Do you know your customer? Bank risk assessment based on machine learning

Know Your Customer (KYC) data can serve as a valuable risk assessment tool for banks by providing information that can identify customers who are more likely to default on a loan. This study aims to provide an accurate risk assessment tool using unique KYC data and machine-learning techniques to overcome problems in existing risk detection methods. This study proposes that the bank branch is the best level at which to determine the degree of default risk, and can also provide insight into patterns of suspicious transactions. Bank managers and regulators can focus on suspicious behavior at specific branches to increase overall compliance and reduce the risk of illegal activity.     

Do you know your user group? Why it is essential to put your user-requirements analysis on a broad database

Universal Access in the Information Society - When developing a novel technological system, it is important to meet the users’ needs and expectations to ensure that the product will be...     

Do you really mean what you actually enforced?

In their works on the theoretical side of Polymer, Ligatti and his co-authors have identified a new class of enforcement mechanisms based on the notion of edit automata that can transform sequences and enforce more than simple safety properties. We show that there is a gap between the edit automata that one can possibly write (e.g., by Ligatti et?al in their IJIS running example) and the edit automata that are actually constructed according the theorems from Ligatti??s IJIS paper or from Talhi et?al. ??Ligatti??s automata?? are just a particular kind of edit automata. Thus, we re-open a question which seemed to have received a definitive answer: you have written your security enforcement mechanism (aka your edit automata); does it really enforce the security policy you wanted?     

What does your selfie say about you?

Selfies refer to self-portraits taken by oneself using a digital camera or a smartphone. They become increasingly popular in social media. However, little is known about how selfies reflect their owners’ personality traits and how people judge others’ personality from selfies. In this study, we examined the association between selfies and personality by measuring participants’ Big Five personality and coding their selfies posted on a social networking site. We found specific cues in selfies related to agreeableness, conscientiousness, neuroticism, and openness. We also examined zero-acquaintance personality judgment and found that observers had moderate to strong agreement in their ratings of Big Five personality based on selfies. However, they could only accurately predict selfie owners’ degree of openness. This study is the first to reveal personality-related cues in selfies and provide a picture-coding scheme that can be used to analyze selfies. We discussed the difference between personality expression in selfies and other types of photos, and its possible relationship with impression management of social media users.     

What surprises does your past have for you?

Although the current Recommender Systems (RSs) focus on discovering unknown items for users in several domains, users may be particularly interested in consuming items in which they are already familiar. As a result, this study aims to uncover subsets of known items that are useful for recommendations in the present. The main argument highlighted in this study is that past consumption is a rich source of relevant recommendations neglected or underexploited by current RSs. Thus, we propose a methodology to quantify the effectiveness of recommending known items in real domains. Afterwards, we proposed distinct heuristics to search the consumption history of each user items unexpected to be consumed, but potentially relevant. Such heuristics exploit time-related, context-related, and relevance-related information; as well as a combination of these three types of information. Assessments on real collections allowed us to verify the applicability of our methodology. Furthermore, offline evaluations demonstrated that past relevance, consumption recency, and associations with currently consumed items are useful information to model reconsumption. Finally, through a user study with members of Movielens, we verified that users are willing to reconsume some known items and recognized the value in this type of recommendation. Therefore, by exploiting the long history of each user, we are able to match a piece of the user’s preference neglected by current RSs, hence, improving the user’s satisfaction.     

Do you remember？

“今天是什么日子，是不是一点印象也没有，都忘了吧？我爸妈可生气了！”工作越来越忙，今天是什么日子还真是想不起来了……被这批头盖脸地一骂，自己难免有些心虚，想了又想，才猛然想起，今天本是约好去她家探望未来岳父岳母的日子！     

Are you emotional or depressed? Learning about your emotional state from your music using machine learning

The Journal of Supercomputing - Music plays an important role in our society and has applications broader than just entertainment and pleasure due to its social and physiological effects. There has...     

Which middleware platform should you choose for your next remote service?

Due to the shift from software-as-a-product to software-as-a-service, software components that were developed to run in a single address space must increasingly be accessed remotely across the network. Distribution middleware is frequently used to facilitate this transition. Yet a range of middleware platforms exist, and there are few existing guidelines to help the programmer to choose an appropriate middleware platform to achieve desired goals for performance, conciseness, intuitiveness, and reliability. To address this limitation, in this article, we describe a case study of transitioning an Open Service Gateway Initiative service from local to remote access. In our case study, we evaluate five remote versions of this service, constructed using different distribution middleware platforms. These platforms are implemented by widely-used commercial technologies or have been proposed as improvements on the state of the art. In particular, we implemented a service-oriented version of our own Remote Batch Invocation abstraction. We compare and contrast these implementations in terms of their respective performance, conciseness, complexity, and reliability. Our results can help remote service programmers make informed decisions when choosing middleware platforms for their applications.     

Electronic retention: what does your mobile phone reveal about you?

