User Credit Research Articles

A Deep Federated Learning-Based User Credit Evaluation Model Under Financial Internet of Things Scenarios

With the rapid development of Internet of Things (IoT) technology and the digital transformation of the financial industry, the financial IoT is becoming an important trend in the future financial field. In the era of financial IoT, a large amount of data information is recorded by sensors and devices, which poses new challenges and opportunities for user credit evaluation. In this context, conventional deep learning-based user credit evaluation methods often cannot meet privacy needs. The paper combines the privacy security ability of federated learning with deep learning, and proposes a deep federated learning-based user credit evaluation model under financial IoT scenarios. First, a particle swarm optimization-based backpropagation neural network algorithm is formulated to extract user credit evaluation features, in order to obtain user behavior patterns and credit features. Then, the XGBoost algorithm is employed to output credit evaluation results. As for the training process, the thought of federated learning is integrated to distribute the model to individual participants. In such mode, the model can be updated and trained without exposing user data to the central cloud. The experiments are conducted on real-world data to assess the proposal’s performance. The results show that the proposed credit evaluation framework can achieve better accuracy, under the guarantee of user privacy.

Utilizing the LightGBM algorithm for operator user credit assessment research

Mobile Internet user credit assessment is an important way for communication operators to establish decisions and formulate measures, and it is also a guarantee for operators to obtain expected benefits. However, credit evaluation methods have long been monopolized by financial industries such as banks and credit. As supporters and providers of platform network technology and network resources, communication operators are also builders and maintainers of communication networks. Internet data improves the users credit evaluation strategy. This paper uses the massive data provided by communication operators to carry out research on the operators user credit evaluation model based on the fusion LightGBM algorithm. First, for the massive data related to user evaluation provided by operators, key features are extracted by data preprocessing and feature engineering methods, and a multi-dimensional feature set with statistical significance is constructed; then, linear regression, decision tree, LightGBM, etc. The machine learning algorithm builds multiple basic models to find the best basic model; finally, integrates Averaging, Voting, Blending, Stacking and other integrated algorithms to refine multiple fusion models, and finally establish the most suitable fusion model for operator user evaluation.

Credit Risk Assessment Using a Combined Approach of Supervised and Unsupervised Learning

In the financial industry, credit scoring is a crucial tool for assessing credit risk. The study aims to enhance the accuracy and reliability of credit scoring by combining supervised and unsupervised learning methods. We propose an integrated model that combines Kohonen's Self-Organizing Maps (SOM) with the Random Forest algorithm to provide a more comprehensive analysis of credit card user data. Key features for model training were identified through feature selection and extraction. Experimental results show that the integrated model improved the AUC from 0.82 to 0.89, increased user satisfaction from a score of 3.8 to 4.35, and boosted usage rates by 12.5%. Additionally, the integrated model significantly enhanced the discrimination and prediction accuracy of user credit risk. These findings indicate that the combination of unsupervised learning with Kohonen's Self-Organizing Maps and supervised learning with Random Forest can effectively improve the accuracy of credit scoring, providing financial institutions with a more reliable tool for credit risk assessment.

An FTwNB Shield: A Credit Risk Assessment Model for Data Uncertainty and Privacy Protection

Credit risk assessment is an important process in bank financial risk management. Traditional machine-learning methods cannot solve the problem of data islands and the high error rate of two-way decisions, which is not conducive to banks’ accurate credit risk assessment of users. To this end, this paper establishes a federated three-way decision incremental naive Bayes bank user credit risk assessment model (FTwNB) that supports asymmetric encryption, uses federated learning to break down data barriers between banks, and uses asymmetric encryption to protect data security for federated processes. At the same time, the model combines the three-way decision methods to realize the three-way classification of user credit (good, bad and delayed judgment), so as to avoid the loss of bank interests caused by the forced division of uncertain users. In addition, the model also incorporates incremental learning steps to eliminate training samples with poor data quality to further improve the model performance. This paper takes German Credit data and Default of Credit Card Clients data as examples to conduct simulation experiments. The result shows that the performance of the FTwNB model has been greatly improved, which verifies that it has good credit risk assessment capabilities.

