Machine Learning en la detección de fraudes de comercio electrónico aplicado a los servicios bancarios

Alvarez, Fredi W.

doi:10.18682/cyt.vi0.4310

Cited by 3 publications

(2 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Automatización de procesos, la automatización de tareas rutinarias o mecánicas sin valor agregado es una característica recurrente en la lista de beneficios asociados con ML. Gracias al aprendizaje automático, las máquinas sabrán qué procesos manejar y los mejorarán con el tiempo e incluso ampliarán la cantidad de tareas que pueden manejar (Alvarez, 2020).…”

Section: Aporte Del Machine Learning En La Cultura Organizacionalunclassified

Support industrial processes through machine learning

Curo¹,

Giribaldi

Quispe³

et al. 2021

jstri

View full text Add to dashboard Cite

Machine learning is a data analysis method that automatically creates analysis models. It is a branch of artificial intelligence based on the idea that systems can learn from data, recognize patterns, and make decisions with minimal human intervention. The implementation of Machine Learning (ML) can improve decision making and transform an organization or business, however, taking advantage of its potential requires a change in mindset and culture.

show abstract

Section: Aporte Del Machine Learning En La Cultura Organizacionalunclassified

Support industrial processes through machine learning

Curo¹,

Giribaldi

Quispe³

et al. 2021

jstri

View full text Add to dashboard Cite

show abstract

“…Es crucial destacar los dos enfoques fundamentales en el Aprendizaje Automático (AA): el aprendizaje supervisado (AS), que implica entrenar con datos previamente etiquetados y se utiliza comúnmente para clasificación o predicción; y el aprendizaje no supervisado (ANS), que trabaja con datos no etiquetados, buscando patrones que permitan la agrupación e identificación de similitudes. El aprendizaje supervisado ha demostrado ser efectivo en diversas aplicaciones, desde diagnósticos médicos (Kononenko, 2001;Mello-Román & Hernández, 2020) hasta la detección de fraudes (Alvarez, 2020).…”

Section: Introductionunclassified

Análisis de datos de covid-19: imputación y rendimiento de modelos de aprendizaje supervisado

2023

RICS

View full text Add to dashboard Cite

uno sin registros vacíos y otro con un 20% de datos faltantes por filas. La imputación se realiza mediante las técnicas de imputación por moda y bosque aleatorio en el conjunto con datos faltantes. La variable dependiente evaluada es la clasificación final de la enfermedad, confirmada o descartada por criterios laboratoriales. El modelo de Bosque Aleatorio destaca por su eficiencia superior en el conjunto de datos sin registros vacíos y muestra robustez ante la imputación de datos. Este estudio contribuye significativamente al proporcionar información sobre los efectos

show abstract

Benchmarking quantum versions of the kNN algorithm with a metric based on amplitude-encoded features

Guerrero-Estrada,

Quezada,

Sun

2024

Sci Rep

View full text Add to dashboard Cite

This work introduces a quantum subroutine for computing the distance between two patterns and integrates it into two quantum versions of the kNN classifier algorithm: one proposed by Schuld et al. and the other proposed by Quezada et al. Notably, our proposed subroutine is tailored to be memory-efficient, requiring fewer qubits for data encoding, while maintaining the overall complexity for both QkNN versions. This research focuses on comparing the performance of the two quantum kNN algorithms using the original Hamming distance with qubit-encoded features and our proposed subroutine, which computes the distance using amplitude-encoded features. Results obtained from analyzing thirteen different datasets (Iris, Seeds, Raisin, Mine, Cryotherapy, Data Bank Authentication, Caesarian, Wine, Haberman, Transfusion, Immunotherapy, Balance Scale, and Glass) show that both algorithms benefit from the proposed subroutine, achieving at least a 50% reduction in the number of required qubits, while maintaining a similar overall performance. For Shuld’s algorithm, the performance improved in Cryotherapy (68.89% accuracy compared to 64.44%) and Balance Scale (85.33% F1 score compared to 78.89%), was worse in Iris (86.0% accuracy compared to 95.33%) and Raisin (77.67% accuracy compared to 81.56%), and remained similar in the remaining nine datasets. While for Quezada’s algorithm, the performance improved in Caesarian (68.89% F1 score compared to 58.22%), Haberman (69.94% F1 score compared to 62.31%) and Immunotherapy (76.88% F1 score compared to 69.67%), was worse in Iris (82.67% accuracy compared to 95.33%), Balance Scale (77.97% F1 score compared to 69.21%) and Glass (40.04% F1 score compared to 28.79%), and remained similar in the remaining seven datasets.

show abstract

Machine Learning en la detección de fraudes de comercio electrónico aplicado a los servicios bancarios

Cited by 3 publications

References 7 publications

Support industrial processes through machine learning

Support industrial processes through machine learning

Análisis de datos de covid-19: imputación y rendimiento de modelos de aprendizaje supervisado

Benchmarking quantum versions of the kNN algorithm with a metric based on amplitude-encoded features

Contact Info

Product

Resources

About