Towards Blockchain Network Platform for IoT Data Integrity and Scalability

<p>Decentralised technology backed by blockchain has gained popularity in recent years, as it secures autonomous ecosystems without the need for a central authority. The blockchain concept originated in the financial domain using cryptocurrency but has been applied to a variety of industries over the last few years. In the era of Industry 4.0, most enterprises leverage automation by using Internet of Things (IoT) technology. Despite the numerous applications of blockchain across industries, significant latency in the consensus algorithm in blockchain hinders its adoption among businesses using IoT technology. A number of studies have addressed the obstacles of transaction processing performance and system scalability, mostly based on a public blockchain. However, the approaches still involve centralised components and thus fail to fully utilise decentralisation. Here, a private blockchain-based IoT data integration platform is proposed to achieve data integrity and system scalability. Along with a lightweight IoT gateway, instead of any other additional middleware, the process and the system configuration are streamlined. By using Hyperledger Fabric, the design is validated, and the proposed architecture outperforms other conventional models in IoT data processing. Thus, decentralisation in IoT environments is achieved.</p>

Towards Blockchain Network Platform for IoT Data Integrity and Scalability

<p>Decentralised technology backed by blockchain has gained popularity in recent years, as it secures autonomous ecosystems without the need for a central authority. The blockchain concept originated in the financial domain using cryptocurrency but has been applied to a variety of industries over the last few years. In the era of Industry 4.0, most enterprises leverage automation by using Internet of Things (IoT) technology. Despite the numerous applications of blockchain across industries, significant latency in the consensus algorithm in blockchain hinders its adoption among businesses using IoT technology. A number of studies have addressed the obstacles of transaction processing performance and system scalability, mostly based on a public blockchain. However, the approaches still involve centralised components and thus fail to fully utilise decentralisation. Here, a private blockchain-based IoT data integration platform is proposed to achieve data integrity and system scalability. Along with a lightweight IoT gateway, instead of any other additional middleware, the process and the system configuration are streamlined. By using Hyperledger Fabric, the design is validated, and the proposed architecture outperforms other conventional models in IoT data processing. Thus, decentralisation in IoT environments is achieved.</p>

A multi-source entity-level sentiment corpus for the financial domain: the FinLin corpus

We introduce FinLin, a novel corpus containing investor reports, company reports, news articles, and microblogs from StockTwits, targeting multiple entities stemming from the automobile industry and covering a 3-month period. FinLin was annotated with a sentiment score and a relevance score in the range [− 1.0, 1.0] and [0.0, 1.0], respectively. The annotations also include the text spans selected for the sentiment, thus, providing additional insight into the annotators’ reasoning. Overall, FinLin aims to complement the current knowledge by providing a novel and publicly available financial sentiment corpus and to foster research on the topic of financial sentiment analysis and potential applications in behavioural science.

Counterfactual Explanations as Interventions in Latent Space

Explainable Artificial Intelligence (XAI) is a set of techniques that allows the understanding of both technical and non-technical aspects of Artificial Intelligence (AI) systems. XAI is crucial to help satisfying the increasingly important demand of \emph{trustworthy} Artificial Intelligence, characterized by fundamental characteristics such as respect of human autonomy, prevention of harm, transparency, accountability, etc. Within XAI techniques, counterfactual explanations aim to provide to end users a set of features (and their corresponding values) that need to be changed in order to achieve a desired outcome. Current approaches rarely take into account the feasibility of actions needed to achieve the proposed explanations, and in particular they fall short of considering the causal impact of such actions. In this paper, we present Counterfactual Explanations as Interventions in Latent Space (CEILS), a methodology to generate counterfactual explanations capturing by design the underlying causal relations from the data, and at the same time to provide feasible recommendations to reach the proposed profile. Moreover, our methodology has the advantage that it can be set on top of existing counterfactuals generator algorithms, thus minimising the complexity of imposing additional causal constrains. We demonstrate the effectiveness of our approach with a set of different experiments using synthetic and real datasets (including a proprietary dataset of the financial domain).

