Improving Federated Learning through Abnormal Client Detection and Incentive

Data sharing and privacy protection are made possible by federated learning,which allows for continuous model parameter sharing between several clients and a central server.Multiple reliable and high-quality clients must participate in practical applications for the federated learning global model to be accurate,but because the clients are independent,the central server cannot fully control their behavior.The central server has no way of knowing the correctness of the model parameters provided by each client in this round,so clients may purposefully or unwittingly submit anomalous data,leading to abnormal behavior,such as becoming malicious attackers or defective clients.To reduce their negative consequences,it is crucial to quickly detect these abnormalities and incentivize them.In this paper,we propose a Federated Learning framework for Detecting and Incentivizing Abnormal Clients(FL-DIAC)to accomplish efficient and security federated learning.We build a detector that introduces an auto-encoder for anomaly detection and use it to perform anomaly identification and prevent the involvement of abnormal clients,in particular for the anomaly client detection problem.Among them,before the model parameters are input to the detector,we propose a Fourier transform-based anomaly data detectionmethod for dimensionality reduction in order to reduce the computational complexity.Additionally,we create a credit scorebased incentive structure to encourage clients to participate in training in order tomake clients actively participate.Three training models(CNN,MLP,and ResNet-18)and three datasets(MNIST,Fashion MNIST,and CIFAR-10)have been used in experiments.According to theoretical analysis and experimental findings,the FL-DIAC is superior to other federated learning schemes of the same type in terms of effectiveness.

MSEs Credit Risk Assessment Model Based on Federated Learning and Feature Selection

Federated learning has been used extensively in business inno-vation scenarios in various industries.This research adopts the federated learning approach for the first time to address the issue of bank-enterprise information asymmetry in the credit assessment scenario.First,this research designs a credit risk assessment model based on federated learning and feature selection for micro and small enterprises(MSEs)using multi-dimensional enterprise data and multi-perspective enterprise information.The proposed model includes four main processes:namely encrypted entity alignment,hybrid feature selection,secure multi-party computation,and global model updating.Secondly,a two-step feature selection algorithm based on wrapper and filter is designed to construct the optimal feature set in multi-source heterogeneous data,which can provide excellent accuracy and interpretability.In addition,a local update screening strategy is proposed to select trustworthy model parameters for aggregation each time to ensure the quality of the global model.The results of the study show that the model error rate is reduced by 6.22%and the recall rate is improved by 11.03%compared to the algorithms commonly used in credit risk research,significantly improving the ability to identify defaulters.Finally,the business operations of commercial banks are used to confirm the potential of the proposed model for real-world implementation.

Real-Time Fraud Detection Using Machine Learning

Credit card fraud remains a significant challenge, with financial losses and consumer protection at stake. This study addresses the need for practical, real-time fraud detection methodologies. Using a Kaggle credit card dataset, I tackle class imbalance using the Synthetic Minority Oversampling Technique (SMOTE) to enhance modeling efficiency. I compare several machine learning algorithms, including Logistic Regression, Linear Discriminant Analysis, K-nearest Neighbors, Classification and Regression Tree, Naive Bayes, Support Vector, Random Forest, XGBoost, and Light Gradient-Boosting Machine to classify transactions as fraud or genuine. Rigorous evaluation metrics, such as AUC, PRAUC, F1, KS, Recall, and Precision, identify the Random Forest as the best performer in detecting fraudulent activities. The Random Forest model successfully identifies approximately 92% of transactions scoring 90 and above as fraudulent, equating to a detection rate of over 70% for all fraudulent transactions in the test dataset. Moreover, the model captures more than half of the fraud in each bin of the test dataset. SHAP values provide model explainability, with the SHAP summary plot highlighting the global importance of individual features, such as “V12” and “V14”. SHAP force plots offer local interpretability, revealing the impact of specific features on individual predictions. This study demonstrates the potential of machine learning, particularly the Random Forest model, for real-time credit card fraud detection, offering a promising approach to mitigate financial losses and protect consumers.

The Effectiveness of Self-regulated Learning Strategies on Chinese College Students' English Learning

The purpose of this paper is to argue the effectiveness of self-regulated learning in English education in Chinese college classroom instruction. A study is given to show whether the introduction of self-regulated learning can help improve Chinese college students' English learning, and help them perform better in the National English test-CET-4 (College English Test Level-4,).

