Fraudulent Transactions Research Articles

Cloud-Based Transaction Fraud Detection: An In-depth Analysis of ML Algorithms

Context: Cloud-based services are increasingly central in financial technology, enabling scalable and efficient transactions. However, they also heighten vulnerability to fraud, challenging the security of online financial activities. Traditional fraud detection struggles against sophisticated tactics, highlighting the need for advanced, cloud-compatible solutions. Objectives: This study assesses machine learning (ML) algorithms' ability to detect fraud in cloud environments, focusing on Logistic Regression (LR), Decision Trees (DT), Random Forest (RF), Support Vector Machines (SVM), and XGBoost (XGB). It uses a comprehensive dataset to determine which ML model best identifies fraudulent transactions, aiming to optimize these models for accuracy, precision, and efficiency in real-time detection. Results: The XGBoost model outperformed others in fraud detection accuracy, with Random Forest and Decision Trees also showing high effectiveness. These models were particularly good at balancing precision and recall, minimizing false positives, and accurately identifying fraud in complex transaction patterns. Conclusion: ML, especially ensemble and boosting models like XGBoost and Random Forest, offers a strong approach to detecting transaction fraud in cloud-based financial systems. Their capacity to handle vast data volumes and adapt to new fraud patterns enhances cloud transaction security. Implication: The study provides a guide for financial and cloud services to implement sophisticated fraud detection systems. It emphasizes the importance of continual ML innovation to tackle digital finance fraud, suggesting that adopting these advanced ML models can significantly reduce transaction fraud risks, ensuring a secure, efficient, and trustworthy platform for users.

Fraudulent act: essence and legal regulation

The article examines current issues of science and practice regarding the definition of the essence, signs and legal regulation of a fraudulent transaction as one of the types of contracts in civil law. The importance of the category of “deeds” for civil law is emphasized. Modern scientific positions on understanding the essence of the “fraudulent act” categories are defined and analyzed. The author's vision of the understanding of the above-mentioned category is proposed, under which, in a general sense, a transaction is defined where the debtor (as one of the parties) performs dishonest actions in order to avoid fulfilling his or her obligation to the creditor. The necessity of forming a unified approach to defining the essence of the category of fraudulent transaction is emphasized. The principles of civil legislation, which are violated as a result of the conclusion of a fraudulent transaction, and the court practice on this issue are defined. The essence of the violation of the principle of good faith when concluding a fraudulent transaction is clarified. The need to make appropriate changes to the current civil legislation of Ukraine in order to standardize judicial practice and eliminate existing legislative gaps is emphasized. The judicial practice is analyzed and a review of court decisions regarding the fraudulent transaction and its essential conditions is carried out. It has been established that private law instruments should not be used by participants in civil transactions to avoid paying a debt (money, damages, damage) or to execute a court decision on debt collection (money, damages, damage) that has entered into force. The article notes that a fraudulent contract can be both paid and unpaid. A paid fraudulent contract has its own specifics and features that distinguish it from another fraudulent contract (for example, a free one). The right to evil is singled out as a sign of a committed fraudulent act. Further prospective directions of scientific research on certain issues of fraudulent transactions have been established.

A combined framework based on LSTM autoencoder and XGBoost with adaptive threshold classification for credit card fraud detection

The digital invasion of the banking and financial sectors made life simple and easy. Traditional machine learning models have been studied in credit card fraud detection, but these models are often difficult to find effective for unseen patterns. This study proposes a combined framework of deep learning and machine learning models. The long short term memory autoencoder (LSTMAE) with attention mechanism is developed to extract high-level features and avoid overfitting of the model. The extracted features serve as input to the powerful ensemble model XGBoost to classify legitimate and fraudulent transactions. As the focus of fraud detection is to increase the recall rate, an adaptive threshold technique is proposed to estimate an optimal threshold value to enhance performance. The experiment was done with the IEEE-CIS fraud detection dataset available in Kaggle. The proposed model with optimal threshold has an increase in predicting fraudulent transactions. The research findings are compared with conventional ensemble techniques to find the generalization of the model. The proposed LSTMAE-XGB w/ attention method attained a good precision and recall of 94.2 and 90.5%, respectively, at the optimal threshold of θ = 0.22. The experimental results proved that the proposed approach is better at finding fraudulent transactions than other cutting-edge models

Leveraging ML for Anomaly Detection in Healthcare Data Warehouses

The rapid emergence of digitalisation leads to unprecedented growth in the generation of the healthcare sector-particularly EHRs and medical equipment data. This extended the way for challenges for integrity in managing data and anomaly detection, including fraudulent transactions, medication errors, and many more system failures. Modern healthcare data poses a challenge to traditional methods of anomaly detection due to high and complex dimensionality. Machine learning provides a strong solution, using algorithms such as Gaussian Mixture Models, One-Class SVM and deep learning algorithms such as Autoencoders, and Recurrent Neural Networks in the detection of anomalies in healthcare data warehouse settings [1]. This study reports how ML can help advance care for patients, enable the validity of the data and reduce costs through real-time monitoring, fraud detection, and early detection of diseases. Applying anomaly detection through ML would most likely bring better operational performance, patient safety, and decision-making in health care for organizations as issues of poor data quality, lack of interpretability of models, and real-time detection would be addressed [2].

A Logistic Regression-based Model for Identifying Credit Card Fraudulent Transactions

A Logistic Regression-based Model for Identifying Credit Card Fraudulent Transactions

Deep learning-based credit card fraud detection in federated learning

The increased growth of various communication systems and computing technology enhanced the growth of regular and online transactions through credit cards. Similarly, it has also dramatically increased the frequency of fraudulent transactions, which significantly affects various organizations. Hence, it is necessary to implement precise techniques for secure transactions and the detection of certain credit card fraud transactions. In this investigation, a hybrid algorithmic optimization-based deep learning technique is designed. The Jellyfish Namib Beetle Optimization Algorithm-SpinalNet (JNBO-SpinalNet) is designed for fraudulent credit card transaction detection. The pre-processing of input data using quantile normalization is performed and the features are selected using various distance measures. The selected features are augmented using Bootstrapping method and SpinalNet is finally allowed to detect credit card frauds. The detection process in the classifier is improved by tuning the SpinalNet with the help of the designed JNBO model. The superiority of the designed fraudulent transaction detection method is estimated by using different evaluation parameters. The JNBO-SpinalNet model recorded higher performance with 89.10 % accuracy, 13.16 % loss function, 28.68 % Mean Square Error (MSE), 10.20 % False Positive Rate (FPR), 89.82 %, Mean Average Precision (MAP), and 53.56 % Root Mean Square Error (RMSE).

CREDIT CARD FRAUD DETECTION

It is important that credit card companies are able to recognize fraudulent credit card transactions so that customers are not charged for items that they did not purchase. In an era where digital transactions have become ubiquitous, the security of financial transactions is of paramount importance. The advent of machine learning and data science techniques offers promising avenues for enhancing fraud detection mechanisms. Analysing a dataset is a critical step in obtaining relevant insights from massive amounts of data. This research paper delves into the use case of Data science & Machine Learning and its applications for our major project. It goes into the use of Python as a powerful tool for data analysis, emphasizing its importance in dealing with complex datasets. Furthermore, the project investigates the many Python libraries used in data science and machine learning applications, the significance of data visualization with Libraries such as Seaborn and Matplotlib, etc. After which it goes on with the main work. This project of ours delves into the realm of credit card fraud detection, leveraging Python and its powerful libraries such as NumPy, Pandas, Seaborn, TensorFlow, and Matplotlib for comprehensive data analysis and visualization. Employing a host of machine learning algorithms including K-Nearest Neighbors, Logistic Regression, Random Forest, Decision Tree, and LDA, the project aims to tackle the challenge posed by highly unbalanced datasets, specifically transactions made by European cardholders in September 2013. By discerning fraudulent transactions accurately, this endeavour seeks to bolster the integrity of financial systems, safeguarding both customers and institutions from potential losses. Keywords: Python, pandas, seaborn, data science, machine learning.

A Comprehensive Survey on Fraud Detection Methods in Financial Transactions

Financial institutions have enormous hurdles as a result of fraudulent transactions, which makes the creation and application of strong detection techniques necessary. This research paper offers a thorough examination of the approaches currently in use for identifying fraudulent activity on different financial platforms. It examines both cutting-edge and conventional strategies, such as data mining, artificial intelligence, and machine learning algorithms, as well as statistical and rule-based systems. It also looks at how big data and real-time analytics may work together to improve detection accuracy. Future approaches in fraud detection research are also covered in this study, along with the advantages and disadvantages of these methods and the significance of adaptive learning models. Through an amalgamation of current developments and persistent obstacles, this assessment seeks to provide significant perspectives for scholars committed to battling financial deception. Key Words: Fraudulent transactions, financial platforms, rule-based systems, machine learning, data mining, real-time analytics, big data.

