The study proposed in this paper analyses the problems existing in the college course score prediction methodologies. Because of diversity and multiple choices in course selection, the analysis of college students’ course score can be quite complex. This paper proposes a student achievement prediction method based on factor analysis (FA) and Back-Propagation (BP) neural network. Our method is based on the improvement of FA algorithm. Firstly, special factors will be added to complement the equation of common factor score. Secondly, the initial equation of common factor score will be improved. Thirdly, a new equation intended to give an estimation of the special factors mentioned in the first point will be proposed. Finally, an improvement on the common factor loading matrix will be made. We use the improved equation of common factor score to calculate the score of each common factor. Then we use these scores as the input vector of the BP neural network. The output of the neural network is brought into the final equation to get the final prediction result. The experimental results show that the prediction accuracy is very high and the prediction model can be used for most of the college courses. The error on the prediction result is reduced by using the prediction model proposed in this paper. Therefore, the model developed in this paper is very effective and has high application value.
[1]
Jianqiang Yi,et al.
BP neural network prediction-based variable-period sampling approach for networked control systems
,
2007,
Appl. Math. Comput..
[2]
Kurt Hornik,et al.
Multilayer feedforward networks are universal approximators
,
1989,
Neural Networks.
[3]
Christian Borgelt,et al.
Induction of Association Rules: Apriori Implementation
,
2002,
COMPSTAT.
[4]
Wang Ji-shun.
Comprehensive Evaluation on the Marks of Statistical Practices Graduates Based on Factor Analysis and Cluster Analysis
,
2011
.
[5]
Wm. R. Wright.
General Intelligence, Objectively Determined and Measured.
,
1905
.
[6]
Al Cripps,et al.
Using artificial neural nets to predict academic performance
,
1996,
SAC '96.
[7]
Sotiris B. Kotsiantis,et al.
PREDICTING STUDENTS' PERFORMANCE IN DISTANCE LEARNING USING MACHINE LEARNING TECHNIQUES
,
2004,
Appl. Artif. Intell..
[8]
Dimitrios Kalles,et al.
ANALYZING STUDENT PERFORMANCE IN DISTANCE LEARNING WITH GENETIC ALGORITHMS AND DECISION TREES
,
2006,
Appl. Artif. Intell..
[9]
Rakesh Agarwal,et al.
Fast Algorithms for Mining Association Rules
,
1994,
VLDB 1994.