Credit Card Fraud Detection on Original European Credit Card Holder Dataset Using Ensemble Machine Learning Technique

The proliferation of digital payment methods facilitated by various online platforms and applications has led to a surge in financial fraud,particularly in credit card transactions.Advanced technologies such as machine learning have been widely employed to enhance the early detection and prevention of losses arising frompotentially fraudulent activities.However,a prevalent approach in existing literature involves the use of extensive data sampling and feature selection algorithms as a precursor to subsequent investigations.While sampling techniques can significantly reduce computational time,the resulting dataset relies on generated data and the accuracy of the pre-processing machine learning models employed.Such datasets often lack true representativeness of realworld data,potentially introducing secondary issues that affect the precision of the results.For instance,undersampling may result in the loss of critical information,while over-sampling can lead to overfitting machine learning models.In this paper,we proposed a classification study of credit card fraud using fundamental machine learning models without the application of any sampling techniques on all the features present in the original dataset.The results indicate that Support Vector Machine(SVM)consistently achieves classification performance exceeding 90%across various evaluation metrics.This discovery serves as a valuable reference for future research,encouraging comparative studies on original dataset without the reliance on sampling techniques.Furthermore,we explore hybrid machine learning techniques,such as ensemble learning constructed based on SVM,K-Nearest Neighbor(KNN)and decision tree,highlighting their potential advancements in the field.The study demonstrates that the proposed machine learning models yield promising results,suggesting that pre-processing the dataset with sampling algorithm or additional machine learning technique may not always be necessary.This research contributes to the field of credit card fraud detection by emphasizing the potential of employing machine learning models directly on original datasets,thereby simplifying the workflow and potentially improving the accuracy and efficiency of fraud detection systems.

To supervise or to self‑supervise:a machine learning based comparison on credit supervision

This study investigates the need for credit supervision as conducted by on-site banking supervisors.It builds on a real bank on-site credit examination to compare the performance of a hypothetical self-supervision approach,in which banks themselves assess their loan portfolios without external intervention,with the on-site banking supervision approach of the Central Bank of Brazil.The experiment develops two machine learning classification models:the first model is based on good and bad ratings informed by banks,and the second model is based on past on-site credit portfolio examinations conducted by banking supervision.The findings show that the overall performance of the on-site supervision approach is consistently higher than the performance of the self-supervision approach,justifying the need for on-site credit portfolio examination as conducted by the Central Bank.

基于PU learning的信用卡交易安全监管研究

目前信用卡套现手段复杂多变、虚假交易形态层出不穷,在仅有账户级套现标签数据的基础上,信用卡套现管理面临着与客户交互过程难以获取其真实交易情况的业务痛点。为了探究一种精准的信用卡虚假交易监管方法,以商业银行信用卡系统的套现账户交易标签数据为研究对象,建立了基于PUlearning(positive-unlabeledlearning)的信用卡单笔交易安全识别模型。所提模型在样本数据标注中引入了间谍(Spy)机制,随机抽取高可靠套现交易正样本100万笔及待标注的交易样本130万笔,借助学习器预测结果分布对难以判别的非套现交易负样本进行标注,以获取相对可靠的负样本标签120万笔。基于上述正样本及标注得到的负样本数据,构建了信用卡客户属性信息、额度使用情况及交易偏好特征等120个候选变量,通过变量重要性筛选得到入模变量近50个,利用XGBoost二分类算法进行模型开发预测。结果显示,所提模型对信用卡套现虚假交易的识别准确率为94.20%,群体稳定性指标(PSI)为0.10%,表明基于PUlearning的单笔交易安全识别模型能够实现对信用卡虚假交易的有效监测。该研究改进了机器学习二分类算法在难以获取高精度样本标签数据场景下的模型判别性能,为商业银行信用卡系统交易安全监控提供了新方法。

Research on Personal Credit Risk Assessment Model Based on Instance-Based Transfer Learning

