scholarly journals PREDICCIÓN DE FRAUDES EN EL CONSUMO DE AGUA POTABLE MEDIANTE EL USO DE MINERÍA DE DATOS

2020 ◽  
Vol 24 (104) ◽  
pp. 58-66
Author(s):  
Fredy Humberto Troncoso Espinosa ◽  
Fuentes Figueroa Paulina Gisselot ◽  
Italo Ramiro Belmar Arriagada
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
New York ◽  
Electrical Power ◽  
Fraud Detection ◽  
Accounting Fraud ◽  
Power Utility ◽  
Palabras Clave ◽  
Comprehensive Survey ◽  
Prevention Methods

El comportamiento fraudulento en el consumo de agua potable es un problema importante que enfrentan las empresas de tratamiento de agua debido a que genera pérdidas económicas significativas. Caracterizar consumos fraudulentos es una tarea compleja, basada principalmente en la experiencia, y que presenta el desafío de la incorporación constante de nuevos clientes y la variación en el consumo mensual. En esta investigación, las técnicas de minería de datos se utilizan para caracterizar y predecir los consumos fraudulentos de agua potable. Para esto, se utilizó información histórica relacionada con el consumo. Las técnicas aplicadas mostraron un alto rendimiento predictivo y su aplicación permitirá enfocar eficientemente los recursos orientados a evitar este tipo de fraude. Palabras Clave: minería de datos, machine learning, agua potable, detección de fraude. Referencias [1]Centro de Investigación Periodística., «Producción y facturación de agua potable,» 30 Julio 2020. [En línea]. Disponible en: https://ciperchile.cl/wp-content/uploads/gestion-siis-2014-pag 88.pdf. [Último acceso: 30 Julio 2020]. [2]Bureau Veritas S.A., «https://www.bureauveritas.cl/es,» [En línea]. Disponible en: https://www.bureauveritas.cl/es/bureau-veritas-lider-mundial-en-ensayos-inspeccion-y-certificacion. [Último acceso: 1 Junio 2020]. [3]Essbio S.A., «www.essbio.cl,» [En línea]. [4]I. Monedero, F. Biscarri, J. Guerrero, M. Peña, M. Roldán y C. León, «Detection of water meter under-registration using statistical algorithms,» Journal of Water Resources Planning and Management, vol. 142, nº 1, p. 04015036, 2016. [5]I. Monedero, F. Biscarri, C. León, J. Guerrero, J. Biscarri y R. Millán, «Detection of frauds and other non-technical losses in a power utility using Pearson coefficient, Bayesian networks and decision trees,» International Journal of Electrical Power & Energy Systems, vol. 34, nº 1, pp. 90-98, 2012. [6]S. Wang, «A comprehensive survey of data mining-based accounting-fraud detection research,» de 2010 International Conference on Intelligent Computation Technology and Automation, New York, 2010. [7]J. Bierstaker, R. Brody y C. Pacini, «Accountants' perceptions regarding fraud detection and prevention methods,» Managerial Auditing Journal, vol. 21, nº 5, pp. 520-535, 2006. [8]C. Phua, V. Lee, K. Smith y R. Gayler, «A comprehensive survey of data mining-based fraud detection research,» arXiv preprint arXiv:1009.6119, 2010. [9]S. Kotsiantis, I. Zaharakis y P. Pintelas, «Machine learning: a review of classification and combining techniques,» Artificial Intelligence Review, vol. 26, nº 3, pp. 159-190, 2006. [10]J. Han, J. Pei y M. Kamber, Data Mining: Concepts and Techniques, Elsevier, 2011.  

A Study on Various Applications of Data Mining and Supervised Learning Techniques in Business Fraud Detection

2021 ◽  
pp. 108-125
Author(s):  
Amit Majumder ◽  
Ira Nath
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Supervised Learning ◽  
Academic Research ◽  
Fraud Detection ◽  
Customer Relationships ◽  
Financial Accounting ◽  
Accounting Fraud ◽  
Data Mining Technique ◽  
Learning Techniques

Data mining technique helps us to extract useful data from a large dataset of any raw data. It is used to analyse and identify data patterns and to find anomalies and correlations within dataset to predict outcomes. Using a broad range of techniques, we can use this information to improve customer relationships and reduce risks. Data mining and supervised learning have applications in multiple fields of science and research. Machine learning looks at patterns of data and helps to predict future behaviour by learning from the patterns. Data mining is normally used as a source of information on which machine learning can be applied to solve some of problems in our daily life. Supervised learning is one type of machine learning method which uses labelled data consisting of input along with the label of inputs and generates one learned model (or classifier for classification type work) which can be used to label unknown data. Financial accounting fraud detection has become an emerging topic in the field of academic, research and industries.

scholarly journals Imbalance class problems in data mining: a review

2019 ◽  
Vol 14 (3) ◽  
pp. 1552 ◽  
Author(s):  
Haseeb Ali ◽  
Mohd Najib Mohd Salleh ◽  
Rohmat Saedudin ◽  
Kashif Hussain ◽  
Muhammad Faheem Mushtaq
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Imbalanced Data ◽  
Machine Learning Algorithms ◽  
The Other ◽  
Minority Class ◽  
Future Directions ◽  
Significant Research ◽  
Comprehensive Survey ◽  
Imbalanced Class

<span>The imbalanced data problems in data mining are common nowadays, which occur due to skewed nature of data. These problems impact the classification process negatively in machine learning process. In such problems, classes have different ratios of specimens in which a large number of specimens belong to one class and the other class has fewer specimens that is usually an essential class, but unfortunately misclassified by many classifiers. So far, significant research is performed to address the imbalanced data problems by implementing different techniques and approaches. In this research, a comprehensive survey is performed to identify the challenges of handling imbalanced class problems during classification process using machine learning algorithms. We discuss the issues of classifiers which endorse bias for majority class and ignore the minority class. Furthermore, the viable solutions and potential future directions are provided to handle the problems<em>.</em></span>

Data Avalanche

2020 ◽  
pp. 28-49
Author(s):  
Emmanuel Awuni Kolog ◽  
Acheampong Owusu ◽  
Samuel Nii Odoi Devine ◽  
Edward Entee
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Developing Countries ◽  
Fraud Detection ◽  
Mobile Payment ◽  
Mobile Money ◽  
Governmental Agencies ◽  
Learning Framework ◽  
Formal And Informal Sectors ◽  
Existing Data

Globalizing businesses from developing countries require a thoughtful strategy and adoption of state-of-the-art technologies to meet up with the rapidly changing society. Mobile money payment service is a growing service that provides opportunities for both the formal and informal sectors in Ghana. Despite its importance, fraudsters have capitalized on the vulnerabilities of users to defraud them. In this chapter, the authors have reviewed existing data mining techniques for exploring the detection of mobile payment fraud. With this technique, a hybrid-based machine learning framework for mobile money fraud detection is proposed. With the use of the machine learning technique, an avalanche of fraud-related cases is leveraged, as a corpus, for fraud detection. The implementation of the framework hinges on the formulation of policies and regulations that will guide the adoption and enforcement by Telcos and governmental agencies with oversight responsibilities in the telecommunication space. The authors, therefore, envision the implementation of the proposed framework by practitioners.

scholarly journals THE USE OF MACHINE LEARNING TECHNIQUES IN ACCOUNTING. A SHORT SURVEY

2021 ◽  
Vol 4 (3) ◽  
pp. 139-143
Author(s):  
Mariana Vlad ◽  
◽  
Sorin Vlad ◽  
Keyword(s):  
Machine Learning ◽  
Learning Algorithm ◽  
Real Life ◽  
Fraud Detection ◽  
Machine Learning Algorithms ◽  
Machine Learning Techniques ◽  
Behavior Prediction ◽  
Accounting Fraud ◽  
Research Fields ◽  
Learning Techniques

Machine learning (ML) is a subset of artificial Intelligence (AI) aiming to develop systems that can learn and continuously improve the abilities through generalization in an autonomous manner. ML is presently all around us, almost every facet of our digital and real life is embedding some ML related content. Customer recommendation systems, customer behavior prediction, fraud detection, speech recognition, image recognition, black & white movies colorization, accounting fraud detection are just some examples of the vast range of applications in which ML is involved. The techniques that this paper investigates are mainly focused on the use of neural networks in accounting and finance research fields. An artificial neural network is modelling the brain ability of learning intricate patterns from the information presented at its inputs using elementary interconnected units, named neurons, grouped in layers and trained by means of a learning algorithm. The performance of the network depends on many factors like the number of layers, the number of each neurons in each layer, the learning algorithm, activation functions, to name just a few of them. Machine learning algorithms have already started to replace humans in jobs that require document’s processing and decision making.

scholarly journals An Xgboost based system for financial fraud detection

2020 ◽  
Vol 214 ◽  
pp. 02042
Author(s):  
Shimin LEI ◽  
Ke XU ◽  
YiZhe HUANG ◽  
Xinye SHA
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Credit Card ◽  
Detection System ◽  
Fraud Detection ◽  
Financial Fraud ◽  
Credit Card Fraud

Credit card fraud leads to billions of losses in online transaction. Many corporations like Alibaba, Amazon and Paypal invest billions of dollars to build a safe transaction system. There are some studies in this area having tried to use machine learning or data mining to solve these problems. This paper proposed our fraud detection system for e- commerce merchant. Unlike many other works, this system combines manual and automatic classifications. This paper can inspire researchers and engineers to design and deploy online transaction systems.

scholarly journals Fraud Detection Using the Fraud Triangle Theory and Data Mining Techniques: A Literature Review

Computers ◽  
2021 ◽  
Vol 10 (10) ◽  
pp. 121
Author(s):  
Marco Sánchez-Aguayo ◽  
Luis Urquiza-Aguiar ◽  
José Estrada-Jiménez
Keyword(s):  
Machine Learning ◽  
Data Mining ◽  
Deep Learning ◽  
Learning Strategies ◽  
Fraud Detection ◽  
Machine Learning Techniques ◽  
Mining Machine ◽  
General Interest ◽  
Fraud Triangle ◽  
Learning Techniques

Fraud entails deception in order to obtain illegal gains; thus, it is mainly evidenced within financial institutions and is a matter of general interest. The problem is particularly complex, since perpetrators of fraud could belong to any position, from top managers to payroll employees. Fraud detection has traditionally been performed by auditors, who mainly employ manual techniques. These could take too long to process fraud-related evidence. Data mining, machine learning, and, as of recently, deep learning strategies are being used to automate this type of processing. Many related techniques have been developed to analyze, detect, and prevent fraud-related behavior, with the fraud triangle associated with the classic auditing model being one of the most important of these. This work aims to review current work related to fraud detection that uses the fraud triangle in addition to machine learning and deep learning techniques. We used the Kitchenham methodology to analyze the research works related to fraud detection from the last decade. This review provides evidence that fraud is an area of active investigation. Several works related to fraud detection using machine learning techniques were identified without the evidence that they incorporated the fraud triangle as a method for more efficient analysis.

Sign in / Sign up

Export Citation Format

Share Document