Targeted Poverty Alleviation refers to the targeted funding work completed in the process of higher education development. However, at present, in the process of implementing the requirements of Targeted Poverty Alleviation in China's universities, some students' families are difficult to complete identification, and there are also some problems in the information management of the funders, which has seriously affected the funding for students with financial difficulties in their families during the period of higher education in China. With the rapid development and progress of Big data technology, through the establishment of a sound information technology system, we must help students actively change the funding model in the future and greatly improve the funding, which is of great significance to the development of university funding supervision and management.

With the development of teaching reform, how to optimize funding and education activities from the perspective of "Great Ideological and Political Education" and improve accuracy has become a focus. From the analysis of the current teaching development situation, the guiding role of ideological and political education in funding precision education activities has been very obvious. To better enhance the effectiveness of funding education, actively optimize the precision of funding education, and innovate the way related activities are carried out, which is an inevitable choice for better education work. Based on this, this article mainly studies the precise methods of funding education under the perspective of "Great Ideological and Political Education", for reference only.

This research presents a novel approach utilizing a self-enhanced chimp optimization algorithm (COA) for feature selection in crowdfunding success prediction models, which offers significant improvements over existing methods. By focusing on reducing feature redundancy and improving prediction accuracy, this study introduces an innovative technique that enhances the efficiency of machine learning models used in crowdfunding. The results from this study could have a meaningful impact on how crowdfunding campaigns are designed and evaluated, offering new strategies for creators and investors to increase the likelihood of campaign success in a rapidly evolving digital funding landscape.