Incoming Transactions Research Articles

Research on automatic pricing and replenishment strategy of vegetable commodities based on ARIMA algorithm

In just a few years' time, supermarkets have transformed from a novelty into a mainstream channel that unifies the retail world. Since superstores sell vegetables with a wide variety of types, different origins, and shorter freshness periods, the incoming transaction time of vegetables is often in the early morning, so superstores usually replenish their stocks on a daily basis according to the historical sales and demand of each commodity. First, this paper visualizes the historical data of vegetable commodity purchasing and pricing in superstores in order to observe the distribution characteristics and trends, and then analyzes the correlation between categories or individual products using statistical methods such as correlation factors and covariance. To predict replenishment and pricing strategies for the coming week, this paper analyzes the relationship between overall sales and cost-plus pricing for each vegetable category, using given sales data to establish the relationship between sales volume and price for each category. Based on the ARIMA predicted sales model and given costs, the optimal replenishment quantities and pricing strategies were determined using an optimization algorithm.

A Proposed Approach to Integrate Application Security Vulnerability Data with Incidence Response Systems

This paper has proposed a method to develop an attack tree, from application vulnerability data discovered through tests and scans and correlation analysis using incoming transaction requests monitored by a Web Application Firewall (WAF) tool. The attack tree shows multiple pathways for an attack to shape through vulnerability linkages and a deeper analysis of the Common Weakness Enumeration (CWE) and Common Vulnerability Exposure (CVE) mapping to individual vulnerabilities. By further relating to a parent, peer, or child CWE (including CWEs that follow another CWE and in some cases precede other CWEs) will provide more insight into the attack patterns. These patterns will reveal a multi-vulnerability, multi-application attack pattern which will be hard to visualize without data consolidation and correlation analysis. The correlation analysis tied to the test and scan data supports a vulnerability lineage starting from incoming requests to individual vulnerabilities found in the code that traces a possible attack path. This solution, if automated, can provide threat alerts and immediate focus on vulnerabilities that need to be remedied as a priority. SOAR (Security Orchestration, Automation, and Response), XSOAR (Extended Security Orchestration, Automation, and Response), SIEM (Security Information and Event Management), and XDR (Extended Detection and Response) are more constructed to suit networks, infrastructure and devices, and sensors; not meant for application security vulnerability information as collected. So, this paper makes a special case that must be made for integration of application security information as part of threat intelligence, and threat and incident response systems.

Secure Scan -Analysis of Credit Card Fraud Detection Using Machine Learning

Credit Card usage has been drastically increased across the world , now people believe in going cashless and are completely dependent on online transactions .The credit card has made the digital transaction easier and nowadays credit card frauds are drastically increasing in numbers compared to earlier times . A powerful fraud detection system is required to stop these frauds . Fraud detection is the process of monitoring the transaction behaviour of a cardholder to detect whether an incoming transaction is authentic and authorised or not otherwise it will be detected as illicit .Machine learning -based fraud detection systems rely on machine learning algorithms that can be trained with historical data and can perform classification , regression or finding the patterns among the data . Keywords: Credit card machine learning , fraud detection ,historical data, algorithms.

Addressing the Transaction Validation Issue in IOTA Tangle: A Tip Selection Algorithm Based on Time Division

IOTA is a new public chain system specifically designed for the Internet of Things (IoT), which provides strong support for the high concurrency, scalability, and zero handling fees of the IoT. The distributed ledger of IOTA, called the tangle, adopts a Directed Acyclic Graph (DAG) structure. However, compared to the single-chain architecture, the tangle is more complex and highly vulnerable to security threats. The existing transaction verification methods still cannot simultaneously meet the need for accelerating approval speed and improving security to resist illegal transactions, such as lazy tips and permanent tips. In this work, we propose TDTS, a tip-selection algorithm based on time division to improve the efficiency of transaction verification. The main idea of the algorithm is to quickly determine two tips of an incoming transaction that need to be confirmed by sorting tip values in a time slot. It shortens the transaction verification time and reduces the number of lazy tips and permanent tips. A comprehensive theoretical analysis confirmed the effectiveness of our proposed algorithm. Based on 1000 IOTA nodes, the evaluations showed that TDTS can select tips quickly like URTS and resist lazy tips like MCMC.

