Rule-Based Neural Networks Pada Data Mining Untuk Market Basket Analysis

Astuti, Yuliani Puji (2005) Rule-Based Neural Networks Pada Data Mining Untuk Market Basket Analysis. Masters thesis, Institut Teknologi Sepuluh November.

Text 1203201004-Master_thesis.pdf Restricted to Repository staff only Download (16MB)

Abstract

Era perdagangan bebas menuntut para produsen untuk selalu meningkatkan daya saing. Selain dengan meningkatkan mutu produk, para produsen juga harus memperhatikan mutu layanan terhadap konsumen. Mutu pelayanan dapat ditingkatkan dengan cara mempermudah konsumen dalam berbelanja dan mendapatkan barang yang dibutuhkannya. Seorang manajer pemasaran membutuhkan informasi yang diperoleh dari pola keterkaitan antarproduk berdasarkan data historis. Pola yang diperoleh dapat dijadikan acuan untuk mengenali perilaku konsumen, membaca kecenderungan selera pasar di masa depan, serta mendapatkan pasar baru. Data mining, khususnya untuk market basket analysis, dapat membantu mengetahui pola keterkaitan antarproduk yang dibeli oleh konsumen dalam bentuk association rules. Association rules tersebut dapat dijadikan pedoman dalam menentukan tata letak produk sehingga memudahkan konsumen untuk mendapatkan produk yang dibutuhkan secara bersamaan. Dalam tesis ini, digunakan Rule-Based Neural Networks (RBNN) sebagai metode untuk mendapatkan association rules dan membandingkannya dengan perhitungan confidence. Melalui proses pelatihan menggunakan 3.500 data transaksi, RBNN berhasil menghasilkan association rules yang mendekati hasil perhitungan confidence sehingga dapat digunakan untuk Market Basket Analysis.
=======================================================================================================================================
The free trade era requires producers to continuously improve their competitiveness. In addition to improving product quality, producers must also pay attention to the quality of service provided to consumers. Service quality can be improved by making it easier for consumers to shop and obtain the goods they need. A marketing manager needs information derived from patterns of relationships among products based on historical data. The resulting patterns can be used to identify consumer behavior, predict future market preferences, and identify new market opportunities. Data mining, particularly Market Basket Analysis, can help identify relationships among products purchased by consumers in the form of association rules. These association rules can serve as a guideline for determining product layouts, making it easier for consumers to find products that are commonly purchased together. In this thesis, Rule-Based Neural Networks (RBNN) is used to obtain association rules and compare them with confidence calculations. Through training with 3,500 transaction data records, RBNN successfully generated association rules that closely approximated the results of the confidence calculations, indicating that it can be applied to Market Basket Analysis.

Item Type:	Thesis (Masters)
Additional Information:	RTMa 006.32 Ast r
Uncontrolled Keywords:	Data Mining, Market Basket Analysis, Association Rules, Rule-Based Neural Networks, Data Mining, Market Basket Analysis, Association Rules, Rule-Based Neural Networks
Subjects:	Q Science > QA Mathematics > QA76.87 Neural networks (Computer Science)
Divisions:	Faculty of Mathematics and Science > Physics > 45101-(S2) Master Thesis
Depositing User:	magang .
Date Deposited:	30 Sep 2026 04:03
Last Modified:	30 Sep 2026 04:03
URI:	http://repository.its.ac.id/id/eprint/145078

Actions (login required)

View Item