Supply chain fraud prediction with machine learning and artificial intelligence

As businesses undergo digital transformation, supply chain fraud poses an increasing threat, necessitating more sophisticated detection and prevention methods. This paper explores the application of machine learning (ML) and artificial intelligence (AI) in detecting and preventing supply chain fraud. The research design involves analyzing a dataset of supply chain operations and employing various ML algorithms to detect consumer-based fraud within the supply chain, which occurs when consumers partake in deceptive practices during the order process of e-commerce transactions. We analyzed 180,000 transactions from an international company recorded between 2015 and 2018. This study emphasises the necessity of human oversight in interpreting the results generated by these technologies. The implications of supply chain fraud on financial stability, legal standing, and reputation are discussed, along with the potential for ML technology to identify irregularities indicative of fraud. Descriptive findings highlight the prevalence of fraudulent transactions in specific payment types. The AI sequential and the CatBoost classifiers were the top-performing algorithms across all performance metrics. The top features to detect unusual orders are delivery status, payment type, and late delivery risks. The discussion emphasises the promising predictive capabilities of the ML and AI models and their implications for detecting supply chain fraud.

Cryptocurrency fraud detection through classification techniques

Ethereum and its native cryptocurrency, Ether, have played a worthy attention in the development of the blockchain and cryptocurrency space. Its programmability and smart contract capabilities have made it a foundational platform for decentralized applications and innovations across various industries. Because of its anonymous and decentralized structure, the hotheaded expansion of cryptocurrencies in the payment space has created both enormous potential and concerns related to cybercrime, including money laundering, financing terrorism, illegal and dangerous services. As more financial institutions attempt to integrate cryptocurrencies into their networks, there is an increasing need to create a more transparent network that can withstand these kinds of attacks. In this work, we are using different classification techniques, such as logistic regression (LR), random forest (RF), k-nearest neighbors (KNN), adaptive boosting (AdaBoost), and extreme gradient boosting (XGBoost) for Ethereum fraud detection. The dataset we are using includes rows of legitimate transactions done using the cryptocurrency Ethereum as well as known fraudulent transactions. The “XGBoost” model, which is noteworthy, detects variations that might attract notice and prevent potential issues in this chore.

ASA-GNN: Adaptive Sampling and Aggregation-Based Graph Neural Network for Transaction Fraud Detection

ASA-GNN: Adaptive Sampling and Aggregation-Based Graph Neural Network for Transaction Fraud Detection

Deep Learning based Credit Card Fraudulency Detection System

Abstract: Huge increase in the internet usage has been observed since last decade. It led to the emergence of services like ecommerce, tap and pay systems, online bill payment systems, etc. have proliferated and become more widely used. Due to various online payment options introduced by e- commerce and other numerous websites, the possibility of online fraud has risen drastically. Thus, due to an increase in fraud rates, research on analyzing and detecting fraud in online transactions has begun utilizing various machine learning techniques. The Deep Learning techniques viz., Convolutional Neural Network Architecture is used to detect credit card frauds in the proposed model. The Principal Component Analysis transformation gives a set of numerical input variables as output which are taken as the features to be considered. Due to confidentiality concerns, some of the original characteristics and background information about the data are not entirely disclosed. Features of credit card frauds must be chosen carefully as they play important role when deep learning techniques are used for credit card fraud detection. The TensorFlow and Keras are used for the development of the current proposed model. The proposed model aims to predict credit card frauds with 91.9% accuracy

How can Artificial Intelligence Techniques Effectively Enhance Credit Card Fraud Detection Systems?

The boom in Artificial Intelligence (AI) revolution is significantly transforming our everyday lives. Every aspect of technology, process, and system implements AI to provide a superior user experience, enhanced machine capabilities and advanced problem-solving and research capabilities. However, due to this technological revolution, rise in fraud has become an enormous challenge in the digital economy. This research paper aims to test different Machine Learning (ML) models to explore real-time fraud detection capabilities accurately, particularly for credit card fraud prevention systems. Technologies like online bank transfers and smartphone payments based on credit accounts are major contributors to fraudulent transactions. AI/ML models have proven to be industry-disruptors, robust, significantly faster and produce more accurate results. These advantages have led to launch of successful companies like OpenAI. This paper uses model metrics such as Supervised, Unsupervised, and Ensemble methods to improve the detection of unauthorized transactions for fraud detection. Models will be ranked for performance using accuracy metrics, F-1, and Area Under Curve (AUC) scores. While zero false rates are not yet achievable, this study aims to reach a reasonably low level by selecting an appropriate model.