A meta-analysis of financial self-control strategies: Comparing empirical findings with online media and lay person perspectives on what helps individuals curb spending and start saving

Self-control can be assisted by using self-control strategies rather than relying solely on willpower to resist tempting situations and to make more goal-consistent decisions. To understand how self-control strategies can aid financial goals, we conducted a meta-analysis (Study 1) to aggregate the latest research on self-control strategies in the financial domain and to estimate their overall effectiveness for saving and spending outcomes. Across 29 studies and 12 different self-control strategies, strategies reduced spending and increased saving significantly with a medium effect size (d = 0.57). Proactive and reactive strategies were equally effective. We next examined whether these strategies studied in the academic literature were present in a media sample of websites (N = 104 websites with 852 strategies) and in individuals’ personal experiences (N = 939 participants who listed 830 strategies). About half the strategies identified in the meta-analysis were present in the media sample and about half were listed by lay participants as strategies they personally use. In sum, this paper provides a comprehensive overview of the self-control strategies that have been studied in the empirical literature to date and of the strategies promoted in the media and used in daily life, identifying gaps between these perspectives.

TAX EVASION AND FINANCIAL FRAUD IN THE CURRENT DIGITAL CONTEXT

Preventing and combating phenomenon of tax evasion is a present concern of national governments due to the magnitude this phenomenon represents and because of the increasingly sophisticated techniques used by the authors in carrying out tax frauds. Evolution of tax evasion phenomenon at international level has acquired a profound technological character due to the increasingly elaborate methods. Illegal behaviour has some specific features that could be recognized easily by artificial intelligence models. They use real data in order to derive characteristics that could be identified in due time so that tax avoidant behaviour be identified and prevented. The use of forecasting models like logistic regression, random forests or decision trees in order to model tax avoidant behaviour shows having a good predictive power. Also, the use of the neural networks allowed scientists to calculate probability of an individual taxpayer that would attempt to evade taxes or commit other types of financial frauds. Scientific literature shows an increasing interest in using neural networks to detect and predict fraudulent behaviour in the fields of tax avoidance and financial domain. Cybercrime, cryptocurrency and blockchain were created in order to facilitate payments and help owner in accumulating wealth. Current landscape of financial frauds shows a different picture. Intracommunity frauds are more and more diversified. European Union and International bodies act together to prevent and combat fraud. Could these new technologies possess a real threat to the financial security of our transactions or encourage fraudulent behaviour? This paper tries to find the answer to this question.

On systematically building a controlled natural language for functional requirements

Natural language (NL) is pervasive in software requirements specifications (SRSs). However, despite its popularity and widespread use, NL is highly prone to quality issues such as vagueness, ambiguity, and incompleteness. Controlled natural languages (CNLs) have been proposed as a way to prevent quality problems in requirements documents, while maintaining the flexibility to write and communicate requirements in an intuitive and universally understood manner. In collaboration with an industrial partner from the financial domain, we systematically develop and evaluate a CNL, named Rimay, intended at helping analysts write functional requirements. We rely on Grounded Theory for building Rimay and follow well-known guidelines for conducting and reporting industrial case study research. Our main contributions are: (1) a qualitative methodology to systematically define a CNL for functional requirements; this methodology is intended to be general for use across information-system domains, (2) a CNL grammar to represent functional requirements; this grammar is derived from our experience in the financial domain, but should be applicable, possibly with adaptations, to other information-system domains, and (3) an empirical evaluation of our CNL (Rimay) through an industrial case study. Our contributions draw on 15 representative SRSs, collectively containing 3215 NL requirements statements from the financial domain. Our evaluation shows that Rimay is expressive enough to capture, on average, 88% (405 out of 460) of the NL requirements statements in four previously unseen SRSs from the financial domain.

A Prior Information Enhanced Extraction Framework for Document-level Financial Event Extraction

Document-level financial event extraction (DFEE) is the task of detecting event and extracting the corresponding event arguments in financial documents, which plays an important role in information extraction in the financial domain. This task is challenging as the financial documents are generally long text and event arguments of one event may be scattered in different sentences. To address this issue, we propose a novel Prior Information Enhanced Extraction framework (PIEE) for DFEE, leveraging prior information from both event types and pre-trained language models. Specifically, PIEE consists of three components: event detection, event argument extraction, and event table filling. In event detection, we identify the event type. Then, the event type is explicitly used for event argument extraction. Meanwhile, the implicit information within language models also provides considerable cues for event arguments localization. Finally, all the event arguments are filled in an event table by a set of predefined heuristic rules. To demonstrate the effectiveness of our proposed framework, we participate the share task of CCKS2020 Task5-2: Document-level Event Arguments Extraction. On both Leaderboard A and Leaderboard B, PIEE takes the first place and significantly outperforms the other systems.