Sistem Rekomendasi Properti Berbasis Hybrid Filtering dan Profile Matching

Arisudana, I Gusti Made (2025) Sistem Rekomendasi Properti Berbasis Hybrid Filtering dan Profile Matching. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5026211188-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (2MB) | Request a copy

Abstract

Tempat tinggal merupakan salah satu kebutuhan mendasar bagi setiap individu. Banyaknya pilihan properti yang tersedia sering kali menyebabkan informasi yang berlebih (information overload), sehingga mempersulit proses pengambilan keputusan. Untuk mengatasi masalah ini, tugas akhir ini mengembangkan sistem rekomendasi properti berbasis Hybrid Filtering yang mengintegrasikan pendekatan Content-Based Filtering (CBF) dan Knowledge-Based Recommender Systems (KBRS) dengan metode Profile Matching. Sistem ini dirancang untuk menghasilkan rekomendasi properti yang lebih relevan dan terpersonalisasi, sekaligus mengatasi masalah cold-start. Pada implementasinya, sistem diuji menggunakan metode Black-Box Testing dengan Decision Table Testing yang terdiri dari total 300 kasus uji, masing-masing 100 kasus untuk tiga profil pengguna berbeda: Individu Lajang, Pasangan Bekerja tanpa Anak, dan Pasangan Bekerja dengan Anak. Hasil pengujian menunjukkan bahwa sistem berhasil mengenali profil Individu Lajang dengan akurasi sekitar 61% dan Pasangan Bekerja dengan Anak sekitar 75%, namun hanya 35% untuk Pasangan Bekerja tanpa Anak. Analisis confusion matrix memperlihatkan bahwa sistem seringkali salah mengklasifikasikan properti, mengindikasikan adanya tumpang tindih karakteristik antar segmen. Secara keseluruhan, sistem hanya mampu mengklasifikasikan profil dengan tingkat keberhasilan sekitar 57%. Hasil ini menunjukkan bahwa meskipun pendekatan hybrid ini mampu diterapkan dengan menggabungkan keunggulan CBF, KBRS, dan profile matching, sistem masih memerlukan penyempurnaan, khususnya dalam mendefinisikan profil ideal dan pembobotan kriteria, agar dapat meningkatkan akurasi dan relevansi rekomendasi pada masa mendatang.
=================================================================================================================================
Housing is a fundamental need for every individual. However, the abundance of available property options often leads to information overload, complicating decision-making processes. To address this issue, this final project develops a property recommendation system based on Hybrid Filtering that integrates Content-Based Filtering (CBF) and Knowledge-Based Recommender Systems (KBRS) with the Profile Matching method. This system aims to produce more personalized and relevant property recommendations while also mitigating the cold-start problem. During implementation, the system was evaluated using Black-Box Testing with Decision Table Testing, comprising a total of 300 test cases, 100 cases for each of three user profiles: Single Individuals, Working Couples without Children, and Working Couples with Children. The testing results indicated that the system could identify the Single Individuals profile with an accuracy of approximately 61% and Working Couples with Children at about 75%, but only around 35% for Working Couples without Children. The confusion matrix analysis revealed frequent misclassification of properties, indicating overlapping characteristics among segments. Overall, the system achieved only about 57% classification success. This suggests that although the hybrid approach can be applied by combining the advantages of CBF, KBRS, and profile matching, further refinements are needed, particularly in defining ideal profiles and weighting criteria, to improve the accuracy and relevance of recommendations in future work.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Hybrid Filtering, Profile Matching, Content-Based Filtering, Knowledge-Based Recommender Systems, TF-IDF.
Subjects:	Q Science > QA Mathematics > QA76.9.I58 Recommender systems (Information filtering)
Divisions:	Faculty of Intelligent Electrical and Informatics Technology (ELECTICS) > Information System > 57201-(S1) Undergraduate Thesis
Depositing User:	I Gusti Made Arisudana
Date Deposited:	23 Jul 2025 07:18
Last Modified:	23 Jul 2025 07:18
URI:	http://repository.its.ac.id/id/eprint/120819

Actions (login required)

View Item