At the time when "smart campus" is popular, the warm care of campus is an important element of smart campus, and the big data consumption evaluation model derived from the analysis of big data and data mining can effectively determine the consumption level and family economic status of various students, so as to accurately identify the students in need of help on campus, and provide important data support for the granting of college The article provides an important data support for grant distribution and facilitates warm-hearted assistance to them. The article classifies each student according to his or her consumption amount and gives the top three hundred students with low consumption levels. Considering the existence of values in the data and the existence of helping classmates to bring meals, only those students who have consumption for all three months and whose consumption amount is below 30 yuan each time are analyzed. A K-Means clustering evaluation model was constructed for them to obtain three types of students with different consumption types, while each student was given a positive rating, which was ranked in ascending order to obtain a list of target students. On this basis, the consumption window factor was added, and after eliminating the non-essential consumption types, the consumption window price level was used to classify them, and two types of low consumption windows and high consumption windows were obtained, while scores were assigned to various windows, and positive scores were given to each student window consumption in turn, and the optimized K-Means clustering evaluation model was used to rank them in ascending order to obtain the target student list.

Junyan Tian, Zhijing Wu, Xin Qu. Research on the Evaluation of Financial Aid for Poor Students in Colleges and Universities Based on K-Means Cluster Analysis. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 3: 111-117. https://doi.org/10.25236/AJCIS.2023.060314.

[1] https://blog.csdn.net/qq_32892383/article/details/80107795. K-Means clustering algorithm detailed 2022.5.14

[2] Lin Chongde. Dictionary of Psychology: Shanghai Education Press, December 2003

[3] Sun YH, Zhang MD. Hierarchical DEMATEL analysis method based on R-type clustering [J]. Practice and understanding of mathematics, 2019, 49(06): 42-51.

[4] Li Weichun. Application of Q-type clustering method based on IBM-SPSS in teacher evaluation [J]. Fujian Computer, 2017, 33(01): 150-151. DOI: 10.16707/j.cnki.fjpc. 2017.01.079.

[5] Yi Guijiao. Using big data to build a precise financial aid system for poor students in colleges and universities [J]. School Party Construction and Thought Education, 2020(22): 28-30.

[6] Jiang Dongxing, Fu Xiaolong, Yuan Fang, Wu Haiyan, Liu Qixin. Discussion on the construction of university wisdom campus under the background of big data [J]. Journal of East China Normal University (Natural Science Edition), 2015(S1): 119-125+131.

[7] Yang Junbang, Zhao Chao. A review of research on K-Means clustering algorithm [J]. Computer Engineering and Applications, 2019, 55(23): 7-14+63.

[8] Zhang Yuanhang. On the "precise financial assistance" for students with family economic difficulties in colleges and universities [J]. Thought Theory Education, 2016(01): 108-111. DOI: 10. 16075/ j. cnki. cn31-1220/g4. 2016.01.020.

[9] Tang Shenwei, Jia Ruiyu. A k-mean clustering algorithm based on improved particle swarm algorithm [J]. Computer Engineering and Applications, 2019, 55(18): 140-145.

[10] Tang Dongkai, Wang Hongmei, Hu Ming, Liu Gang. An improved K-means algorithm for optimizing initial clustering centres [J]. Small microcomputer systems, 2018, 39(08): 1819-1823.