A multi-time scale schedulable capacity evaluation method for stations considering user wishes

As a flexible resource, electric vehicles (EVs) can realize various auxiliary services such as peak shaving, reactive power optimization, fault recovery, and emergency power supply. It is essential to quickly and accurately evaluate the EV schedulable capacity to realize auxiliary services. In this context, this paper first simulates EV charging demand using trip chain and Monte Carlo (MC) methods based on the 2017 National Household Travel Survey (NHTS2017) results to provide a multi-time scale estimation of EV charging station schedulable capacity to provide a data foundation. Then, considering incentive price, price sensitivity, and user credit, a demand response model is established to describe the uncertainty of user response and constraints such as differentiated demand on both sides of the grid user, battery charging and discharging state, battery loss, and response uncertainty are integrated to establish a multi-time scale evaluation model of the schedulable capacity of EV charging stations. Finally, the effectiveness of the proposed evaluation model is verified by simulation, and the effects of site area, incentive price, and dispatching time scale on the maximum schedulable capacity of EV charging stations are analyzed.

Importance–performance and potential gain of food delivery apps: in view of the restaurant partner perspective

PurposeThe food industry is continuously developing its online services called food delivery applications (FDAs). This study aims to evaluate FDA's importance–performance and identify strategies to maximize its potential gains from a business partner's perspective.Design/methodology/approachData are collected from 208 FDA partners in Indonesia. Importance–performance analysis (IPA) is applied to evaluate the FDA feature and extended the theory of potential gain in customer value (PGCV) to achieve potential gains from FDA business partners.FindingsThis study provides a clear and measurable direction for future research to develop FDA performance. Owning customer data, revenue sharing and competitive advantage are the most potential gains from joining the FDA from the business partner perspective.Research limitations/implicationsThe respondents are restaurants from the micro, small, and medium enterprises levels. Further research should involve middle to upper level restaurants to discover all business partners' perceptions. This will be very helpful for FDA providers interested in improving the best performance for all their partners.Practical implicationsFDA providers must focus on improving and maintaining the features of owning customer data, revenue sharing, competitive advantage, stable terms and conditions, customer interface, building customer loyalty, online presence, user credit rating, promotion and offers, delivery service and sales enhancement to increase consumer satisfaction and meet the expectations desired by business partners.Originality/valueThis research provides a meaningful theoretical foundation for future work. It extends the theory of PGCV using the value of a partner perspective as a substitute for customer value; hence, the authors call it a potential gain in partner value.

Leveraging the State-of-the-Art Machine-Learning Techniques for Amplifying the Credit Card Fraud Detection

In this paper mainly focused on credit card fraud detection for in real world. Initially collect the credit card datasets for trained dataset. Then will provide the user credit card queries for testing data set. After classification process of random forest algorithm using to the already analyzing data set and user provide current dataset. Finally optimizing the accuracy of the result data. Then will apply the processing of some of the attributes provided can find affected fraud detection in viewing the graphical model visualization. The performance of the techniques is evaluated based on accuracy, sensitivity, and specificity, precision. The results indicate about the optimal accuracy for Decision tree are 98.6% respectively. Keywords: credit card fraud detection, random forest algorithm, fraud detection, visualization, Decision tree.

DETECTING CREDIT CARD FRAUD USING MACHINE LEARNING

Bank fraud is "The unauthorized use of an individual's confidential information to make purchases or withdraw funds from a user's account." E-commerce is growing rapidly, and the world is moving towards digitization, cashless transactions, the use of credit cards, the number of users is rapidly increasing, and with it the number of frauds associated with it. Due to the development of technology and the increase in the number of online transactions, fraud is also increasing, leading to huge financial losses. Therefore, effective methods to reduce losses are needed. In addition, scammers find ways to steal the user's credit card information by sending fake SMS and calls, as well as by masquerade attacks, phishing attacks, and so on. This article aims to use several machine learning algorithms such as Support Vector Machine (SVM), Decision Tree, Bayesian Belief Networks, Logistic Regression, k-Nearest Neighbor (Knn), and Artificial Neural Network (ANN) to predict the occurrence of fraud. In addition, we differentiate between the implemented supervised machine learning and deep learning methods to distinguish between fraudulent and non-fraudulent transactions.

Fuzzy MLKNN in Credit User Portrait

Aiming at the problems of subjective enhancement caused by the discretization of credit data and the lack of a multi-dimensional portrait of credit users in the current credit data research, this paper proposes an improved Fuzzy MLKNN multi-label learning algorithm based on MLKNN. On the one hand, the subjectivity of credit data after discretization is weakened by introducing intuitionistic fuzzy numbers. On the other hand, the algorithm is improved by using the corresponding fuzzy Euclidean distance to realize the multi-label portrait of credit users. The experimental results show that Fuzzy MLKNN performs significantly better than MLKNN on credit data and has the most significant improvement on One Error.

