BENCHMARKING OF HALAL FOOD PRODUCTS USING SIMILARITY MEASURES - A CONCEPTUAL RETRIEVAL MODEL

Abstract

Muslims are concerned with the Halal status of food products sold in the supermarkets. Many products that are imported from overseas are not certified by JAKIM. In this paper, we proposed a conceptual model for benchmarking food products against certified Halal products. Our motivation is to provide similarity measurement between certified and non-certified food products based on their ingredients. This model comprises three main phases: ingredient acquisition, ingredient transformation and similarity measures calculation. In the first phase, web crawlers are employed to retrieve product information from JAKIM online database and supermarket web pages. In the second phase, an index structure will be constructed to allow faster ingredient retrieval which will be used for similarity calculation. In the last phase, Euclidian distance, cosine similarity measure and Jaccard correlation coefficient will be used to measure the similarities between two products. Our proposed model is to complement but not to replace the existing JAKIM procedure to verify food products by empowering Muslim consumers with informed decision making.