Personal credit risk assessment is an important part of the development of financial enterprises. Big data credit investigation is an inevitable trend of personal credit risk assessment, but some data are missing and the amount of data is small, so it is difficult to train. At the same time, for different financial platforms, we need to use different models to train according to the characteristics of the current samples, which is time-consuming. In view of these two problems, this paper uses the idea of transfer learning to build a transferable personal credit risk model based on Instance-based Transfer Learning (Instance-based TL). The model balances the weight of the samples in the source domain, and migrates the existing large dataset samples to the target domain of small samples, and finds out the commonness between them. At the same time, we have done a lot of experiments on the selection of base learners, including traditional machine learning algorithms and ensemble learning algorithms, such as decision tree, logistic regression, xgboost and so on. The datasets are from P2P platform and bank, the results show that the AUC value of Instance-based TL is 24% higher than that of the traditional machine learning model, which fully proves that the model in this paper has good application value. The model’s evaluation uses AUC, prediction, recall, F1. These criteria prove that this model has good application value from many aspects. At present, we are trying to apply this model to more fields to improve the robustness and applicability of the model;on the other hand, we are trying to do more in-depth research on domain adaptation to enrich the model.

Impact of learning through credit and value creation on the efficiency of Japanese commercial banks

This study investigates the learning curve of commercial banks regarding the efficiency of credit and value creation.However,current empirical methods for accessing the learning curve in organizations are not suitable for use in financial institutions.Considering bank-specific characteristics,we introduce a dynamic learning curve using a cost function adjusted to capture learning-by-doing in banks.Using the model,we test several hypotheses on the impact of bank intermediary experience(learning)on the efficiency of credit and value creation in Japanese commercial banks.The findings show that bank intermediary learning significantly improves the cost efficiency gain in the gross value created,total credit created,and investment.However,bank intermediary experience has no significant effect on the efficiency of the economic value created for all the banks analyzed.These findings have practical implications for evaluating cost dynamics in bank credit and value creation,risk management,lending to the real sector,and shareholder value creation.

Measuring the model risk-adjusted performance of machine learning algorithms in credit default prediction

Implementing new machine learning(ML)algorithms for credit default prediction is associated with better predictive performance;however,it also generates new model risks,particularly concerning the supervisory validation process.Recent industry surveys often mention that uncertainty about how supervisors might assess these risks could be a barrier to innovation.In this study,we propose a new framework to quantify model risk-adjustments to compare the performance of several ML methods.To address this challenge,we first harness the internal ratings-based approach to identify up to 13 risk components that we classify into 3 main categories—statistics,technology,and market conduct.Second,to evaluate the importance of each risk category,we collect a series of regulatory documents related to three potential use cases—regulatory capital,credit scoring,or provisioning—and we compute the weight of each category according to the intensity of their mentions,using natural language processing and a risk terminology based on expert knowledge.Finally,we test our framework using popular ML models in credit risk,and a publicly available database,to quantify some proxies of a subset of risk factors that we deem representative.We measure the statistical risk according to the number of hyperparameters and the stability of the predictions.The technological risk is assessed through the transparency of the algorithm and the latency of the ML training method,while the market conduct risk is quantified by the time it takes to run a post hoc technique(SHapley Additive exPlanations)to interpret the output.

A high‑dimensionality‑trait‑driven learning paradigm for high dimensional credit classification

To solve the high-dimensionality issue and improve its accuracy in credit risk assessment,a high-dimensionality-trait-driven learning paradigm is proposed for feature extraction and classifier selection.The proposed paradigm consists of three main stages:categorization of high dimensional data,high-dimensionality-trait-driven feature extraction,and high-dimensionality-trait-driven classifier selection.In the first stage,according to the definition of high-dimensionality and the relationship between sample size and feature dimensions,the high-dimensionality traits of credit dataset are further categorized into two types:100<feature dimensions<sample size,and feature dimensions≥sample size.In the second stage,some typical feature extraction methods are tested regarding the two categories of high dimensionality.In the final stage,four types of classifiers are performed to evaluate credit risk considering different high-dimensionality traits.For the purpose of illustration and verification,credit classification experiments are performed on two publicly available credit risk datasets,and the results show that the proposed high-dimensionality-trait-driven learning paradigm for feature extraction and classifier selection is effective in handling high-dimensional credit classification issues and improving credit classification accuracy relative to the benchmark models listed in this study.

