عنوان مقاله [English]
Crowdfunding Platforms are transformed to Websites by which people will be able either to back financially new Ideas or to try to seek investment (Fundraising) for their products and services. Whereas in recent years this kind of investment is highly advertised in press circles and many success stories are reported in this kind of investments, many people have referred to these newly developed platforms (websites) and many projects have been launched on these various sites. In spite of dramatic growth of the turnout of the people in the role of investors or in the role of investment attractors, the percentage of successful projects in absorbing complete investment has experienced decreasing growth. The works, which have been conducted with regards to prediction of successful projects, are merely concentrated on optimization of prediction models to improve the prediction procedures, but in these studies the prediction scenarios are not dealt with. But we should consider this fact that without identification and definition of prediction scenarios, we couldn’t reach to the main goal of this undertaking which is to present effective suggestions for success improvement of the launching of crowd funding projects. In this paper, the main objective is to suggest some proposals based on the available information regarding the status of the projects through success prediction of launched projects by means of Business Intelligence: (BI). To realize this, in this paper by using business intelligence features, initially, we have presented a comprehensive model for prediction issues in target business based on Key Performance Indicator: (KPI). Then, according to extracted requests from the model, we gathered a large amount of data from the Kick Start website which consist of the project records, user records, temporal data and projects users profile in famous social media. In the next step, by consideration of extracted model, based on business intelligence, we implemented the corresponding model by means of data analysis for prediction and evaluation of the financial pledges of the implemented projects. Our practical results show that prediction models can predict effectively the success of the projects and also they can suggest, by means of identification of projects success factors, proposals in order to improve the success probability of the projects.