Integrating LA and EDM for Improving Students Success in Higher Education Using FCN Algorithm

Table 2

Existing methods of educational data miningEDM and data analytics: parameters, conclusion, and future enhancement.

Author name	Proposed parameters	Conclusion	Future enhancement
Göppert et al. [20]	Accuracy	The findings show that the learning algorithm can accurately anticipate pleasant outcomes including over 95% correctness as well as predict the makespan with less than 3% of distortion	A reinforcement learning-based approach will be used for effective outcomes and more data will be collected
	Mean absolute error
	Validation error
Chango et al. [21]	Accuracy	The efficient outcomes in AUC values and accuracy came from using ensembles and finding the best features technique from variational data sets	Intelligent data aggregation based system will be developed by using abstract features
	AUC
Mubarak et al. [22]	Accuracy	The proposed methodology improves the class imbalance issues	Student textual data will be mined in the future for better outcomes of the model
Fotso et al. [23]	Accuracy	The proposed model can efficiently predict the failure and dropping out students	Inaccurate results will be improved using the optimization technique
Al Nagi et al. [24]	F- measure	The proposed model can handle imbalanced data efficiently	For efficient outcomes of the proposed model accuracy classifiers will be enhanced in future
	Acc
	Rec
	Pre
Raga et al. [25]	Accuracy	The proposed work is a type of project to create a system that may be used in specific collaborative learning contexts to provide an autonomous assessment as well as educator guidance.	For the early warning of poor performance of students, the planned model will be enhanced with a hybrid approach
	AUC

Abbreviations: SVM: support vector machine; CNN: convolutional neural network; LSTM: long-short term memory; DNN: deep neural network; ANN: artificial neural network; DT: decision tree; KNN: k-nearest neighbor; EDM: educational data mining; LA: learning analytics; OULAD: open university learning analytics dataset; AUC: area under the curve; Rec: recall; Pre: precision; acc: accuracy; MAE: mean absolute error rate.