Certification and Conversion Mode of Learning Achievement Based on Credit Bank under the Background of Higher Vocational Enrollment Expansion

Credit bank system is a very important management mode in current higher vocational education,and it is also an important means for the Ministry of Education to promote China's modern education reform.This paper combines the specific background of higher vocational enrollment expansion,expounds the practical significance of the credit bank system in the training of the expanded enrollment talents,and explores the methods and rules of the authentication and transformation of the learning achievement of the expanded enrollment students under the system.In order to achieve convergence of different types of learning results,smooth talent growth channel,a useful exploration is carried out.

Predicting Credit Card Transaction Fraud Using Machine Learning Algorithms

Credit card fraud is a wide-ranging issue for financial institutions, involving theft and fraud committed using a payment card. In this paper, we explore the application of linear and nonlinear statistical modeling and machine learning models on real credit card transaction data. The models built are supervised fraud models that attempt to identify which transactions are most likely fraudulent. We discuss the processes of data exploration, data cleaning, variable creation, feature selection, model algorithms, and results. Five different supervised models are explored and compared including logistic regression, neural networks, random forest, boosted tree and support vector machines. The boosted tree model shows the best fraud detection result (FDR = 49.83%) for this particular data set. The resulting model can be utilized in a credit card fraud detection system. A similar model development process can be performed in related business domains such as insurance and telecommunications, to avoid or detect fraudulent activity.

The Role of Self-regulation in Blended Learning

Self-regulation is crucial to learners’learning outcomes in a blended education context.This paper first discusses its definitions and importance,then explores factors affecting self-regulation,and finally puts forward several ways to improve learners’self-regulation.

Understanding the effects of structured self-assessment in directed,self-regulated simulation-based training of mastoidectomy:A mixed methods study

Objective:Self-directed training represents a challenge in simulation-based training as low cognitive effort can occur when learners overrate their own level of performance.This study aims to explore the mechanisms underlying the positive effects of a structured self-assessment intervention during simulation-based training of mastoidectomy.Methods:A prospective,educational cohort study of a novice training program consisting of directed,self-regulated learning with distributed practice(5x3 procedures)in a virtual reality temporal bone simulator.The intervention consisted of structured self-assessment after each procedure using a rating form supported by small videos.Semi-structured telephone interviews upon completion of training were conducted with 13 out of 15 participants.Interviews were analysed using directed content analysis and triangulated with quantitative data on secondary task reaction time for cognitive load estimation and participants’self-assessment scores.Results:Six major themes were identified in the interviews:goal-directed behaviour,use of learning supports for scaffolding of the training,cognitive engagement,motivation from self-assessment,selfassessment bias,and feedback on self-assessment(validation).Participants seemed to self-regulate their learning by forming individual sub-goals and strategies within the overall goal of the procedure.They scaffolded their learning through the available learning supports.Finally,structured self-assessment was reported to increase the participants’cognitive engagement,which was further supported by a quantitative increase in cognitive load.Conclusions:Structured self-assessment in simulation-based surgical training of mastoidectomy seems to promote cognitive engagement and motivation in the learning task and to facilitate self-regulated learning.

RankXGB-Based Enterprise Credit Scoring by Electricity Consumption in Edge Computing Environment

With the rapid development of the internet of things(IoT),electricity consumption data can be captured and recorded in the IoT cloud center.This provides a credible data source for enterprise credit scoring,which is one of the most vital elements during the financial decision-making process.Accordingly,this paper proposes to use deep learning to train an enterprise credit scoring model by inputting the electricity consumption data.Instead of predicting the credit rating,our method can generate an absolute credit score by a novel deep ranking model–ranking extreme gradient boosting net(rankXGB).To boost the performance,the rankXGB model combines several weak ranking models into a strong model.Due to the high computational cost and the vast amounts of data,we design an edge computing framework to reduce the latency of enterprise credit evaluation.Specially,we design a two-stage deep learning task architecture,including a cloud-based weak credit ranking and an edge-based credit score calculation.In the first stage,we send the electricity consumption data of the evaluated enterprise to the computing cloud server,where multiple weak-ranking networks are executed in parallel to produce multiple weak-ranking results.In the second stage,the edge device fuses multiple ranking results generated in the cloud server to produce a more reliable ranking result,which is used to calculate an absolute credit score by score normalization.The experiments demonstrate that our method can achieve accurate enterprise credit evaluation quickly.

