Title:	A DATA MINING APPROACH FOR CUSTOMER SEGMENTATION USING A SAF-T BASED BUSINESS INTELLIGENCE SYSTEM
Author(s):	Rosa Silveira, Bruno Oliveira, Mariana Carvalho and Telmo Matos
ISBN:	978-989-8704-21-4
Editors:	Yingcai Xiao, Ajith P. Abraham and Jörg Roth
Year:	2020
Edition:	Single
Keywords:	Data Mining, SAF-T (PT), Data Warehousing, Customer Segmentation, ETL
Type:	Short
First Page:	173
Last Page:	180
Language:	English
Cover:
Full Contents:	click to dowload
Paper Abstract:	In 2018, 70% of the Portuguese companies produced thousands of Portuguese Audit Tax documents (SAF-T (PT)) files for tax validation. These documents represent a standardized procedure for the Portuguese companies, providing the necessary data about billing, accounting, and taxation. These files contain valuable information that can represent an important tool for analytical procedures to support decision-making processes. Thus, a Business Intelligence System based on SAF-T (PT) was created to support companies' analytical needs. An important decision-making process involves customer evaluation. So, the proposed system will begin, in a preliminary phase, with RFM analysis, for customer segmentation using Clustering techniques and results were cross-validated using Decision Tree and Linear Discriminant Analysis. Additionally, a brief interpretation of marketing strategies was suggested and a comparison between Rapid Miner and SPSS was synthesized. The results show that it is possible to explore SAF-T (PT) files to extract knowledge different than tax purposes, namely, the determination of customer profiles. Accuracy is superior to 80% in both software and techniques.
	Go Back