The work considers various multivariate statistical techniques in their modifications and applications to management, information systems, economics, decision making, and marketing research problems. The methods include eigenvectors for many-way matrices, dual partial lest squares, modified factor and cluster analyses, and enhanced canonical correlation analysis. These approaches have been applied in numerous real projects and proved to be useful for data analysts, managers, and decision makers in solving practical problems.
{"title":"Multivariate statistical methods: A brief review on their modifications and applications","authors":"S. Lipovetsky","doi":"10.3233/mas-220017","DOIUrl":"https://doi.org/10.3233/mas-220017","url":null,"abstract":"The work considers various multivariate statistical techniques in their modifications and applications to management, information systems, economics, decision making, and marketing research problems. The methods include eigenvectors for many-way matrices, dual partial lest squares, modified factor and cluster analyses, and enhanced canonical correlation analysis. These approaches have been applied in numerous real projects and proved to be useful for data analysts, managers, and decision makers in solving practical problems.","PeriodicalId":35000,"journal":{"name":"Model Assisted Statistics and Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46048847","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Currently, the Algerian health system is facing the fourth wave of COVID-19 in which the number of recovered cases grows exponentially each day due to the COVID-19 Omicron variant. According to the Algerian National Institute of Public Health (ANIPH), it was reported 168 668 confirmed cases and 4 189 deaths till 29 July, 2021. In this work, we aim to utilize supervised Machine Learning (ML) based models in an attempt to forecast the future trend of the disease in Algeria. To that end, we use three forecasting models: Facebook Prophet, LSTM and ARIMA. Forecasting results of the 90 future days are provided. The used dataset contains the confirmed and death cases collected from the daily Epidemiological Situation (ES), published by ANIPH, from 19 April 2020 to 29 July 2021. The forecasting accuracy of the models are assessed and compared using several statistical assessment criteria. The results show that ARIMA outperforms Facebook Prophet and LSTM in the case of confirmed cases. However, LSTM shows best performance in the case of death cases. This study shows clearly that the pandemic spread is still in progress and protection measures like contact restriction and lockdown should be strictly applied especially with the appearance of the COVID-19 Delta and Omicron variants.
{"title":"Machine Learning-based forecasting models for COVID-19 spread in Algeria","authors":"Mohamed Sedik Chebout, Oussama Kabour","doi":"10.3233/mas-220013","DOIUrl":"https://doi.org/10.3233/mas-220013","url":null,"abstract":"Currently, the Algerian health system is facing the fourth wave of COVID-19 in which the number of recovered cases grows exponentially each day due to the COVID-19 Omicron variant. According to the Algerian National Institute of Public Health (ANIPH), it was reported 168 668 confirmed cases and 4 189 deaths till 29 July, 2021. In this work, we aim to utilize supervised Machine Learning (ML) based models in an attempt to forecast the future trend of the disease in Algeria. To that end, we use three forecasting models: Facebook Prophet, LSTM and ARIMA. Forecasting results of the 90 future days are provided. The used dataset contains the confirmed and death cases collected from the daily Epidemiological Situation (ES), published by ANIPH, from 19 April 2020 to 29 July 2021. The forecasting accuracy of the models are assessed and compared using several statistical assessment criteria. The results show that ARIMA outperforms Facebook Prophet and LSTM in the case of confirmed cases. However, LSTM shows best performance in the case of death cases. This study shows clearly that the pandemic spread is still in progress and protection measures like contact restriction and lockdown should be strictly applied especially with the appearance of the COVID-19 Delta and Omicron variants.","PeriodicalId":35000,"journal":{"name":"Model Assisted Statistics and Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48706024","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. S. Aravinth, S. Srithar, M. Senthilkumar, J. Senthilkumar
Regression analysis is a widely used statistical technique for estimating the relationship between two variables. These two variables are called independent and dependent variables. The regression techniques are classified into two broad categories such as linear and logistic regression. Based on the input dataset, these two techniques are chosen and implemented. Many organizations and institutions are trying to use the decision support system for extracting the relationship between the employees’ salaries based on the target achieved and the years of experience. In this paper, the relationship extraction between two variables is analysed and studied. Based on the Experience, the salary of employees is predicted. Here the model extracts the relationship among the variables first, next to that forecasting of new observations is carried out. In this phased approach, the data pre-processing is carried out to clean the noise on the dataset. Followed by, fitting the model to train the train set and testing test. The third phase predicts the results based on the two variables to draw some observations. As a final step, visualization is employed on training and testing datasets. To implement this proposed work, the employee database from an organization is considered. This dataset contains 115 technical and non-technical staff details with their profile information.
