Advertising Recommendation System Based on Dynamic Data Analysis

The research paper describes and evaluates privacy-friendly methods to reach to the correct customer by posting the advertisement on social networking sites. The purpose of the research paper is finding good audience for brand advertising. Targeting social-network neighbors resounds well with advertisers, and on-line browsing behavior data counter unthinkingly can allow the identification of good audiences anonymously. This research paper introduces a framework for evaluating brand audiences with the help of Ads Recommendation. This introduces methods of extracting the specified users of social networks from data on visitations to social networking pages, without collecting any information on the identities of the browsers or the content of the social-network pages. The research paper introduces measure of Online Recommendation System. Fine-Grained user are sorted are provided to the advertiser by using the Ads Recommendation Algorithm. To implement the Ads Recommendation system, a Social Networking Platform is created. To implement the proposed algorithm Pattern Matching and Machine Learning concepts are used to implement the project. As by using the ads recommendation system the sorted users are provided to the advertiser as it will maximize the actual conversion ratio of user to the customer. Finally, the evidences are provided that the quasi-social network embeds a true social network along with results from social theory offers ones explanation for the increase in audience brand affinity.