Abstract:
The rapid emergence and evolution of the Internet of Things has increased the amount of data that banks collect. Due to the volume of information, analytical tools are be...Show MoreMetadata
Abstract:
The rapid emergence and evolution of the Internet of Things has increased the amount of data that banks collect. Due to the volume of information, analytical tools are being used to improve the customer experience and make informed decisions. Classification and prediction are two of the most critical factors that banks need to consider when it comes to providing effective and efficient services to their customers. In this paper, we present a framework that combines the capabilities of machine learning (ML) and big data analytics on bank marketing data. For ML methods, we used logistic regression, support vector machine, k nearest neighbor, decision tree, and random forest, whereas for big data analysis method, we used PySpark with ML libraries to analyze the data. The results of the study revealed that the PySpark framework provides a faster time-to-value compared to other ML algorithms. It also uses distributed computing power, which is ideal for big data applications.
Date of Conference: 01-03 November 2023
Date Added to IEEE Xplore: 01 January 2024
ISBN Information: