Arofah, Muhimmatul (2025) Perbandingan Market Basket Analysis Menggunakan Algoritma Apriori dan FP-Growth dalam Menentukan Pola Pembelian Konsumen (Studi Kasus: UD. Kurnia). Undergraduate thesis, Universitas Pembangunan Nasional Veteran Jawa Timur.
![[img]](https://repository.upnjatim.ac.id/style/images/fileicons/text.png) |
Text (Cover)
21083010055_Cover.pdf Download (1MB) |
|
Text (Bab 1)
2103010055_BAB 1.pdf Download (23kB) |
|
Text (Bab 2)
2103010055_BAB 2.pdf Restricted to Registered users only until June 2028. Download (523kB) |
|
Text (Bab 3)
2103010055_BAB 3.pdf Restricted to Registered users only until June 2028. Download (575kB) |
|
Text (Bab 4)
2103010055_BAB 4.pdf Restricted to Registered users only until June 2028. Download (1MB) |
|
Text (Bab 5)
2103010055_BAB 5.pdf Download (127kB) |
|
Text (Daftar Pustaka)
2103010055_Daftar Pustaka.pdf Restricted to Registered users only until June 2028. Download (137kB) |
|
Text (Lampiran)
2103010055_Lampiran.pdf Restricted to Registered users only until June 2028. Download (599kB) |
Abstract
Micro, Small, and Medium Enterprises (MSMEs) are the backbone of Indonesia's economy, yet they continue to face challenges in inventory management and understanding consumer behavior. Digital transformation is crucial for MSMEs to enhance competitiveness through data-driven technological adoption. One relevant approach is Market Basket Analysis (MBA), which aims to identify consumer purchasing patterns to support strategic decision-making. This study compares the performance of the Apriori and FP-Growth algorithms in analyzing transaction data from the building material store UD. Kurnia, consisting of 7,778 transactions from August 2023 to July 2024. Unlike previous studies that relied solely on support and confidence metrics, this research adopts the lift metric to evaluate the strength of associations between items, thereby reducing the risk of generating invalid or spurious rules. The comparison is conducted under 15 combinations of minimum support and lift threshold values. Results show that the Apriori algorithm outperforms FP-Growth in terms of execution time, even though both produce identical association rules. In the scenario of minimum support 0.0005 and minimum threshold 1.5, Apriori completes the process in 3.23 seconds, about 6.7 times faster than FP-Growth which takes 21.81 seconds. Additionally, a Streamlit-based analytical dashboard was developed to interactively display frequent itemsets, association rules, and product recommendations. This study provides practical contributions to inventory management and sales strategy, offering an adaptive and relevant analytical approach for MSMEs in the retail sector.
| Item Type: | Thesis (Undergraduate) | ||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Contributors: |
|
||||||||||||
| Subjects: | H Social Sciences > HG Finance > HG1709 Data processing Q Science > Q Science (General) Q Science > QA Mathematics Q Science > QA Mathematics > QA76 Computer software Q Science > QA Mathematics > QA76.6 Computer Programming |
||||||||||||
| Divisions: | Faculty of Computer Science > Departemen of Data Science | ||||||||||||
| Depositing User: | Muhimmatul Arofah | ||||||||||||
| Date Deposited: | 20 Jun 2025 02:04 | ||||||||||||
| Last Modified: | 20 Jun 2025 02:04 | ||||||||||||
| URI: | https://repository.upnjatim.ac.id/id/eprint/37736 |
Actions (login required)
 |
View Item |