Applicatin of suggestion system to e-commerce sites

Digitalization has become possible not only through commodities and tangible assets, but also through human behavior and habits. This has led to the emergence of new data stores for many fields and objectives. Productivity has increased across a variety of industries thanks to the use of these data sources, particularly in e-commerce. Data mining, a technology created to make active use of stored data, recommender systems that maximize data mining benefits, and applications for recommender systems that will help make use of them more effectively are discussed in this study. This study, which has four main sections and detailed subsections, focuses primarily on data mining. Each main section is prepared to cover all the details pertinent to the main topic and divided into subsections based on its content. The needs are assessed from many different perspectives while providing solutions to potential problems. The descriptive concepts, along with the data mining processes and models, which are included in the first chapter, are supported by road maps and described in the context of the subject. In addition to playing a crucial role in supporting the main idea, this part also acts as one of the foundations on which the study is based. The second section is devoted to the recommender systems that are implemented using the data obtained by data mining. The issues that recommender systems present are also analyzed, along with their uses, applications, and advantages. In addition, active and developing recommender systems in the e-commerce industry are also mentioned. The third section, which comprises the literature review, is followed by the fourth section that focuses on the material method. The system data is mentioned first in this case as well without deviating from the basis of data mining and the context of recommender systems. System data is corroborated by activity data. In this process, project designs and necessary analyzes are also presented. The last section is crucial for correctly and effectively implementing data mining and determining a strategy to provide the major advantages. This study puts forward propositions suggestions to manage the segmentation, analysis and filtering processes that emerge as a need to improve the current efficiency of the recommender system applications. Statistics and performances of case studies are also considered as reference while presenting the propositions.