الفهرس 
Table of contentsOnly 14 pages are availabe for public view
 |  | from | 132 |  |  |
| | | from | 132 | | |
Abstract
Due to the increase of retail sales all over the world, especially in Egypt. As Egypt has passed with a lot of economic and political changes recently ( since 2010 until now) these changes make retail sales came in the first degree of national income ( source commerce ministry January 2016). from this point of view, came the importance for increasing the retail sales. the managers of supermarkets of course need to increase their profits, so they need to develop marketing strategy to maximize their profits, by getting rid of inactive products. Product bundling is one of the most important marketing strategies used to get rid of stock by making integrated bundles of inactive products and demanded products with discount prices. We can do that through our recommendation system and also increase customers’ faith by keeping up with their purchase habits changes in low prices. In this study, first association rules are applied to find the best-integrated bundles with optimal suggested bundle size according to customer habits. Second testing these resulting product bundles to eliminate bundles didn’t contain Products aim to get rid of them. Finally the given suggested bundles’ elements replaced with stagnant products that are the same kind of product in the bundle but with another trade. During that study algorithms (Apriori and Frequent pattern-growth) were studied. Although the two algorithms give strong association rules, and the results were so near. But FP-Growth algorithm was more efficiency as Apriori algorithm caused problems with minimum support parameter as, in a small system transaction, big minimum support did not work when using it. Also, it makes the memory PC faces memory hangs when minimum support was very low. On the other hand, all of this didn’t appear with FP-Growth algorithm, and it was faster in dealing data. Also during or generating of the system we pay a great attention to The parameters used in association rules and how we can include rare frequent items. To have an accuracy association rules when using these two algorithms we must concern on the Min. confidence value. a good algorithm must be investigated carefully and a multilayered approach to association rule should be developed. Although applying the traditional data mining techniques, the rules still ignore rare frequent items. So, the researcher develop suggested system for data mining production , that replace frequent items with rare ones of the same type, that rare ones apply the condition of wanting to get rid of them. The previous work that was done in producing product bundle using data mining techniques, produce bundles with high frequency, and they didn’t test the value of Min. confidence, they also didn’t give the retailer the ability to choose the product himself. This thesis aims to strengthen the database accuracy and maximize the profit of retailer. To achieve this goal, it develops an efficient suggested system based on applying a replacement onto the Apriori and Fp-Growth algorithms, after testing the optimum Min confidence it was from ( 0.3 to 0.4) and tested min. support it was 0.1.