fraud detection

Explainable AI (XAI) has been delivering ground-breaking results in various domains. Emerging in parallel with the rise of powerful machine learning models, how to extend explainability to those black-box systems and promote its integrality have evolved into a blooming research field. Financial services are among the first to highlight the requirement for interpretable and fair algorithms, and the European Union has established the minimum regulatory and supervisory expectations for taking Transparency and Explainability of AI into national law. And XAI seems to be an inevitable future trend in anti-money laundering detection due to the booming applications of machine learning techniques. Thereat, a novel and all-round XAI-Prompted AI-Driven Security and Compliance Platform for Financial Transactions is proposed, providing AI decision uncertainty and traces, disclosing feature attributions, and automatically generating data analytic compliance documentation. A comprehensive comparison of manifold interpretation methods is also conducted to yield salient results, suggesting that a model-specific and post-hoc algorithm can prominently outperform others in this special financial domain. Moreover, adopting the innovative language model to automatically generate explanations of the prediction target is also explored successfully. Fargo is an interdisciplinary team, composed of researchers across computer science, machine learning, natural language processing, and financial regulation. They communicate and cooperate to make Fargo transparent and clearly documented its model, data, techniques, methodology and results. They receive a financial transaction that is not classified as suspicious or unusual.

A Managing Compliance in Financial Institution Security is required to ensure that sensitive financial transactions are carried out without incurring losses. Losses would be due to a number of factors whether internal or external, deliberate or accidental, and strongly dependent on correct and timely reactions in response to incidents. Events related to the assessment of online compliance can be classified in terms of the impact on the financial transactions e.g. fraud. Events exposing the transaction to fraud are used to generate rules to monitor cryptographic techniques applied to sensitive financial data, either as part of the transaction or for value recovery. Intelligent block-based fuzzy classification is used to determine different safety levels for different parts of the financial data thereby enabling secure trade with a lowest level of encryption and s igning overhead. This is facilitated by intelligent targeting of fraud events cutting through a range of signatures. Experiments with sets of fraud profiles derived from analysis of previous incidents employing branded-transaction card fraud are presented. In these experiments, monitoring rules are generated automatically using unsupervised neural gas clustering from detection blocks that are input to the intelligent classification engine. It is suggested that the versatility of G- Cluster in this area is demonstrated by the ability to adjust the fraud profile easily.

Real-time traffic congestion is a challenging problem in smartcities. An Intelligent Transportation System (ITS) is a big data application integrating sensor hardware and network technologies, which can intelligently capture traffic information, efficiently transform data into knowledge, and organize and manage transportation resources. Urban Traffic Control (UTC) is a critical component of ITS, analyzing real-time traffic information and coordinating traffic signal timing plans to optimize traffic network performance and improve vehicle travel speeds. However, traditional UTC based on centralized architecture would be challenged in data transmission, architecture malfunctions, system bottlenecks, etc. As a solution, the multi-Agent based RTC (ATC) with smart intersections is proposed. Additionally, more comprehensive traffic data can be captured with advanced detection techniques, and Regional Traffic Control (RTC) systems can be designed with advanced optimal control algorithms. Digital Banking (DB) Infrastructures powered with AI can be trained on historical data to simulate human understanding of patterns and trends when leveraging custom models tuned to understand banking transactions. Integrating artificial intelligence (AI) and automation into the digital banking infrastructure can result in a stable pipeline implementation of sorting transactions data for anomalies per the bank thresholds. Moreover, with the integration of AI systems, captured data can be analysed to study the traffic characteristics of the bank and determine how efficiently it is working. AI can also be used to examine this data, identify problematic data, perform risk prediction, timely tracking, and further determine whether it fits the standards of bank transactions. AI can warn of difficulties in bank transactions. When an unauthorised transaction is detected, that transaction can be prohibited in real-time. Furthermore, it can help to significantly increase banks' risk management levels, improved efficiency and a near-zero error output requirement of regular activity.