Smart Garage Utilizing Internet of Things (IoT)

People in urban regions face a daily problem finding parking slot for their vehicles. So, this study develops a network architecture based on Internet of Things platform. A system improves the efficiency of the current cloud-based smart-parking system. This study suggested a system that assists users in automatically finding a free parking space at the lowest cost. With an application, a user can request to reserve a parking slot. The application moves a driver directly into the free slot in a garage. Also, it utilizes the distance and total number of free spaces in each garage to determine the user nearest parking slot and cost. The garage slot cost will be charged by user credit once the user entered the garage or reserved a parking slot through the application. The system proposed a novel system which picks up a parking slot, reserves, and pays for it through mobile application. The proposed system can easily be deployed in the actual world.

TCA: Telecom Credit Assessment Assisted by Edge Intelligence

With China’s economic transformation into a high-quality development stage, the importance of credit system construction has become increasingly prominent. The problems existing in the current telecom credit system include: (1) insufficient coverage of credit features; (2) traditional credit assessment models are difficult to reflect user credit status objectively, comprehensively and timely; (3) user demand for credit management and credit services are ignored. Due to these deficiencies, a new multi-level credit system is necessary to meet the rapid development of market economy. Telecom operators have large amount of precious data, with the advantages of large-scale, high-precision and data-diversity, which can provide new ideas for the construction of credit system. This work focuses on the current problems and conducts research as follows: design a Telecom Credit Assessment Model based on Boosting and Stacking ensemble techniques, called TCAMBS, to improve the evaluation accuracy, and to select the best model according to the experimental results. On the one hand, this work can promote the innovation of telecom credit assessment models and provide new ideas for the construction of the credit system. On the other hand, this work will also help telecom operations to improve the quality of telecom credit services.

Deep learning based loan eligibility prediction with Social Border Collie Optimization

PurposeThe bank is termed as an imperative part of the marketing economy. The failure or success of an institution relies on the ability of industries to compute the credit risk. The loan eligibility prediction model utilizes analysis method that adapts past and current information of credit user to make prediction. However, precise loan prediction with risk and assessment analysis is a major challenge in loan eligibility prediction.Design/methodology/approachThis aim of the research technique is to present a new method, namely Social Border Collie Optimization (SBCO)-based deep neuro fuzzy network for loan eligibility prediction. In this method, box cox transformation is employed on input loan data to create the data apt for further processing. The transformed data utilize the wrapper-based feature selection to choose suitable features to boost the performance of loan eligibility calculation. Once the features are chosen, the naive Bayes (NB) is adapted for feature fusion. In NB training, the classifier builds probability index table with the help of input data features and groups values. Here, the testing of NB classifier is done using posterior probability ratio considering conditional probability of normalization constant with class evidence. Finally, the loan eligibility prediction is achieved by deep neuro fuzzy network, which is trained with designed SBCO. Here, the SBCO is devised by combining the social ski driver (SSD) algorithm and Border Collie Optimization (BCO) to produce the most precise result.FindingsThe analysis is achieved by accuracy, sensitivity and specificity parameter by. The designed method performs with the highest accuracy of 95%, sensitivity and specificity of 95.4 and 97.3%, when compared to the existing methods, such as fuzzy neural network (Fuzzy NN), multiple partial least squares regression model (Multi_PLS), instance-based entropy fuzzy support vector machine (IEFSVM), deep recurrent neural network (Deep RNN), whale social optimization algorithm-based deep RNN (WSOA-based Deep RNN).Originality/valueThis paper devises SBCO-based deep neuro fuzzy network for predicting loan eligibility. Here, the deep neuro fuzzy network is trained with proposed SBCO, which is devised by combining the SSD and BCO to produce most precise result for loan eligibility prediction.

An Effective Credit Evaluation Mechanism with Softmax Regression and Blockchain in Power IoT

This paper is oriented to the credit investigation scenario of power grid supply chain enterprises and proposes a blockchain user credit assessment method based on improved Softmax regression in Power IoT. This method first designs a credit-rating mechanism that meets industry characteristics based on business needs. Second, it proposes a user credit evaluation model based on the blockchain architecture. Finally, the improved Softmax regression algorithm is used to train the proposed credit evaluation model, which effectively solves the credit rating. The multiclassification problem has achieved the goal of categorizing the credit rating of the enterprise. The simulation results show that the credit evaluation mechanism proposed in this paper can accurately evaluate the multisource credit data that lacks trust foundation and effectively realize the credit rating of power grid material supply chain enterprises. The credit evaluation mechanism proposed for Power IoT in this paper could have high potential for entity identity authentication and rating for securing mobile video communications.