Leveraging Geospatial Technology for Smallholder Farmer Credit Scoring

According to the Food and Agriculture Organization of the United Nations (FAO), there are about 500 million smallholder farmers in the world, and in developing countries, such farmers produce about 80% of the food consumed there;their farming activities are therefore critical to the economies of their countries and to the global food security. However, these farmers face the challenges of limited access to credit, often due to the fact that many of them farm on unregistered land that cannot be offered as collateral to lending institutions;but even when they are on registered land, the fear of losing such land that they should default on loan payments often prevents them from applying for farm credit;and even if they apply, they still get disadvantaged by low credit scores (a measure of creditworthiness). The result is that they are often unable to use optimal farm inputs such as fertilizer and good seeds among others. This depresses their yields, and in turn, has negative implications for the food security in their communities, and in the world, hence making it difficult for the UN to achieve its sustainable goal no.2 (no hunger). This study aimed to demonstrate how geospatial technology can be used to leverage farm credit scoring for the benefit of smallholder farmers. A survey was conducted within the study area to identify the smallholder farms and farmers. A sample of surveyed farmers was then subjected to credit scoring by machine learning. In the first instance, the traditional financial data approach was used and the results showed that over 40% of the farmers could not qualify for credit. When non-financial geospatial data, i.e. Normalized Difference Vegetation Index (NDVI) was introduced into the scoring model, the number of farmers not qualifying for credit reduced significantly to 24%. It is concluded that the introduction of the NDVI variable into the traditional scoring model could improve significantly the smallholder farmers’ chances of accessing credit, thus enabling such a farmer to be better evaluated for credit on the basis of the health of their crop, rather than on a traditional form of collateral.

基于特征提取和集成学习的个人信用评分方法

在大数据蓬勃发展的今天,信息经济已经深入社会方方面面,个人信用体系建设的重要性越发突出。而传统的信用体系存在覆盖率不足、评价特征维度高、数据孤岛等问题,为了解决以上问题,提出一种基于特征提取和Stacking集成学习的个人信用评分方法(PSL-Stacking)。方法首先利用Pearson和Spearman系数对数据进行初始化分析剔除不相关数据,利用LightGBM算法进行特征选择,减少冗余特征对模型的影响;其次选取XGboost、LightGBM、Random Forest以及Huber回归等算法,利用Stacking集成学习技术构造个人信用评分模型。最后,以某电信数据为研究对象,对该上述模型的个人信用评分能力进行验证。实验结果得出上述模型具有很好的预测能力,能够准确的对用户信用进行评分,有效降低企业遭受金融欺诈、团伙套利等问题的风险。

基于区块链技术的国家学分银行系统研究与设计

区块链作为一种新兴技术,具有去中心化和不可篡改等特征,它能为学分银行建设提供技术支持。突破以往从理论上论证区块链技术服务于学分银行建设的可行性,以国家开放大学推进学分银行建设实践为依托,系统介绍了区块链+学分银行的应用案例。同时,对基于区块链技术的国家学分银行系统可能存在的技术风险进行分析,并提出应对方案。

基于学习成果应用的学分银行建设探索——以上海市终身教育学分银行为例

学习成果的应用是学分银行存在和发展的基石。学分银行中学习成果应用价值发挥有利于促进学习者终身学习,为构建服务全民终身学习的教育体系赋能助力。当前学分银行面临学习成果“只存不用”的困境,上海市终身教育学分银行在探索学习成果应用价值层面建构了学习成果应用共同体、搭建了学习成果应用平台,创新了学习成果应用模式,为攻克学习成果应用困境提供了经验参考。未来学分银行可从激发学习成果高频应用主体需求、内外联动建立全纳的学习成果应用数据库和基于多维数据分析开拓学习成果新应用等拓宽学习成果应用路径,为实现学分银行内生发展开拓新势能。