Halal Network International (HNI) products already have around 100 products which are divided into three categories, namely Herbs Products, Health Food & Beverages, and Cosmetics & Home Care. These products are published through an electronic catalog that provides product information and search features to facilitate users. The mismatch between keywords and product descriptions causes the search to fail to display relevant results. To overcome this problem, the Term Frequency-Inverse Document Frequency (TF-IDF) algorithm is implemented in the search feature. This algorithm is used to calculate the weight of each word in the product description and determine the relevance of the keywords entered by the user. The system is built with React.js framework on the frontend, Node.js on the backend, and PostgreSQL as the database. Based on the test results, the average precision value is 71%, recall 85% and accuracy 73%. These results show that the TF-IDF algorithm is effective in improving the relevance of product search results.
Copyrights © 2025