An Online Transfer Learning Framework With Extreme Learning Machine for Automated Credit Scoring

Automated Credit Scoring (ACS) is the process of predicting user credit based on historical data. It involves analysing and predicting the association between the data and particular credit values based on similar data. Recently, ACS has been handled as a machine learning problem, and numerous models were developed to address it. In this paper, we address ACS issues concerning credit scoring in a batch of machine learning problems, namely, feature irregularities due to empty features in many records, class imbalance due to non-uniform statistical distributions of the records between classes, and concept drift due to changing statistical characteristics concerning certain classes and features with time. Considering the limited credit scoring data volume, we propose to address the challenge using the Transfer Learning with Lag (TLL) algorithm based on embedded shallow neural networks that enable knowledge transfer when the number of active features changes. Knowledge transfer is based on lags having an adaptive length that is changed based on performance change feedback. Furthermore, the framework proposes classifier aggregation and the chunk balancing mechanism for handling class imbalance. An evaluation was conducted using the Lending club, German, Default, and PPDai datasets. The results show the superiority of the proposed algorithm over the benchmarks in terms of the majority of classification metrics concerning both time series and overall results. TLL offered improvements of 58.6% and 28.2% over FA-OSELM and OSELM using the Lending club dataset.

FlexFashion: E-Commerce with Advance Features

Abstract: The aim of this website is to enhance the shopping experience for customers using an advance feature of recommending matching outfits using the colorgram module. Flex Fashion is an interactive e-commerce solution providing users with an excellent fashion platform. The e - commerce platform displays an order cut-off time and a delivery window for the products selected by the consumer. The e - commerce platform does not settle with the user's credit supplier until the item chosen by the consumer is picked from inventory but before it is delivered. As a result, the buyer can make adjustments to the purchase online. There are different categories on the home page available to filter the products based on your style and needs. In addition to the apparels for both men and women one will find flexible variety of accessories and daily essential products. The e - commerce platform does not settle with the user's credit supplier until the item chosen by the consumer is picked from inventory but before it is delivered. As a result, the buyer can make adjustments to the purchase online. Once the customer decides to submit a purchase order, there is a track us page where just by adding ordered and email the user can track there order. This is to facilitate all people who are busy with their work and have no time to get their desired apparels. We are here to provide user with all the best and suitable clothing for sale. If once register into our site, then anyone can avail the benefit with our latest updates of the sale. Keywords: Colorgram, Tracker

Behavioral Based Credit Card Fraud Detection

Credit card fraud is a significant threat in the BFSI sector. This credit card fraud detection system analyzes user behavioral patterns and their location to identify any unusual patterns. This consists of user characteristics, which includes user spending styles as well as standard user geographic places to verify his identity. One of the user behavior patterns includes spending habits, usage patterns, etc. This system deals with user credit card data for various characteristics, which includes user country, usual spending procedures. Based upon previous transactions information of that person, the system recognizes unusual patterns in the payment method. The fraud detection system contains the past transaction data of each user. Based on this data, it identifies the standard user behavior patterns for individual users, and any deviation from those normal user patterns becomes a trigger for the detection system. If it detects any unusual patterns, then user will be required to undergo the security verification, which identifies the original user using QR code recognition system. In case of any unusual activity, the system not only raises alerts but it will block the user after three invalid attempts.

RETRACTED ARTICLE: Trust model simulation of cross border e-commerce based on machine learning and Bayesian network

In recent years, many scholars at home and abroad have devoted themselves to the research of e-commerce trust, which has even become a hot topic in scientific research. When we explore the factors that affect consumers' choice of e-commerce transactions, e-commerce trust is undoubtedly an important breakthrough in this issue. E-commerce trust can have a profound impact on the popularity of e-commerce among customers and the future development. But in the current environment, consumers are still unfamiliar or skeptical about e-commerce. Based on these problems, this paper proposes a cross-border e-commerce trust model based on the existing trust evaluation technology, machine learning theory and the cloud model in Bayesian network technology to prevent fraud. With the support of cloud model, trust evaluation method has been improved. Trust has changed from qualitative to quantitative, and the relevant data can reflect the nature of trust more intuitively and objectively. In addition, the model can also start from the enterprise, according to the e-commerce enterprise for consumer privacy protection, information trading and other services to conduct a comprehensive evaluation of the enterprise, giving consumers a clearer choice. In addition, the evaluation quantity and adaptive time window algorithm are also introduced in the evaluation of e-commerce enterprises. All kinds of measures are to prevent illegal businesses from misleading consumers by credit fraud and speculation. Through the above methods, researchers can understand the trust degree of users for cross-border e-commerce, and put forward relevant methods to improve user credit. At the same time, through a variety of theoretical methods such as machine learning and Bayesian network, we can provide enterprises with more market and user demand information, make them aware of the shortcomings and constantly improve their business in the future, so as to improve the trust of users to enterprises, and attract a wider user group, so as to provide more ideas and guidance for the development of cross-border e-commerce.

Distributed diffusion fusion cooperative spectrum sensing based on reinforcement learning

The openness and complexity of wireless channels make collaborative spectrum sensing vulnerable to malicious users[1]. Therefore, it is very important to identify the attributes of malicious users before collaborative spectrum awareness networks make data fusion decisions. In this paper, a method combining reinforcement learning and cognitive user credit model is proposed, in which the maximum and minimum eigenvalues of signals are used as the initial information for exchange, and the whole sensing network tends to diffuse and fuse nodes with high credit. Finally, the convergence value of the whole network is compared with the decision threshold to complete collaborative spectrum sensing. By combining with consensus fusion network and traditional collaborative sensing algorithm, the proposed method can effectively improve the convergence speed of fusion network and shorten the sensing time on the premise of effectively identifying malicious users[2], so as to improve the spectrum sensing performance and make the collaborative sensing network more adaptive and stable.

Robust Ordinal Regression: User Credit Grading with Triplet Loss-Based Sampling

With the development of social media sites, user credit grading, which served as an important and fashionable problem, has attracted substantial attention from a slew of developers and operators of mobile applications. In particular, multi-grades of user credit aimed to achieve (1) anomaly detection and risk early warning and (2) personalized information and service recommendation for privileged users. The above two goals still remained as up-to-date challenges. To these ends, in this article, we propose a novel regression-based method. Technically speaking, we define three natural ordered categories including BlockList , GeneralList , and AllowList according to users’ registration and behavior information, which preserve both the global hierarchical relationship of user credit and the local coincident features of users, and hence formulate user credit grading as the ordinal regression problem. Our method is inspired by KDLOR ( kernel discriminant learning for ordinal regression ), which is an effective and efficient model to solve ordinal regression by mapping high-dimension samples to the discriminant region with supervised conditions. However, the performance of KDLOR is fragile to the extreme imbalanced distribution of users. To address this problem, we propose a robust sampling model to balance distribution and avoid overfit or underfit learning, which induces the triplet metric constraint to obtain hard negative samples that well represent the latent ordered class information. A step further, another salient problem lies in ambiguous samples that are noises or located in the classification boundary to impede optimized mapping and embedding. To this problem, we improve sampling by identifying and evading noises in triplets to obtain hard negative samples to enhance robustness and effectiveness for ordinal regression. We organized training and testing datasets for user credit grading by selecting limited items from real-life huge tables of users in the mobile application, which are used in similar problems; moreover, we theoretically and empirically demonstrate the advantages of the proposed model over established datasets.

Welfare impacts of rural credit and saving program in Kurfa Chele district, eastern Ethiopia: a propensity score matching estimation

PurposeThis study is conducted to evaluate the impact of rural credit on farm household income and food security.Design/methodology/approachA multistage random sampling procedure is implemented to select 180 (82 credit user and 98 non-credit user) households from Kurfa Chele district, eastern Ethiopia. The Propensity Score Matching technique is used to estimate the impact of credit utilization on the welfare indicators.FindingsThe results of the econometric model estimation show that participation in the rural credit program was positively influenced by a household's educational status, family size, voluntary saving and participation in training related to credit and saving. On the contrary, livestock holding and extension advice were found to negatively affect participation. Furthermore, participation in rural credit program is found to increase annual income by 59% and calorie intake by 21%. These are significant results implying that participation in the rural credit and saving program improved household welfare in the study area.Originality/valueThis study is important because it shows the welfare impact of making credit program available to potential users in the study area. Moreover, for effectiveness of the credit program it is necessary to target households with relatively larger family size and those with relatively better education (to induce change among the wider farming community). It is also essential to focus on the saving behavior of the program beneficiaries and enhancing the management system by ensuring that sufficient development agents are in place.