Implementation Strategies and Quality Evaluation Systems for Community College Guided Pathways Programs

Abstract

The “Guided Pathways” program in community colleges can promote the efficient completion of students’ studies without restricting their choices and promote the popularization of education. This paper proposes a specific strategy for the implementation of the Guided Pathway program, and proposes a quality evaluation model for the Guided Pathway program based on the Sparrow Search Algorithm and Deep Neural Networks to construct an evaluation system. In the construction of the quality evaluation model, transient optimization perturbations are added to the SSA to improve the diversity, searchability, and robustness of the population position transformation. DNN cannot retain all the valuable features, so they are optimized to form DRNN, which is the quality evaluation model based on ISSA-DRNN. In terms of overall performance, the ISSA-DRNN algorithm in this paper has a prediction accuracy of more than 98% in different datasets, and the training and testing time required for evaluation is also significantly shorter than that of SVM and DRNN algorithms, resulting in superior overall performance. The quality evaluation of the Guided Pathways program was conducted at a community college in District S, City Q, China. The primary and secondary indicators have mean values between [3.4,3.7] and [3.4,3.6] that fall short of the respondents’ expectation of more than 4 points and cannot meet the demand. The implementation of Guided Pathways in S community college has deficiencies, and it should be improved and optimized by combining them with the implementation strategies proposed in this paper.

Keywords

• sparrow search algorithm
• deep neural network
• issa-drnn
• guided pathways program
• 08a02