A Hybrid Feature Selection Framework for Predicting Students Performance
Source abstract
Abstract
Student performance prediction helps the educational stakeholders to take proactive decisions and make interventions, for the improvement of quality of education and to meet the dynamic needs of society. The selection of features for student's performance prediction not only plays significant role in increasing prediction accuracy, but also helps in building the strategic plans for the improvement of students’ academic performance. There are different feature selection algorithms for predicting the performance of students, however the studies reported in the literature claim that there are different pros and cons of existing feature selection algorithms in selection of optimal features. In this paper, a hybrid feature selection framework (using feature-fusion) is designed to identify the significant features and associated features with target class, to predict the performance of students. The main goal of the proposed hybrid feature selection is not only to improve the prediction accuracy, but also to identify optimal features for building productive strategies for the improvement in students’ academic performance. The key difference between proposed hybrid feature selection framework and existing hybrid feature selection framework, is two level feature fusion technique, with the utilization of cosine-based fusion. Whereas, according to the results reported in existing literature, cosine similarity is considered as the best similarity measure among existing similarity measures. The proposed hybrid feature selection is validated on four benchmark datasets with variations in number of features and number of instances. The validated results confirm that the proposed hybrid feature selection framework performs better than the existing hybrid feature selection framework, existing feature selection algorithms in terms of accuracy, f-measure, recall, and precision. Results reported in presented paper show that the proposed approach gives more than 90% accuracy on benchmark dataset that is better than the results of existing approach.
Source: openalex_inverted_index · Quality: baseline
Research context
OpenAlex topics: Online Learning and Analytics · Software System Performance and Reliability · Imbalanced Data Classification Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
References (73)
Show source-provided references
1. Predicting students'performance through classification: A case study
2. A framework for students'academic performance analysis using naïve Bayes classifier
3. Educational data mining for prediction and classification of engineering students achievement
4. Predicting students’ performance using modified ID3 algorithm
5. Predicting academic performance in traditional environments at higher-education institutions using data mining: A review
6. Performance analysis and prediction in educational data mining: A research travelogue
7. A study on feature selection techniques in educational data mining
8. Performance evaluation of feature selection algorithms in educational data mining
9. Selecting relevant educational attributes for predicting students’ academic performance
10. A proposed framework on hybrid feature selection techniques for handling high dimensional educational data,10.1063/1.5005463 ↗
11. A review on predicting student's performance using data mining techniques10.1016/j.procs.2015.12.157 ↗
12. A survey on machine learning techniques for cyber security in the last decade10.1109/ACCESS.2020.3041951 ↗
13. Data mining application in enrollment management: A case study10.5120/7604-0535 ↗
14. Improving quality of educational processes providing new knowledge using data mining techniques10.1016/j.sbspro.2014.07.117 ↗
15. Shaukat · Student's Performance: A Data Mining Perspective · 2017
16. Comprehensive analysis of student's academic failure classification through role-sphere influence and flow betwenness centrality10.1016/j.procs.2017.10.031 ↗
17. Survey of feature selection algorithms in higher education
18. Selecting optimal subset of features for intrusion detection systems
19. Romero · Educational Data Mining · 2014 · 2910.1007/978-3-319-02738-8_2 ↗
20. The impact of artificial intelligence and robotics on the future employment opportunities
21. A model to enhance governance issues through opinion extraction
22. A comprehensive dataset for bibliometric analysis of SARS and coronavirus impact on social sciences10.1016/j.dib.2020.106520 ↗
23. A review of content-based and context-based recommendation systems10.3991/ijet.v16i03.18851 ↗
24. Feature selection of post-graduation income of college students in the United States
25. Feature selection techniques to analyse student acadamic performance using naïve Bayes classifier
26. Modeling and predicting students’ academic performance using data mining techniques10.5815/ijmecs.2016.11.05 ↗
27. An appraisal model based on a synthetic feature selection approach for students’ academic achievement10.3390/sym9110282 ↗
28. Student's performance in the context of data mining
