Optimizing Business Intelligence System Using Big Data and Machine Learning

Autor: Gabriel Gregory James, Oise G P, Chukwu E G, Michael N A, Ekpo W F, Okafor P E
Jazyk: English<br />Indonesian
Rok vydání: 2024
Předmět:
Zdroj: Journal of Information Systems and Informatics, Vol 6, Iss 2, Pp 1215-1236 (2024)
Druh dokumentu: article
ISSN: 2656-5935
2656-4882
DOI: 10.51519/journalisi.v6i2.631
Popis: The Business Intelligence (BI) and Data Warehouse (DW) system deployed in the Nigerian National Petroleum Corporation should provide cooperate decision makers with real-time information to help them identify and understand key business factors to make the best decisions for the situation at any given time. The relentless collection of data from user interactions have introduced both a high level of complexity, as well as a great opportunity for businesses. In addition to connecting not just people, but also machines to the internet, and then collecting data from these machines via sensors would result in an unimaginable repository of data. This ever-increasing collection of data is known as Big Data. Integrating this with existing Business intelligence systems and deep analysis using Machine Learning algorithms, Big Data can give useful insights into business problems and perhaps even to make suggestions as to when and where future problems will occur (Predictive Analysis) so that problems can be avoided or at least mitigated. This paper targets at developing a system capable of optimizing a business intelligence using big data and machine learning approach. The design of a system to optimize the Business Intelligence System using Machine Learning and Big Data at NNPC was successfully carried out. The System was able to automatically analyze the sample report under NNPC permission to use and it generated expected predictive outputs which serves as a better guide to managers. When applying Deep Learning, one seeks to stack several independent neural network layers that, working together, produce better results than the already existing shallow structures.
Databáze: Directory of Open Access Journals
Externí odkaz: