Implementation of Association Rules with Apriori Algorithm in Determining Customer Purchase Patterns
4th IEEE International Conference of Computer Science and Information Technology, ICOSNIKOM 2022
; 2022.
Article
in English
| Scopus | ID: covidwho-2281737
ABSTRACT
Micro, Small, and Medium Enterprises in Indonesia Usaha Mikro, Kecil, Menengah (UMKM) have been affected by the COVID-19 pandemic. The barcode scanning system currently only helps support the buying and selling process and cannot determine the provision of stock or the creation of promotional packages. Website application development using the Association Rule Method with the Apriori Algorithm is the solution offered to produce a pattern of relationships between products that buy by customers. The goods relationship is the basis for making decisions by shop owners to determine the stock of interconnected goods or making promotional packages with the association method by calculating the value of support and confidence. The system was built using the PHP programming language and 4820 transaction data. The results of data analysis through the website using the Antoni store dataset show the results of association rules. Based on 50 experiments conducted by researchers, if the Antoni shop wants to produce two directions, it is better to use minimum confidence of 10% or 12% with minimum support of 2% or 4%. However, if you want to produce 1 rule, you should use minimum confidence of 14%, 16%, or 18% with minimum support of 2%, 4%, or 6%. The lift ratio value of each minimum belief and the recommended support are more significant than 1. Therefore, the combination of association rules results is solid and valid. It can be used that this algorithm is suitable for a collection of related items, so it is appropriate to be used in analyzing product sales patterns at Antoni Stores. © 2022 IEEE.
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
4th IEEE International Conference of Computer Science and Information Technology, ICOSNIKOM 2022
Year:
2022
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS