선택한 단어 수는 입니다.
최소 단어 이상 선택하여야 합니다.
최소 단어 이상 선택하여야 합니다.
선택한 단어 수는 30입니다.
최대 10 단어까지만 선택 가능합니다.
최대 10 단어까지만 선택 가능합니다.
제안 방법
- Based on the experiments, we compared the quality of CF based on web usage mining with that of CF based on purchase data and then evaluated the effect of Clustering technique. Our experiments presented that the quality of CF with Web log data) better than CF with Purchase data.
- system. Main research objective of this paper is to develop new procedures for making recommendations that has better quality and more speed compared to previously studied approaches. Therefore, two evaluation metrics are employed for evaluating our procedures in terms of quality and performance requirements.
- quality [Sarwar et al, 2000]. To determine the sensitivity of neighborhood size, we performed an experiment in which we varied the number of neighbors and computed the corresponding Fl metric. Figure 3 shows our experimental results.
- While our experimental results suggest that the proposed methodology are promising new recommendation methodology, these results are based on studies limited to the particular e-commerce site that has small customers, products, and transactions. Therefore, it is required to evaluate our methodologies in more detail using data sets from a variety of large e-commerce sets.
대상 데이터
- Finally, we obtained z transaction database in the form of <time9 cust이ner■너, product-id, shopping-step> which the shopping-s tep represents one of the click-through step, the basket-plac ement step and the purchase step. This database contains tr msactions of 49597 customers on 278 products. In total, th? database contains 428, 510 records that consist of 781 pur chase records, 5, 350 basket-placement records, and 422, 3:'9 click-through records.
※ AI-Helper는 부적절한 답변을 할 수 있습니다.