CREDIT CARD FRAUD DETECTION USING MACHINE LEARNING AND DEPLOYMENT USING FLASK

Credit card fraud detection is a method which is design in such a way where fraudulent transactions can be identified with different algorithms present in the system. As, due to the presence of such a software, it would be easy for all to know the transactions occur that are legit or fraudulent in that particular credit card. The different algorithms which are being used are Random Forest Algorithm, Support Vector Machine and Isolation Forest Algorithm. The data is stored in the dataset for a temporary time till the software runs, once the software restarts the data will be lost. The future scope for such a project could be it where the data can be stored permanently in the dataset for future references of transactions occurring which would lead to legit or fraud transactions in the system.

Advanced risk management solutions for mitigating credit risk in financial operations

Advanced risk management solutions are essential for mitigating credit risk in financial operations, particularly in today's volatile economic environment. This Review explores the innovative approaches and technologies being utilized to enhance credit risk management and safeguard financial institutions against potential losses. Credit risk, the possibility that a borrower will default on their obligations, poses a significant threat to financial stability. Traditional methods of assessing and managing credit risk, such as credit scoring and historical data analysis, are no longer sufficient to address the complexities of modern financial markets. Advanced risk management solutions offer more robust and dynamic tools for identifying, assessing, and mitigating credit risk. One of the key advancements in this field is the integration of big data and machine learning algorithms. By analyzing vast amounts of data from diverse sources, financial institutions can gain deeper insights into borrower behavior, market trends, and economic indicators. Machine learning models can predict default probabilities with greater accuracy, allowing for proactive risk mitigation strategies. Additionally, real-time risk monitoring systems have become increasingly prevalent. These systems provide continuous oversight of credit portfolios, enabling financial institutions to detect early warning signs of potential defaults and take timely action. Advanced analytics and visualization tools facilitate the identification of emerging risks and the implementation of targeted interventions. Another crucial component of advanced risk management solutions is the use of stress testing and scenario analysis. These techniques simulate various economic conditions and assess the impact on credit portfolios, helping financial institutions prepare for adverse scenarios and develop contingency plans. Furthermore, blockchain technology is emerging as a promising tool for enhancing transparency and reducing fraud in credit transactions. By providing a secure and immutable record of credit histories and transactions, blockchain can improve trust and reliability in credit assessments. In conclusion, advanced risk management solutions are transforming the way financial institutions mitigate credit risk. By leveraging big data, machine learning, real-time monitoring, stress testing, and blockchain technology, financial institutions can achieve more accurate risk assessments and implement more effective risk mitigation strategies. These innovations not only enhance the stability and resilience of financial operations but also contribute to a more secure and trustworthy financial system.

The role of big data in detecting and preventing financial fraud in digital transactions

The role of big data in detecting and preventing financial fraud in digital transactions

Leveraging Cryptographic Hash Functions for Credit Card Fraud Detection

Credit card fraud remains a significant challenge in the financial industry, posing substantial financial losses to both consumers and businesses. Traditional fraud detection methods often rely on rule-based approaches and statistical models, which may struggle to keep pace with evolving fraud tactics and sophisticated cyber threats. In this paper, we propose a novel approach to credit card fraud detection leveraging cryptographic hash functions. Cryptographic hash functions offer robust security guarantees, including collision resistance and preimage resistance, making them well-suited for ensuring the integrity and authenticity of transaction data. Our proposed system employs cryptographic hash functions, such as SHA-256, to generate unique hash values for credit card transactions. These hash values serve as digital fingerprints of the transaction data, enabling secure verification and auditing of transactions on the blockchain. We conducted experiments using a dataset of 100,000 credit card transactions, evaluating the performance of our system in terms of accuracy, precision, recall, and F1-score. The results demonstrate the effectiveness of our approach in accurately identifying fraudulent transactions while minimizing false positives. Furthermore, we discuss the implications of our findings and explore future research directions, including the integration of advanced cryptographic techniques and blockchain technology to enhance the security and privacy of credit card transactions. Overall, our study underscores the importance of cryptographic hash functions in building robust and secure fraud detection systems capable of combating emerging fraud threats in the digital era.

ВИКОРИСТАННЯ МАШИННОГО НАВЧАННЯ ДЛЯ ОБРОБКИ ДАНИХ НА МІКРОКОМП’ЮТЕРАХ

Machine learning is a data analysis method that automates the construction of an analytical model. It is a branch of artificial intelligence based on the idea that machines should be able to learn and adapt through experience. It is closely related to computational statistics, which makes predictions based on statistical data collected by a computer. It is sometimes confused with data mining, but that is more focused on analyzing intelligence data, while machine learning contains complex algorithms that are used mainly for prediction, where machine learning concentrates on predicting based on already known attributes obtained through training data, then data mining focuses more on finding unknown attributes in any data. attributes in any data. Machine learning applications may be associated with spam filtering, optical character recognition, and search engines. Machine learning uses data to determine which algorithm is best for generating results based on the quantity, quality, and nature of the data. This data is then used for intelligent analysis in various ways, such as recommendation systems such as similar products on eBay, personalized content on google plus pages, video ads on sites such as YouTube, and last but not least, suggestions from friends on Facebook. Machine learning and artificial intelligence can be used to solve business problems, namely: Automating repetitive tasks such as data entry, document processing and customer service. This frees up employees' time for more complex work. Optimization of business processes. ML/AI can analyze data to identify inefficiencies and optimize business processes, increasing company productivity. Service personalization. ML/AI helps analyze customer data to provide them with personalized offers, recommendations and support. Automation of answers to questions and anticipation of customer needs. Detection of fraudulent transactions and cyber security. Risk management.

K‐Fuse: Credit card fraud detection based on a classification method with a priori class partitioning and a novel feature selection strategy

AbstractOnline transactions have become the dominant and most popular form of online payment in today's digital economy. Due to the growing popularity of e‐commerce and the convenience it offers, both consumers and businesses are rapidly adopting online transactions. Notably, credit cards have become one of the most popular and standard online payment methods. However, it should be noted that credit card transactions are not without challenges. In particular, detecting and preventing fraudulent transactions is a major concern of the online payment system. It is difficult to find an effective detection model that can detect the new patterns created by fraudsters, due to the constant evolution of their methods to exploit the vulnerability of current security protocols. These fraud patterns are evolving and may not correspond to existing documented models, leading to a reduction in their identification. In addition, the customer's behavior can affect the model detection as it is susceptible to change based on factors such as economic conditions, trends, and individual circumstances. When consumers deviate from their typical behavior, the model may generate false alerts, thereby reducing its ability to differentiate between legitimate and fraudulent transactions. This article presents a new supervised detection model, called K‐Fuse, which introduces an unsupervised phase in order to detect fraud patterns that may correspond to innovative models introduced by fraudsters. K‐Fuse is a supervised classification method that fuses three steps consisting of (i) unsupervised clustering to identify hidden patterns of transactions in a dataset, (ii) a novel feature selection criterion based on the unsupervised results, and (iii) supervised classification to exploit the results of clustering and feature selection to predict new transactions as fraudulent or legitimate.

Digital banking fortification: a real-time isolation forest architecture for detecting online transaction fraud

Since the use of the Internet has increased exponentially, numerous organizations, including the financial industry, offer services online. As a result, financial scams are expanding in quantity and complexity worldwide, resulting in massive revenue losses and making digital fraudulent transactions a severe issue. Abnormal attempts and illegal access are instances of these dangers that fraudulent activity detection systems must identify. Machine learning and data mining approaches have been extensively used to address this issue in recent years. However, these approaches must be enhanced regarding real-time detection speed, tackling enormous amounts of data, and finding undiscovered attack patterns. Consequently, the present study provides a real-time architecture for averting and identifying digital transaction fraud, which relies on the Isolation Forest (IForest) approach and big data analytic tools, including Spark Streaming, sparkling water, Kafka, and PostgreSQL. This architecture seeks to improve present detection strategies by increasing accuracy for detection when considering enormous amounts of data. Two real datasets of online transactional fraud are used to assess the proposed architecture, and the findings are compared to relevant studies. The investigation results showed that IForest performed flawlessly, achieving an accuracy of 0.99 in two datasets.