devices. To cope with this overarching issue, the goal of this paper is to identify and analyze existing threats and best practices in the domain of mobile security. To this extent, we conducted a literature review based on a set of keywords. The obtained results concern recognizable threats and established best practices in the domain of mobile security. Afterwards, this outcome was put forward for consideration by mobile application users (n = 167) via a survey instrument. To this end, the results show high awareness of the threats and their countermeasures in the domain of mobile applications. While recognizing the risks associated with physical and social factors, the majority of respondents declared the use of built-in methods to mitigate the negative impact of malicious software and social-engineering scams. The study results contribute to the theory on mobile security through the identification and exploration of a variety of issues, regarding both threats and best practices. Besides this, this bulk of up-to-date knowledge has practical value which reflects in its applicability at both the individual and enterprise level. Moreover, at this point, we argue that understanding the factors affecting users’ intentions and motivations to accept and use particular technologies is crucial to leverage the security of mobile applications. Therefore, future work will cover identifying and modeling users’ perceptions of the security and usability of mobile applications.

No abstract

Churn prediction is a Big Data domain, one of the most demanding use cases of recent time. It is also one of the most critical indicators of a healthy and growing business, irrespective of the size or channel of sales. This paper aims to develop a deep learning model for customers’ churn prediction in e-commerce, which is the main contribution of the article. The experiment was performed over real e-commerce data where 75% of buyers are one-off customers. The prediction based on this business specificity (many one-off customers and very few regular ones) is extremely challenging and, in a natural way, must be inaccurate to a certain ex-tent. Looking from another perspective, correct prediction and subsequent actions resulting in a higher customer retention are very attractive for overall business performance. In such a case, predictions with 74% accuracy, 78% precision, and 68% recall are very promising. Also, the paper fills a research gap and contrib-utes to the existing literature in the area of developing a customer churn prediction method for the retail sector by using deep learning tools based on customer churn and the full history of each customer’s transactions.

No abstract

No abstract