{"title":"Regression analysis based decision support system with relationship extraction","authors":"S. S. Aravinth, S. Srithar, M. Senthilkumar, J. Senthilkumar","doi":"10.3233/mas-220002","DOIUrl":"https://doi.org/10.3233/mas-220002","url":null,"abstract":"Regression analysis is a widely used statistical technique for estimating the relationship between two variables. These two variables are called independent and dependent variables. The regression techniques are classified into two broad categories such as linear and logistic regression. Based on the input dataset, these two techniques are chosen and implemented. Many organizations and institutions are trying to use the decision support system for extracting the relationship between the employees’ salaries based on the target achieved and the years of experience. In this paper, the relationship extraction between two variables is analysed and studied. Based on the Experience, the salary of employees is predicted. Here the model extracts the relationship among the variables first, next to that forecasting of new observations is carried out. In this phased approach, the data pre-processing is carried out to clean the noise on the dataset. Followed by, fitting the model to train the train set and testing test. The third phase predicts the results based on the two variables to draw some observations. As a final step, visualization is employed on training and testing datasets. To implement this proposed work, the employee database from an organization is considered. This dataset contains 115 technical and non-technical staff details with their profile information.","PeriodicalId":35000,"journal":{"name":"Model Assisted Statistics and Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41501661","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Being a combination of several techniques and processing methods, the Data Analytics technology is emerged as an effective tool for the enterprises to obtain relevant results for strategic management and implementation. In the present circumstances the digital world is extensively using the advanced data analytic techniques for extracting knowledge or useful insights from the various kind of data such as Internet of Things (IoT) data, health data, business data, security data, and many more, which can be used for smart decision-making in various application domains. In the areas of data science, advanced analytical methods including machine learning modelling can provide actionable insights or deeper knowledge about data, which makes the computing process automatic and smart. Inspired by the mentioned facts, an international conference on “Data Analytics and Computational Techniques” had been organized and hosted in VIT Bhopal University in fully virtual mode during December 2021. The seven full length papers for this special issue were selected among all the accepted papers in the conference by the MASA Guest Editors Hemant Kumar Nashine, Reena Jain, Neha Choubey and Mayank Sharma, based on the relevance to the journal and the reviews papers. The papers went through the normal journal-style review process and they appear in the present form after implementing the valuable suggestions by the Co-Editor-in-Chief Stan Lipovetsky. The papers are pertaining to the various data analytics techniques applied to the diverse statistic areas. We appreciate the willingness of the authors to help in organizing this special issue. S.S. Aravinth, S. Srithar, M. Senthilkumar and J. Senthilkumar contribute a paper titled ”Regression Analysis Based Decision Support System With Relationship Extraction”. The Authors used the regression modelling to analyse and study the relationship between the Years of Experience and the salary of employees in phased approach. M. Ashraf Bhat and G. Sankara Raju Kosuru present a paper titled “On Continuity of Machine Learning framework of models based on various approaches of artificial to recognize payment behaviour of interrelation between anti-fraud system and operational
数据分析技术是多种技术和处理方法的结合，是企业获取战略管理和实施相关结果的有效工具。在目前的情况下，数字世界正在广泛使用先进的数据分析技术，从各种类型的数据(如物联网(IoT)数据、健康数据、业务数据、安全数据等)中提取知识或有用的见解，这些数据可用于各种应用领域的智能决策。在数据科学领域，包括机器学习建模在内的先进分析方法可以提供可操作的见解或更深入的数据知识，从而使计算过程自动化和智能化。受上述事实的启发，于2021年12月在VIT博帕尔大学以全虚拟模式组织和主办了“数据分析和计算技术”国际会议。本期特刊的七篇论文是由MASA客座编辑Hemant Kumar Nashine, Reena Jain, Neha Choubey和Mayank Sharma根据与期刊和评论论文的相关性从会议接受的所有论文中挑选出来的。这些论文经过了正常的期刊式审稿程序，并在执行了联合主编Stan Lipovetsky的宝贵建议后，以现在的形式出现。这些论文涉及应用于不同统计领域的各种数据分析技术。我们感谢作者愿意帮助组织这个特刊。S.S. Aravinth, S. Srithar, M. Senthilkumar和J. Senthilkumar撰写了一篇题为“基于回归分析的决策支持系统与关系提取”的论文。本文采用回归模型，分阶段分析和研究了工作年限与员工工资的关系。M. Ashraf Bhat和G. Sankara Raju Kosuru发表了一篇题为“基于人工识别反欺诈系统和操作系统之间相互关系的支付行为的各种方法的模型的机器学习框架的连续性”的论文
{"title":"Special issue: International Conference on Data Analytics and Computational Techniques","authors":"H. Nashine, R. Jain, N. Choubey, Mayank Sharma","doi":"10.3233/mas-220001","DOIUrl":"https://doi.org/10.3233/mas-220001","url":null,"abstract":"Being a combination of several techniques and processing methods, the Data Analytics technology is emerged as an effective tool for the enterprises to obtain relevant results for strategic management and implementation. In the present circumstances the digital world is extensively using the advanced data analytic techniques for extracting knowledge or useful insights from the various kind of data such as Internet of Things (IoT) data, health data, business data, security data, and many more, which can be used for smart decision-making in various application domains. In the areas of data science, advanced analytical methods including machine learning modelling can provide actionable insights or deeper knowledge about data, which makes the computing process automatic and smart. Inspired by the mentioned facts, an international conference on “Data Analytics and Computational Techniques” had been organized and hosted in VIT Bhopal University in fully virtual mode during December 2021. The seven full length papers for this special issue were selected among all the accepted papers in the conference by the MASA Guest Editors Hemant Kumar Nashine, Reena Jain, Neha Choubey and Mayank Sharma, based on the relevance to the journal and the reviews papers. The papers went through the normal journal-style review process and they appear in the present form after implementing the valuable suggestions by the Co-Editor-in-Chief Stan Lipovetsky. The papers are pertaining to the various data analytics techniques applied to the diverse statistic areas. We appreciate the willingness of the authors to help in organizing this special issue. S.S. Aravinth, S. Srithar, M. Senthilkumar and J. Senthilkumar contribute a paper titled ”Regression Analysis Based Decision Support System With Relationship Extraction”. The Authors used the regression modelling to analyse and study the relationship between the Years of Experience and the salary of employees in phased approach. M. Ashraf Bhat and G. Sankara Raju Kosuru present a paper titled “On Continuity of Machine Learning framework of models based on various approaches of artificial to recognize payment behaviour of interrelation between anti-fraud system and operational","PeriodicalId":35000,"journal":{"name":"Model Assisted Statistics and Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42339832","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Given a measure space (Ω,Σ,μ), the distribution function μf(ν)=μ({t∈Ω:|f(t)|>ν}) where ν⩾0 and the decreasing rearrangement f*(z)=inf{ν⩾0:μf(ν)⩽z}, where z⩾0 and by convention inf{∅}=∞, of a measurable function f are known to be right continuous functions. However, these functions need not be left continuous. The purpose of this paper is to investigate the conditions under which these functions are continuous. Under the assumption that μ({t∈Ω:|f(t)|>0})<∞, we provide a necessary and sufficient condition for the function μf to be continuous at ν>0. Using the same we provide a similar result for the continuity of decreasing rearrangement f* of the function f.
