IMPLEMENTASI CONTENT-BASED FILTERING MENGGUNAKAN TF-IDF AND COSINE SIMILARITY UNTUK SISTEM REKOMENDASI RESEP MASAKAN

Abstract

Many housewives are still confused about what dishes they will cook with existing food ingredients. Most housewives get recipe ideas from the website. Recipes from the website have the advantage of being easily accessible, but the disadvantages are sometimes troublesome for users because they have to choose a recipe from which site because there are many sites that contain the same recipe, and most of the recipe websites on the internet do not have a feature to search recipes based on the ingredients they have. The aim of this research is to implement a content-based filtering method using TF-IDF and cosine similarity for a recipe recommendation system. The TF-IDF and cosine similarity models are used to find similarity values between material data in the database and the query entered by the user in the search form. The sample data used in this research is 30 recipe data points taken from the website makapahariini.com. As a result, this system displays recipe recommendations that match the query of ingredients inputted by the user on the search form, and based on the test results using root mean square error (RMSE), it can be said that the recommendation system with the content-based filtering method that has been implemented produces quite good recommendations with a value of 0.356359182.