Association Rule Mining Using Market Basket Analysis
Knowledge discovery in databases (KDD) is a field whose goal is to extract usable knowledge from a collection of data (Pazani et al. 1997). Many applications have applied knowledge discovery especially for the company or any applications that use large database in their company activities. This is...
| 第一著者: | |
|---|---|
| フォーマット: | 学位論文 |
| 言語: | 英語 英語 |
| 出版事項: |
2003
|
| 主題: | |
| オンライン･アクセス: | https://etd.uum.edu.my/1075/1/NOR_FADILAH_BT._TAHAR_%40_YUSOFF.pdf https://etd.uum.edu.my/1075/2/1.NOR_FADILAH_BT._TAHAR_%40_YUSOFF.pdf https://etd.uum.edu.my/1075/ |
| Abstract | Abstract here |
| 要約: | Knowledge discovery in databases (KDD) is a field whose goal is to extract usable knowledge from a collection of data (Pazani et al. 1997). Many applications have applied knowledge discovery especially for the company or any applications that use large database in their company activities. This is because that knowledge discovery is very important to extract the useful knowledge in order to improve marketing strategy. Market Basket Analysis (MBA) is one of data mining techniques thut can be used in marketing strategy. Its purpose is to find interesting relationships among retail products. Market basket analysis is used to understand customers buying habits and preference. The results of this analysis can help the retailers to design promotions, arrange shelf or catalogue items and develop cross marketing strategies. To do the analysis, association rules mining is the popular technique for market basket analysis because of their potential in extracting rules between items in transactions. This study presents the analysis using market basket to find the new rules of item that purchased together in transactions. The result of statistical analysis is also presented in this studying in order to compare and then to validate the rules that obtained from a priori algorithm. |
|---|