给定一个测度空间（Ω，∑，μ），分布函数μf（Γ）=μ（{t∈Ω：|f（t）|>Γ}），其中，Γ⩾0和递减重排f*（z）=inf已知可测函数f的｛Γ0：μf（Γ）⩽z｝，其中z⩾0和惯例i n f｛∅｝=∞是右连续函数。然而，这些功能不必保持连续。本文的目的是研究这些函数连续的条件。在μ（{t∈Ω：|f（t）|>0}）为0的假设下。使用相同的结果，我们为函数f的递减重排f*的连续性提供了类似的结果。
{"title":"On continuity of distribution function and decreasing rearrangement","authors":"M. A. Bhat, G. R. Kosuru","doi":"10.3233/mas-220003","DOIUrl":"https://doi.org/10.3233/mas-220003","url":null,"abstract":"Given a measure space (Ω,Σ,μ), the distribution function μf(ν)=μ({t∈Ω:|f(t)|>ν}) where ν⩾0 and the decreasing rearrangement f*(z)=inf{ν⩾0:μf(ν)⩽z}, where z⩾0 and by convention inf{∅}=∞, of a measurable function f are known to be right continuous functions. However, these functions need not be left continuous. The purpose of this paper is to investigate the conditions under which these functions are continuous. Under the assumption that μ({t∈Ω:|f(t)|>0})<∞, we provide a necessary and sufficient condition for the function μf to be continuous at ν>0. Using the same we provide a similar result for the continuity of decreasing rearrangement f* of the function f.","PeriodicalId":35000,"journal":{"name":"Model Assisted Statistics and Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45324147","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Probability of ultimate ruin under the classical risk model is obtained as a solution of an integro -differential equation involving convolutions and we have used Fast Fourier Transform (FFT) to obtain the approximate values of the probability of ultimate ruin from this integro -differential equation under the situation when the claim severity is modelled by the Mixture of 3 Exponentials and the Weibull distribution. Another application of FFT in ruin theory is shown by means of applying it to obtain the quantiles of the aggregate claim distribution under these claim severity distributions. Extension of the application of FFT is shown by using it to obtain the first moment of the time to ruin under the classical risk model for these distributions. The distributions which have been used are such that one is light tailed and the another is heavy tailed so that a comparison can be made between them on the precision of the actuarial quantities obtained through FFT. FFT has been found to be efficient in obtaining these actuarial quantities when used in conjunction with certain modifications like exponential tilting to control the aliasing error.
{"title":"Computation of the probability of ultimate ruin and some other actuarial quantities under the classical risk model via Fast Fourier Transform","authors":"Jagriti Das","doi":"10.3233/mas-220004","DOIUrl":"https://doi.org/10.3233/mas-220004","url":null,"abstract":"The Probability of ultimate ruin under the classical risk model is obtained as a solution of an integro -differential equation involving convolutions and we have used Fast Fourier Transform (FFT) to obtain the approximate values of the probability of ultimate ruin from this integro -differential equation under the situation when the claim severity is modelled by the Mixture of 3 Exponentials and the Weibull distribution. Another application of FFT in ruin theory is shown by means of applying it to obtain the quantiles of the aggregate claim distribution under these claim severity distributions. Extension of the application of FFT is shown by using it to obtain the first moment of the time to ruin under the classical risk model for these distributions. The distributions which have been used are such that one is light tailed and the another is heavy tailed so that a comparison can be made between them on the precision of the actuarial quantities obtained through FFT. FFT has been found to be efficient in obtaining these actuarial quantities when used in conjunction with certain modifications like exponential tilting to control the aliasing error.","PeriodicalId":35000,"journal":{"name":"Model Assisted Statistics and Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43237980","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Working from anywhere or Working from Home has been prevalent in many developed countries, specifically in the IT sector. Still, the pandemic brought in the wave for such concepts in India, and the people here were not ready for it socially and culturally. As it was an unforeseen and forced situation here in the country, its adaptability raised several questions and issues in the minds of employers and employees. With the shift happening in work culture, which is, working from home due to the pandemic, many changes have crept into the employees’ minds. One such notable arena, which should be addressed for better human resources management and efficiency, is perceived job satisfaction and understanding the employees’ work-life balance amidst these changes. In the study, 90 employees from selected IT companies at various levels are under consideration to understand their perseverance of job satisfaction and work-life balance in and before the change. The stability and the effects of the different attributes on the subject are studied. Statistical tools like Multiple Regression Analysis, Pearson Correlation, and Z-test are used.