EFFECTIVE FRAUD DETECTION IN BLOCKCHAIN USING XGBOOST WITH RANDOM FOREST

To solve the issue of fraud and abnormalities in the Bitcoin network, we offer a model. Here, we classify transactions based on integrated and fraudulent transaction patterns using machine learning methods like XGboost and Random Forest (RF). Then, future incoming transactions are predicted using the trained dataset. To identify fraudulent transactions, the authors use blockchain technology with machine learning algorithms. The proposed model performs a security analysis of the proposed smart contract to show the system's robustness and determines the precision and AUC of the models to gauge accuracy. To guard against assaults and vulnerabilities on the suggested system, the authors additionally suggest an attacker model. Overall, as financial technology advances, the proposed approach seeks to offer a more secure method for spotting fraud in the Bitcoin network. The authors assert that their suggested system's use of machine learning and blockchain technology may successfully identify and stop fraudulent transactions.

An improved differential evolution algorithm for quantifying fraudulent transactions

Identification of fraudulent credit card transactions is a complex problem mainly due to the following factors: 1) The relative behavior of customers and fraudsters may alter over time. 2) The ratio of legitimate to fraudulent transactions is highly imbalanced, and 3) Investigators examine a small segment of transactions in a reasonable time frame. Researchers have proposed various algorithms to identify potential fraud in a new incoming transaction. However, these approaches require significant human investigator effort and are sometimes misleading. To address this issue, this paper proposes an improved multiobjective differential evolution (DE) algorithm to estimate the distribution of fraudulent transactions in a set of new incoming transactions, referred to as quantifying fraudulent transactions. Our paper has three major novelties. First, we present the problem formulation of cost-based feature selection with maximum quantification ability. Second, we improve the DE by applying effective trial vector generation algorithms to the random control parameter settings to exploit the advantage of individual DE variants. Third, we develop the maximum-relevancy-minimum-redundancy-based Pareto refining operator to enhance the self-learning ability of individuals in Pareto solutions. We compare our approach against four other modifications of DE and five state-of-the-art evolutionary algorithms on real-time credit datasets in streaming and non-streaming frameworks using hyper-volume, two-set coverage, and spread performance metrics.

Credit Card Fraud Detection Using LSTM

As credit card becomes the most popular payment mode particularly in the online sector, the fraudu- lent activities using credit card payment technologies are rapidly increasing as a result. The purpose of this work is to develop a novel system for credit card fraud detection based on sequential modeling of data, using attention mechanism Long Short Term Mem- ory(LSTM) deep Recurrent Neural Networks(RNN) and Synthetic Minority Oversampling Technique Edited Nearest Neighbour(SMOTE-ENN). The pro- posed approach aims to capture the historic purchase behavior of credit card holders with the goal of im- proving fraud detection accuracy on new incoming transactions. Experiments show that our proposed model gives strong results and its accuracy is quite high. keywords: Credit Card, SMOTE-ENN, FraudDetection, Machine learning,LSTM.

CIP- Efficient Method for Mining Frequent Itemsets from Data streams using Landmark Window Model

Continuous stream transactions like network monitoring, retail market data analysis and stock market prediction need the “frequent patterns” to be detected recurrently. Literature suggests that several pattern mining solutions are being developed over years. Still lot of challenges need to be addressed due to rapidness in generation of continuous, unbounded and ordered data real time. Hence extraction of frequent patterns from recent data will improve the analysis of stream data. In this article, a new landmark window model CIP (candidate indexing and pruning) is considered for mining the datasets. CIP allows us to mine over entire history of data streams, which improves the accuracy. This article also proposes the candidate indexed sub (CIS)-tree scheme to extract the essential information from each incoming transactions of data streams. Our proposal is compared with the existing “improved data stream mining” (ISDM) for maximal frequent itemsets algorithm. Extensive experimental analyses prove the superiority of the proposed CIP over the popular ISDM in terms of accuracy and time complexity for high-speed data stream. This article also covers up a case study where the proposed approach is applied for an application called “web prefetching”.

Investigating the Impact of Consensus Algorithm on Scalability in Blockchain Systems

In the current era, blockchain has emerged as one the best and promising technology. All the cryptocurrencies have also gained a lot of popularity around the globe which are based on blockchain technology. Blockchain provides a distributed architecture, in which transactions are verified by different validators using different algorithms and then are stored in distributed ledger. The verification of transactions is done using consensus algorithms which verifies that incoming transaction is correct and reliable by different distributed nodes working in a peer-to-peer network. Consensus algorithms ensure the integrity and security of blockchain. There are various types of consensus algorithms used in blockchain technology which are used depending on the architecture and usage, some of the consensus algorithms are Proof of Work (PoW), Proof of Stake (PoS) etc. The Proof of Work algorithm is most widely used across the globe by the community. It is used by many popular cryptocurrency networks like Litecoin and Bitcoin. It requires larger computation power while verifying transactions. The selection of a consensus algorithm is one the most important parts of blockchain, as the consensus mechanism is considered to be the core of a network. It is easier to predict and guarantee the security, reliability, fault tolerance, and recoverability of the system if the correct consensus protocol is selected. A single algorithm can never fulfill all the requirements, there is always a tradeoff in the selection of consensus algorithms. Therefore, it is very important to select the best suited consensus algorithm for the network as the consensus mechanism validates transactions without any third-party platform and prevents malicious activities in the network. This paper investigates the comparison among types of consensus algorithms and their effectiveness and viability.