29. Feature selection and classification systems for chronic disease prediction: A review10.1016/j.eij.2018.03.002 ↗
30. Using support vector machines with a novel hybrid feature selection method for diagnosis of erythemato-squamous diseases10.1016/j.eswa.2010.10.050 ↗
31. A hybrid feature selection method to classification and Its application in hypertension diagnosis
32. Sections-based bibliographic coupling for research paper recommendation10.1007/s11192-019-03053-8 ↗
33. Cancer classification with a novel hybrid feature selection technique
34. Performance comparison and current challenges of using machine learning techniques in cybersecurity10.3390/en13102509 ↗
35. Protein-protein interface hot spots prediction based on a hybrid feature selection strategy10.1186/s12859-018-2009-5 ↗
36. A hybrid system with filter approach and multiple population genetic algorithm for feature selection in credit scoring10.1016/j.cam.2017.04.036 ↗
37. An investigation of credit card default prediction in the imbalanced datasets10.1109/ACCESS.2020.3033784 ↗
38. Risk factors identification of malignant mesothelioma: A data mining based approach
39. Handling high dimensional educational data using feature selection techniques
40. Student performance prediction model based on discriminative feature selection10.3991/ijet.v13i10.9451 ↗
41. Big data analytics: Student performance prediction using feature selection and machine learning on microsoft azure platform
42. Identifying Key performance indicators and predicting the result from student data
43. Student pass rates prediction using optimized support vector machine and decision tree
44. A survey on evolutionary computation approaches to feature selection10.1109/TEVC.2015.2504420 ↗
45. Feature selection with multi-view data: A survey10.1016/j.inffus.2018.11.019 ↗
46. A feature fusion based forecasting model for financial time series10.1371/journal.pone.0101113 ↗
47. Feature fusion: Parallel strategy vs. serial strategy10.1016/S0031-3203(02)00262-5 ↗
48. Early versus late fusion in semantic video analysis
49. Random forest feature selection, fusion and ensemble strategy: Combining multiple morphological MRI measures to discriminate among healthy elderly, MCI, cMCI and Alzheimer's disease patients: From the Alzheimer's disease neuroimaging initiative (ADNI) database10.1016/j.jneumeth.2017.12.010 ↗
50. Maimon · Data Mining and Knowledge Discovery Handbook · 201010.1007/978-0-387-09823-4 ↗
51. Predicting defect resolution time using cosine similarity
52. Efficient top-k similarity document search utilizing distributed file systems and cosine similarity10.1007/s10586-015-0506-0 ↗
53. A novel artificial bee colony algorithm based on the cosine similarity10.1016/j.cie.2017.10.022 ↗
54. A feature selection approach based on a similarity measure for software defect prediction10.1631/FITEE.1601322 ↗
55. Cosine similarity metric learning for face verification
56. Arabic text categorization: A comparative study of different representation modes
57. Cosine similarity and the Borda Rule10.1007/s00355-017-1104-2 ↗
58. A cosine-similarity mutual-information approach for feature selection on high dimensional datasets10.4018/JITR.2017010102 ↗
59. An svm framework for malignant melanoma detection based on optimized hog features10.3390/computation5010004 ↗
60. Development and validation of a learning analytics framework: Two case studies using support vector machines10.1007/s10758-014-9226-4 ↗
61. Improving early prediction of academic failure using sentiment analysis on self-evaluated comments10.1111/jcal.12247 ↗
62. Comparative analysis of the properties of the nodular cast iron with carbides and the austempered ductile iron with use of the machine learning and the support vector machine10.1007/s00170-016-8510-y ↗
63. A comparison study of kernel functions in the support vector machine and its application for termite detection10.3390/info9010005 ↗
64. Robust feature selection using ensemble feature selection techniques
65. Forecasting students’ success in an open university10.1504/IJLT.2018.091630 ↗
66. Decision support system of scholarship grantee selection using data mining
67. Rana · Information and Communication Technology for Sustainable Development · 2018 · 7 · 22910.1007/978-981-10-3920-1_23 ↗
68. A novel hybridization of classification trees and artificial neural networks for selection of students in a business school10.1007/s12597-017-0329-2 ↗
69. A tutorial on variable selection for clinical prediction models: Feature selection methods in data mining could improve the results10.1016/j.jclinepi.2015.10.002 ↗
70. Feature selection for high-dimensional data: a fast correlation-based filter solution
71. Key concept identification: A comprehensive analysis of frequency and topical graph-based approaches10.3390/info9050128 ↗
72. Kumar · Knowledge Computing and its Applications · 2018 · 4710.1007/978-981-10-8258-0_3 ↗
73. Using support vector machines with a novel hybrid feature selection method for diagnosis of erythemato-squamous diseases10.1016/j.eswa.2010.10.050 ↗