FTIR of Halal and Non-Halal Adulterations Prediction Analytics Using Induction Decision Tree (ID3) Algorithm

Abstract

Advanced analytical practices such as data mining or predictive analytics are concepts that are increasingly vital in the area of large data sets. Voluminous data are collected over the years and it is important to assess the data quality for the value of information. Large amounts of data can contain knowledge in the form of patterns. What knowledge an organization especially the high-paced halal industry can get once data quality is assessed and data mining technique is applied? In this research, we have two objectives. Number one is to assess the data quality on the unstructured data collected from the Fourier-transform Infrared Spectroscopy (FTIR) instrument and number two is to identify patterns of halal and non-halal samples which have been analyzed using the FTIR instrument from International Institute for Halal Research & Training (INHART) laboratory. Total Data Quality Management (TDQM) methodology is used in this research where field observation, interview with the stakeholders, and data auditing will be our main objectives. Decision tree for data mining technique is used and this will be done by classifying the sample set based on its halal status.