{"title":"A study on work-life balance in the era of work from home with reference to understanding the change in perceived job satisfaction through statistical analysis","authors":"S. Neogi, A. Jason, A. Selvakumar","doi":"10.3233/mas-220007","DOIUrl":"https://doi.org/10.3233/mas-220007","url":null,"abstract":"Working from anywhere or Working from Home has been prevalent in many developed countries, specifically in the IT sector. Still, the pandemic brought in the wave for such concepts in India, and the people here were not ready for it socially and culturally. As it was an unforeseen and forced situation here in the country, its adaptability raised several questions and issues in the minds of employers and employees. With the shift happening in work culture, which is, working from home due to the pandemic, many changes have crept into the employees’ minds. One such notable arena, which should be addressed for better human resources management and efficiency, is perceived job satisfaction and understanding the employees’ work-life balance amidst these changes. In the study, 90 employees from selected IT companies at various levels are under consideration to understand their perseverance of job satisfaction and work-life balance in and before the change. The stability and the effects of the different attributes on the subject are studied. Statistical tools like Multiple Regression Analysis, Pearson Correlation, and Z-test are used.","PeriodicalId":35000,"journal":{"name":"Model Assisted Statistics and Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46060219","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The Bank of Russia is one of the unique banking regulators in the world as it discloses granular reporting information per the existing credit institutions with the available historical track record. Same time the number of banks dramatically declined from above two and a half thousands in 1990s to one thousand in 2010 and to around 350 in 2021. Such information stimulates designing default probability (PD) models for the Russian banks. There is a separate stream of research that studies the amount of negative capital revealed when the Russian bank got its license withdrawn. However, the existing papers have several shortcomings. First, most of them do not account for the structural breaks in data. Second, there is no search for the best fitting model, just a model is offered and the coefficients of interest are interpreted. Third, the best model is poorly interpretable. Forth, the existing models make short-term forecasts. Fifth, there is no a LGD model for Russian banks, though the amount of negative capital upon license withdrawal was considered. Thus, our research objective is to study PD-LGD correlation (PLC) for the Russian banks. To do so, we improve the existing Russian banks PD model and create a respective novel LGD model. We use the homogenous dataset from 2016 to 2021. We find that PLC for Russian banks equals to +22%.
{"title":"PD-LGD correlation for the banking lending segment: Empirical evidence from Russia","authors":"H. Penikas","doi":"10.3233/mas-220005","DOIUrl":"https://doi.org/10.3233/mas-220005","url":null,"abstract":"The Bank of Russia is one of the unique banking regulators in the world as it discloses granular reporting information per the existing credit institutions with the available historical track record. Same time the number of banks dramatically declined from above two and a half thousands in 1990s to one thousand in 2010 and to around 350 in 2021. Such information stimulates designing default probability (PD) models for the Russian banks. There is a separate stream of research that studies the amount of negative capital revealed when the Russian bank got its license withdrawn. However, the existing papers have several shortcomings. First, most of them do not account for the structural breaks in data. Second, there is no search for the best fitting model, just a model is offered and the coefficients of interest are interpreted. Third, the best model is poorly interpretable. Forth, the existing models make short-term forecasts. Fifth, there is no a LGD model for Russian banks, though the amount of negative capital upon license withdrawal was considered. Thus, our research objective is to study PD-LGD correlation (PLC) for the Russian banks. To do so, we improve the existing Russian banks PD model and create a respective novel LGD model. We use the homogenous dataset from 2016 to 2021. We find that PLC for Russian banks equals to +22%.","PeriodicalId":35000,"journal":{"name":"Model Assisted Statistics and Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45002388","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
We currently see a large increase in e-commerce sector; it is becoming a central trend in the banking industry. Fraudsters keep up with modern technologies, and use weak points in human psychology and security systems to steal money from regular users. To ensure the required level of security, banks began to apply artificial intelligence in their anti-fraud systems. Fraud detection can be formulated as a classification problem with a case-based reasoning or knowledge extraction task with unbalanced classes. In this paper we present a framework of models based on various approaches of artificial intelligence, such as neural networks, decision trees, copula models and others to recognize payment behavior of fraudster. The considered framework is evaluated with different metrics and implemented in an actual anti-fraud system, which leads to an improvement of the system performance. Finally, the interrelation between the anti-fraud system indicators and banks operational risks is discussed in this paper.
{"title":"A hybrid machine learning framework for e-commerce fraud detection","authors":"Yury Y. Festa, Ivan Vorobyev","doi":"10.3233/mas-220006","DOIUrl":"https://doi.org/10.3233/mas-220006","url":null,"abstract":"We currently see a large increase in e-commerce sector; it is becoming a central trend in the banking industry. Fraudsters keep up with modern technologies, and use weak points in human psychology and security systems to steal money from regular users. To ensure the required level of security, banks began to apply artificial intelligence in their anti-fraud systems. Fraud detection can be formulated as a classification problem with a case-based reasoning or knowledge extraction task with unbalanced classes. In this paper we present a framework of models based on various approaches of artificial intelligence, such as neural networks, decision trees, copula models and others to recognize payment behavior of fraudster. The considered framework is evaluated with different metrics and implemented in an actual anti-fraud system, which leads to an improvement of the system performance. Finally, the interrelation between the anti-fraud system indicators and banks operational risks is discussed in this paper.","PeriodicalId":35000,"journal":{"name":"Model Assisted Statistics and Applications","volume":" ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"48052208","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The research study tries to understand teenagers’ online engagement and the behavioral transformation in buying stuff online. The study also tries to ideate the stability of spike in online buying (if any) and its sustainability. Statistical tools like the K-S test, M.L.R. test, Pearson Correlation has been used to justify the study and the usage of machine learning algorithms to construct a predictive model of behaviour and its efficiency. The study will help online retailers understand their sales figures’ stability. It will allow them to strategize their marketing functionalities to make the space more attractive even after the world comes out of the pandemic. The increasing usage of intelligent android devices and relatively cheap data has surged the penetration of online engagements among all the age group peoples. The youngsters are engaging in online stuff hence bringing down a considerable transformation in buying behaviour, pattern, and a collective change in marketers’ approach to strategizing according to the ever-evolving market forces.
{"title":"Empirical study on understanding online buying behaviour through machine learning algorithms","authors":"Sayantan Mukherjee, A. Jason, A. Selvakumar","doi":"10.3233/mas-220008","DOIUrl":"https://doi.org/10.3233/mas-220008","url":null,"abstract":"The research study tries to understand teenagers’ online engagement and the behavioral transformation in buying stuff online. The study also tries to ideate the stability of spike in online buying (if any) and its sustainability. Statistical tools like the K-S test, M.L.R. test, Pearson Correlation has been used to justify the study and the usage of machine learning algorithms to construct a predictive model of behaviour and its efficiency. The study will help online retailers understand their sales figures’ stability. It will allow them to strategize their marketing functionalities to make the space more attractive even after the world comes out of the pandemic. The increasing usage of intelligent android devices and relatively cheap data has surged the penetration of online engagements among all the age group peoples. The youngsters are engaging in online stuff hence bringing down a considerable transformation in buying behaviour, pattern, and a collective change in marketers’ approach to strategizing according to the ever-evolving market forces.","PeriodicalId":35000,"journal":{"name":"Model Assisted Statistics and Applications","volume":"36 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2022-04-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"70130890","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：