Utilizing Prediction Intervals for Unsupervised Detection of Fraudulent Transactions: A Case Study

Money laundering operations have a high negative impact on the growth of a country’s national economy. As all financial sectors are increasingly being integrated, it is vital to implement effective technological measures to address these fraudulent operations. Machine learning methods are widely used to classify an incoming transaction as fraudulent or non-fraudulent by analyzing the behaviour of past transactions. Unsupervised machine learning methods do not require label information on past transactions, and a classification is made solely based on the distribution of the transaction. This research presents three unsupervised classification methods: ordinary least squares regression-based (OLS) fraud detection, random forest-based (RF) fraud detection and dropout neural network-based (DNN) fraud detection. For each method, the goal is to classify an incoming transaction amount as fraudulent or non-fraudulent. The novelty in the proposed approach is the application of prediction interval calculation for automatically validating incoming transactions. The three methods are applied to a real-world dataset of credit card transactions. The fraud labels available for the dataset are removed during the model training phase but are later used to evaluate the performance of the final predictions. The performance of the proposed methods is further compared with two other unsupervised state-of-the-art methods. Based on the experimental results, the OLS and RF methods show the best performance in predicting the correct label of a transaction, while the DNN method is the most robust method for detecting fraudulent transactions. This novel concept of calculating prediction intervals for validating an incoming transaction introduces a new direction for unsupervised fraud detection. Since fraud labels on past transactions are not required for training, the proposed methods can be applied in an online setting to different areas, such as detecting money laundering activities, telecommunication fraud and intrusion detection.

“Get Haircut” Application based on Mobile Android Using React Native Framework

Salon or Barbershop is one of the businesses that engaged in services. At this time, hair care is one of the appearance factors that are often considered by both men and women. This is further strengthened by the increase in the salon or barbershop business in Cirebon. Every time the number of customers at the salon or barbershop is increasing and of course it creates problems, such as, regarding reservations (Booking) and also incoming transaction reports. From these problems, we need a system that can handle these problems. Get Haircut Application is an android-based application built using the React Native framework with the PHP programming language that can make it easier for salons or barbershops to receive orders from customers online. In addition, this application is able to process queue number data, service data and related data. This application is made using the Rational Unified Process (RUP) development method.

A Machine Learning and Blockchain Based Efficient Fraud Detection Mechanism.

In this paper, we address the problems of fraud and anomalies in the Bitcoin network. These are common problems in e-banking and online transactions. However, as the financial sector evolves, so do the methods for fraud and anomalies. Moreover, blockchain technology is being introduced as the most secure method integrated into finance. However, along with these advanced technologies, many frauds are also increasing every year. Therefore, we propose a secure fraud detection model based on machine learning and blockchain. There are two machine learning algorithms—XGboost and random forest (RF)—used for transaction classification. The machine learning techniques train the dataset based on the fraudulent and integrated transaction patterns and predict the new incoming transactions. The blockchain technology is integrated with machine learning algorithms to detect fraudulent transactions in the Bitcoin network. In the proposed model, XGboost and random forest (RF) algorithms are used to classify transactions and predict transaction patterns. We also calculate the precision and AUC of the models to measure the accuracy. A security analysis of the proposed smart contract is also performed to show the robustness of our system. In addition, an attacker model is also proposed to protect the proposed system from attacks and vulnerabilities.

Advancing Digital Payment Systems: Combining AI, Big Data, and Biometric Authentication for Enhanced Security

Digital payment solutions have recently gained extraordinary popularity across the globe. Many individuals in cities or urban areas have begun to use these payment systems for financial transactions. The combined use of different advanced technologies is indispensable for widespread adoption. Various obstacles to performing financial transactions using digital payment systems must be considered. Among these obstacles, security is the most remarkable point. Although this online payment system is fast and convenient, the chances of fraud are very high. A cybercriminal can hack into the system, stealing personal information like phone numbers and passwords. This article will focus on a new digital payment security system that will take advantage of artificial intelligence (AI), big data, and biometric authentication (BA). When using this security system, a transaction request will be sent. First, it will check whether the phone number is a registered user and if it is, further authentication will be carried out. The system will automatically authenticate the user’s identity with the help of facial recognition technology that will analyze the features of the face. Further, the user has to show various gestures that are analyzed by the system. This and other personal information will be converted into a number and then encrypted before being stored in the database. The incoming transaction request will be compared against the personal number. If the user is not unique, the transaction request will be immediately rejected. Secondly, if the number matches but the user is fraudulent, the transaction will also be rejected. Only if both are unique, the system will check for duplicate numbers among the other transactions for the particular period. If other numbers are not found, the transaction is executed; otherwise, it is still rejected. This is done to find out fake and auto-generated numbers. This security system will be helpful to ensure the authenticity of the user in digital payment systems.

Understanding Characteristics and System Implications of DAG-Based Blockchain in IoT Environments

Blockchain is starting to be deployed in the Internet of Things (IoT) to enable autonomous device-to-device transactions. However, traditional block-based blockchain techniques, such as Bitcoin and Ethereum, are not suitable for IoT environments due to their low throughput, high computation overhead, and costly transaction fee. To satisfy the requirements of IoT environments, directed-acyclic-graph (DAG)-based approaches, aiming to provide cheap blockchain services with low latency and high throughput, are emerging. This article presents a set of comprehensive experimental studies on IOTA, a representative DAG-based blockchain. We aim to exhibit its unique characteristics mainly from three aspects: 1) performance; 2) security; and 3) system robustness. We have developed a series of benchmark tools and judiciously selected typical configurations to perform experimental examinations with a real private IOTA network. Our studies reveal several interesting findings: 1) the throughput of IOTA is higher than the traditional block-based blockchain but far less than the reported thousands of transactions per second (TPS) in its whitepaper, even with scaling-up configurations; 2) the database query heavily impacts the performance of IOTA, even more than its mining [i.e., Proof of Work (PoW)] process; and 3) the system robustness of IOTA is closely related to the frequency of the incoming transactions while the milestone sent by the centralized coordinator has little effect on the system robustness. We make our benchmark tools public and expect our works can inspire system architects, application designers, and practitioners with new optimization directions and potential application cases for further exploration.

Sequential Pattern Mining Approach for Personalized Fraudulent Transaction Detection in Online Banking

Financial institutions face challenges of fraud due to an increased number of online transactions and sophisticated fraud techniques. Although fraud detection systems have been implemented to detect fraudulent transactions in online banking, many systems just use conventional rule-based approaches. Rule-based detection systems have a difficulty in updating and managing their rules and conditions manually. Additionally, generated from the few fraud cases, the rules are general rather than specific to each user. In this paper, we propose a personalized alarm model to detect frauds in online banking transactions using sequence pattern mining on each user’s normal transaction log. We assumed that a personalized fraud detection model is more effective in responding to the rapid increase in online banking users and diversified fraud patterns. Moreover, we focused on the fact that fraudulent transactions are very different from each user’s usual transactions. Our proposed model divides each user’s log into transactions, extracts a set of sequence patterns, and uses it to determine whether a new incoming transaction is fraudulent. The incoming transaction is divided into multiple windows, and if the normal patterns are not found in the consecutive windows, an alarm is sounded. We applied the model to a real-world dataset and showed that our model outperforms the rule-based model and the Markov chain model. Although more experiments on additional datasets are needed, our personalized alarm model can be applied to real-world systems.

Inventory Grouping to Support IT Business Management with the K-Means Algorithm

Inventory control is an important factor in a company that functions to maintain smooth production. Inventory control is the most important activity in the survival of the company. Fulfillment of stocks of goods or products and recording transactions manually. The fluctuating number of requests from consumers resulted in the stock that Gaptech computer had to prepare to become unstable. In addition, the various and many types of products made stock management inaccurate. by extracting data using one of the data mining methods, namely data grouping. In this study grouping sales reports on Gaptech computer, the data is grouped into 2 groups using one of the data grouping algorithms, namely the K-Means Algorithm. The K-Means algorithm is a non-hierarchical data clustering method that divides data into one or more clusters, so that data with the same characteristics are grouped in the same cluster. The grouping results are used to find out which product groups are in great demand and which are less desirable. The results of this study will produce a software that is created using a method of managing incoming transaction data so that it will make it easier for Gaptech computer store owners to manage stock items.