The global information rich society is increasingly dependent on mobile phone technology for daily activities. A substantial secondary market in mobile phones has developed as a result of a relatively short life-cycle and recent regulatory measures on electronics recycling. These developments are, however, a cause for concern regarding privacy, since it is unclear how much information is retained on a device when it is re-sold. The crucial question is: what, despite your best efforts, does your mobile phone reveal about you?. This research investigates the extent to which personal information continues to reside on mobile phones even when users have attempted to remove the information; hence, passing the information into the secondary market. A total of 49 re-sold mobile devices were acquired from two secondary markets: a local pawn shop and an online auction site. These devices were examined using three industry standard mobile forensic toolkits. Data were extracted from the devices via both physical and logical acquisitions and the resulting information artifacts categorized by type and sensitivity. All mobile devices examined yielded some user information and in total 11,135 artifacts were recovered. The findings confirm that substantial personal information is retained on a typical mobile device when it is re-sold. The results highlight several areas of potential future work necessary to ensure the confidentially of personal data stored on mobile devices.     

Convergence of crisis response strategy and source credibility: Who can you trust?

The purpose of this study was to explore how communicative responses and different sources of communication affect stakeholders’ perception of corporate reputation. The main goal was to explore the effects of crisis response strategy and source of crisis communication on organizational and speaker reputations. In a 2 × 2 scenario experiment, respondents judge corporate and speaker reputation of an imaginary organization. Apology as a strategy results in higher postcrisis reputation of both organization and speaker. However, the selection of the source has little effect on how people react to crisis response strategies. This means that a spokesperson can be as useful as a CEO which can be important if the CEO does not convey a positive presence on a screen.     

For your eyes only? A ‘Do Not Track’ proposal

The Internet has become an indispensable part of Americans’ everyday lives. At the same time, its ease of data collection and storage has put the notion of personal privacy in grave danger. The FTC is finally gearing up to face this danger and opened discussions on how Do Not Track regulations should operate. This article first explores the landscape of the current tracking mechanisms and surveys what Americans actually think of these practices and how much they understand about their legal protections. Second, it proposes a possible solution, partially grounded in a comparison with the popular and proven Do Not Call regulations. Specifically, I parse the problem into three main types of behavior – first-party tracking, third-party tracking, and the selling/sharing of collected data – and suggest a different legal rule for each. Selling/sharing of data poses the greatest threat to personal privacy and therefore, should be governed by an opt-in regime. Third-party tracking can be placed under a browser level opt-out control. This proposal leaves first-party tracking as is, though with some caveats for the direction of potential future regulations. Finally, the article considers a cost-benefit analysis of imposing limits on tracking and offers three responses to the economic-based criticisms of such limits. One, that the choice between free Internet and personal privacy is a false one. Two, that customization and not personalization is a much better answer for both consumer and industry. And three, that there is enough evidence to suggest that the purported benefits are specious at best, and consumers deserve the ability to dispute the cost-benefit balance currently struck by the industry at their expense.     

Human factors in information security: The insider threat – Who can you trust these days?

This paper examines some of the key issues relating to insider threats to information security and the nature of loyalty and betrayal in the context of organisational, cultural factors and changing economic and social factors. It is recognised that insiders pose security risks due to their legitimate access to facilities and information, knowledge of the organisation and the location of valuable assets. Insiders will know how to achieve the greatest impact whilst leaving little evidence. However, organisations may not have employed effective risk management regimes to deal with the speed and scale of change, for example the rise of outsourcing. Outsourcing can lead to the fragmentation of protection barriers and controls and increase the number of people treated as full time employees. Regional and cultural differences will manifest themselves in differing security threat and risk profiles. At the same time, the recession is causing significant individual (and organisational) uncertainty and may prompt an increase in abnormal behaviour in long-term employees and managers – those traditionally most trusted – including members of the security community. In this environment, how can organisations know who to trust and how to maintain this trust?The paper describes a practitioner’s view of the issue and the approaches used by BT to assess and address insider threats and risks. Proactive measures need to be taken to mitigate against insider attacks rather than reactive measures after the event. A key priority is to include a focus on insiders within security risk assessments and compliance regimes. The application of technology alone will not provide solutions. Security controls need to be workable in a variety of environments and designed, implemented and maintained with people’s behaviour in mind. Solutions need to be agile and build and maintain trust and secure relationships over time. This requires a focus on human factors, education and awareness and greater attention on the security ‘aftercare’ of employees and third parties.     

Social networking sites and cognitive abilities: Do they make you smarter?

The purpose of the present study was to investigate the impact of social networking sites (SNS) on cognitive abilities and reported levels of social connectedness in adolescents. In order to provide a reliable measure of cognitive skills, standardized tests of verbal ability, working memory, and academic attainment were administered. Students also responded to questions about the length and type of social media use (Facebook, YouTube, and Twitter). The findings indicated that young people who had used Facebook (but not YouTube) for more than a year had higher scores in tests of verbal ability, working memory, and spelling, compared to their peers who had used it for a shorter time period. The type of Facebook activities seemed to have an impact, as regression analyses confirmed that checking a friend's status updates was a significant predictor of verbal ability scores. However, regular or ‘active’ engagement with SNS (each hour versus once a month) did not make a difference to their cognitive scores. Longer Facebook use, but not YouTube, was linked to higher reported levels of social connectedness. This pattern of results is interpreted in light of previous research, as well as the key physiological and social developments that occur during the adolescent period.