Sistem Pencarian Informasi Penyedia Makanan Halal Berbasis Knowledge Graphs di Surabaya

Bhamakerti, Ganendra Aby (2024) Sistem Pencarian Informasi Penyedia Makanan Halal Berbasis Knowledge Graphs di Surabaya. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 05211940000091-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 March 2026. Download (2MB) | Request a copy

Abstract

Hanya sekitar 10% produk yang memiliki sertifikat halal di Indonesia. Oleh karena itu, diperlukan suatu solusi yaitu suatu sistem yang dapat melakukan pencarian informasi penyedia makanan yang halal serta rekomendasinya, sistem ini merupakan sistem yang berbasis knowledge graph dan sistem ini juga perlu diketahui performanya. Metodologi yang dilakukan dalam mengerjakan penelitian tugas akhir ini yaitu dengan melakukan pengumpulan terhadap data dengan cara crawling API BPJPH. Kemudian, dilakukan penentuan ranking penyedia makanan dengan algoritma Node Similarity dan graph embedding dengan menggunakan algoritma Node2vec dan Fast Random Projection yang dipadukan dengan penggunaan algoritma K-Nearest Neighbors. Kemudian dilakukan pembuatan terhadap aplikasi mesin pencarian sederhana yang dilakukan dengan menggunakan Streamlit yang merupakan sebuah framework aplikasi open-source berbasis Python yang dibuat untuk memudahkan dalam rancang bangun aplikasi web di bidang machine learning dan data science, pembuatan aplikasi juga dilakukan menggunakan SQLiteStudio untuk membuat database aplikasi. Setelah dilakukan proses rancang bangun aplikasi mesin pencarian, kemudian dilakukan proses tahapan evaluasi dengan menggunakan dua metrik, yaitu Mean Reciprocal Rank (MRR) dan Normalized Discounted Cumulative Gain (NDCG). Nilai rata-rata MRR pada algoritma Node Similarity, K-Nearest Neighbors dengan Fast Random Projection, dan K-Nearest Neighbors dengan Node2Vec sebesar 0,7790, 0,7967, dan 0,5430. Nilai rata-rata NDCG pada algoritma Node Similarity, K-Nearest Neighbors dengan Fast Random Projection, dan K-Nearest Neighbors dengan Node2Vec sebesar 0,9572, 0,9157, dan 0,7618.
====================================================================================================
Only around 10% of products have halal certificates in Indonesia. Therefore, a solution is needed, namely a system that can search for information on halal food providers and recommendations. This system is a knowledge graph-based system and this system also needs to know its performance. The methodology used in carrying out this final research project is to collect data by crawling the BPJPH API. Then, the ranking of food providers is determined using the Node Similarity algorithm and graph embedding using the Node2vec algorithm and Fast Random Projection combined with the use of the K-Nearest Neighbors algorithm. Then, a simple search engine application was created using Streamlit, which is a Python-based open-source application framework created to make it easier to design web applications in the fields of machine learning and data science. Application creation was also carried out using SQLiteStudio to create the application database. . After the search engine application design process has been carried out, an evaluation stage process is then carried out using two metrics, namely Mean Reciprocal Rank (MRR) and Normalized Discounted Cumulative Gain (NDCG). The average MRR values for the Node Similarity algorithm, K-Nearest Neighbors with Fast Random Projection, and K-Nearest Neighbors with Node2Vec are 0.7790, 0.7967, and 0.5430. The average NDCG values for the Node Similarity algorithm, K-Nearest Neighbors with Fast Random Projection, and K-Nearest Neighbors with Node2Vec are 0.9572, 0.9157, and 0.7618.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Knowledge Graph, Graph Embedding, Halal, Penyedia Makanan Halal, Sertifikasi Restoran Halal. = Knowledge Graph, Graph Embedding, Halal, Halal Food Providers, Halal Restaurant Certification.
Subjects:	Q Science > QA Mathematics > QA166 Graph theory Q Science > QA Mathematics > QA76.6 Computer programming. Q Science > QA Mathematics > QA76.9.I58 Recommender systems (Information filtering) Q Science > QA Mathematics > QA76.F56 Data structures (Computer science)
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 57201-(S1) Undergraduate Thesis
Depositing User:	Ganendra Aby Bhamakerti Ganendra Aby Bhamakerti
Date Deposited:	25 Jan 2024 05:34
Last Modified:	25 Jan 2024 05:35
URI:	http://repository.its.ac.id/id/eprint/105635

Actions (login required)

View Item