A novel framework for online transaction fraud detection system based on deep neural network

Since the introduction of online payment systems, people have started doing online transactions which has also led to the rise of fraudulent transactions causing loss of money to the users and created distrust in the usage of online payment systems. Hence, fraud detection systems are the need of the hour. Among the transactions occurring on daily basis, frauds are less in number as compared to the genuine transactions, so class imbalance naturally exists in fraud detection systems. In this research work, a novel framework for online transaction fraud detection system based on Deep Neural Network (DNN) has been proposed by utilizing algorithm-level method capable to detect frauds from imbalanced data and to maintain the overall performance of the model as well. The proposed system optimizes the decision threshold by utilizing the validation data efficiently for deciding whether an incoming transaction is a Fraud or not. For demonstration of the efficiency of our proposed system, three class imbalanced publicly available datasets have been used. Proposed system has shown better performance than data-level method. The results produced by the proposed fraud detection system have also been compared with existing machine learning techniques-based fraud detection systems. The experimental results show that the deep learning-based fraud detection system is more efficient for detecting frauds from imbalanced datasets having large number of input features as compared to the machine learning models.

Investigating the Impact of Delayed Mining upon Scaling Blockchain Applications under Malleability Attack—An e-Voting Scenario

Blockchain is a disruptive technology and has attracted significant attention with prominent applications across finance, medical and many other systems. Electronic voting or e-voting is one of the emerging applications of blockchain leveraging benefits such as integrity, and non-repudiation of data. Whilst existing research has focused on using blockchain for e-voting applications to achieve transparent and verifiable solutions, there exists a gap in study with respect to an in-depth investigation for the challenges surrounding the trade-off for scalability versus security in the context of transaction malleability attack when mining capability is compromised for the blockchain network. In order to present our research, we have used e-voting as an example application to demonstrate our investigations regarding the mentioned gap. The paper does not focus on building a blockchain based e-voting system. The study carries out empirical analysis by establishing blockchain networks with varying mining strength under an extreme load of incoming transactions to achieve a real world scenario of large blockchain based system. The developed system has then been exposed to transaction malleability attack while scaling throughput up to thousands of transactions. The findings reveal that blockchain networks upon scaling, are more vulnerable to transaction malleability attack while operating under lower mining strength as compared to the networks having higher mining power under same conditions. These research outcomes would help researchers and application architect to build highly secured and large scaled applications. To the best of our knowledge, there has not been any published empirical investigation present in the given context.

Understanding the Benefit of Being Patient in Payment Channel Networks

Scaling blockchain efficiency is crucial to its widespread usage in which the payment channel is one of the most prominent approaches. With payment channels and the network they construct, two users can move some transactions off-chain to avoid expensive and time-consuming on-chain settlements. Existing works are devoted to designing high-throughput payment channel networks (PCNs) or efficient PCN routing policies to reduce the fee charged by intermediate nodes. In this paper, we investigate the PCN routing from a different perspective by answering whether the routing fee of transactions can be saved through being a bit more patient. The key idea is to reorder the processing sequence of atomic transactions, other than to handle each of them separately and immediately. We present two mechanisms, one is periodic transaction processing and the other is purely strategic waiting. In the former, the incoming transactions in a short time interval are processed collectively. We formulate an optimization model to minimize their total routing fee and derive the optimal permutation of processing transactions as well as the routing policy for each of them. A <i>Shapley value</i> based scheme is presented to redistribute the benefit of reordering among the transactions efficiently and fairly. In the latter, we model the waiting time of a strategic transaction on a single payment channel as the <i>first passage time</i> problem in queuing theory when the transaction value is higher than the channel balance upon its arrival. By capturing the balance dynamics, we are able to calculate the recursive expression of waiting time distribution that is useful to gauge a user&#x0027;s cost of patience. Experimental results manifest that our cost redistribution mechanism can effectively save routing fees for all the transactions, and the waiting time distribution coincides with the model well.

Offline Scaling of IoT Devices in IOTA Blockchain

An increased pattern of hidden Internet of Things (IoT) devices has been observed. Due to the increased number of security attacks, a large number of IoT devices are disappearing from the public internet. Operating blockchain operations in such ad hoc connectivity becomes challenging. However, multiple past studies have pointed towards IOTA Distributed Ledger Technology (DLT) that closely caters to offline blockchain use cases. However, there has been little to no empirical study or introduction to time bounds on transaction confirmation. Therefore, this study explains what provisions the existing IOTA blockchain has to accommodate the increased pattern of hidden IoT devices, and if IOTA is truly sufficient as a solution. In summary, we approach research questions by analyzing the studies that explore the trend of offline IoT devices and evaluating the relevance of offline blockchains, assessing the IOTA specification and codebase around offline transaction-making capabilities and pointing out some bounds that IOTA blockchain nodes must follow towards incoming transactions. Furthermore, we confirm by experimental runs that outside and within the tight time bounds transactions in offline Tangle can become stale and not get confirmed, and the effective time-bound can be even less. Realizing the need for a better offline blockchain scalability solution.