{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T23:35:10Z","timestamp":1772840110378,"version":"3.50.1"},"reference-count":49,"publisher":"MDPI AG","issue":"4","license":[{"start":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T00:00:00Z","timestamp":1762300800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["MAKE"],"abstract":"<jats:p>University advising at matriculation must operate under strict information constraints, typically without any post-enrolment interaction history.We present a unified, leakage-free pipeline for predicting early dropout risk and generating cold-start programme recommendations from pre-enrolment signals alone, with an optional early-warning variant incorporating first-term academic aggregates. The approach instantiates lightweight multimodal architectures: tabular RNNs, DistilBERT encoders for compact profile sentences, and a cross-attention fusion module evaluated end-to-end on a public benchmark (UCI id 697; n = 3630 students across 17 programmes). For dropout, fusing text with numerics yields the strongest thresholded performance (Hybrid RNN\u2013DistilBERT: f1-score \u2248 0.9161, MCC \u2248 0.7750, and simple ensembling modestly improves threshold-free discrimination (Area Under Receiver Operating Characteristic Curve (AUROC) up to \u22480.9488). A text-only branch markedly underperforms, indicating that numeric demographics and early curricular aggregates carry the dominant signal at this horizon. For programme recommendation, pre-enrolment demographics alone support actionable rankings (Demographic Multi-Layer Perceptron (MLP): Normalized Discounted Cumulative Gain @ 10 (NDCG@10) \u2248 0.5793, Top-10 \u2248 0.9380, exceeding a popularity prior by 25\u201327 percentage points in NDCG@10); adding text offers marginal gains in hit rate but not in NDCG on this cohort. Methodologically, we enforce leakage guards, deterministic preprocessing, stratified splits, and comprehensive metrics, enabling reproducibility on non-proprietary data. Practically, the pipeline supports orientation-time triage (high-recall early-warning) and shortlist generation for programme selection. The results position matriculation-time advising as a joint prediction\u2013recommendation problem solvable with carefully engineered pre-enrolment views and lightweight multimodal models, without reliance on historical interactions.<\/jats:p>","DOI":"10.3390\/make7040138","type":"journal-article","created":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T13:19:29Z","timestamp":1762348769000},"page":"138","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Personalized Course Recommendations Leveraging Machine and Transfer Learning Toward Improved Student Outcomes"],"prefix":"10.3390","volume":"7","author":[{"given":"Shrooq","family":"Algarni","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of Jeddah, Jeddah 21959, Saudi Arabia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1241-2750","authenticated-orcid":false,"given":"Frederick T.","family":"Sheldon","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of Idaho, Moscow, ID 83843, USA"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,5]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Iatrellis, O., Kameas, A., and Fitsilis, P. (2017). Academic Advising Systems: A Systematic Literature Review of Empirical Evidence. Educ. Sci., 7.","DOI":"10.3390\/educsci7040090"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"560","DOI":"10.3390\/make5020033","article-title":"Systematic Review of Recommendation Systems for Course Selection","volume":"5","author":"Algarni","year":"2023","journal-title":"Mach. Learn. Knowl. Extr."},{"key":"ref_3","first-page":"5340","article-title":"Personalized Course Sequence Recommendations. IEEE Trans","volume":"64","author":"Xu","year":"2016","journal-title":"Signal Process."},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Chang, P.C., Lin, C.H., and Chen, M.H. (2016). A Hybrid Course Recommendation System by Integrating Collaborative Filtering and Artificial Immune Systems. Algorithms, 9.","DOI":"10.3390\/a9030047"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Lee, E.L., Kuo, T.T., and Lin, S.D. (2017, January 19\u201321). A Collaborative Filtering-Based Two-Stage Model with Item Dependency for Course Recommendation. Proceedings of the 2017 IEEE International Conference on Data Science and Advanced Analytics (DSAA), Tokyo, Japan.","DOI":"10.1109\/DSAA.2017.18"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Zhong, S.-T., Huang, L., Wang, C.-D., and Lai, J.-H. (2019, January 8\u201311). Constrained Matrix Factorization for Course Score Prediction. Proceedings of the 2019 IEEE International Conference on Data Mining (ICDM), Beijing, China.","DOI":"10.1109\/ICDM.2019.00199"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Ren, Z., Ning, X., Lan, A.S., and Rangwala, H. (2019, January 5\u20138). Grade Prediction with Neural Collaborative Filtering. Proceedings of the 2019 IEEE International Conference on Data Science and Advanced Analytics (DSAA), Washington, DC, USA.","DOI":"10.1109\/DSAA.2019.00014"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Malhotra, I., Chandra, P., and Lavanya, R. (2022, January 23\u201325). Course Recommendation Using Domain-Based Cluster Knowledge and Matrix Factorization. Proceedings of the 2022 9th International Conference on Computing for Sustainable Global Development (INDIACom), New Delhi, India.","DOI":"10.23919\/INDIACom54597.2022.9763281"},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Zhao, L., and Pan, Z. (2021, January 24\u201326). Research on Online Course Recommendation Model Based on Improved Collaborative Filtering Algorithm. Proceedings of the 2021 IEEE 6th International Conference on Cloud Computing and Big Data Analytics (ICCCBDA), Chengdu, China.","DOI":"10.1109\/ICCCBDA51879.2021.9442575"},{"key":"ref_10","doi-asserted-by":"crossref","unstructured":"Chen, Z., Liu, X., and Shang, L. (2020, January 23\u201325). Improved Course Recommendation Algorithm Based on Collaborative Filtering. Proceedings of the 2020 International Conference on Big Data and Informatization Education (ICBDIE), Zhangjiajie, China.","DOI":"10.1109\/ICBDIE50010.2020.00115"},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"189069","DOI":"10.1109\/ACCESS.2020.3031572","article-title":"Creating a Recommender System to Support Higher Education Students in the Subject Enrollment Decision","volume":"8","author":"Preciado","year":"2020","journal-title":"IEEE Access"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"105385","DOI":"10.1016\/j.knosys.2019.105385","article-title":"Helping University Students to Choose Elective Courses by Using a Hybrid Multi-Criteria Recommendation System with Genetic Optimization","volume":"194","author":"Esteban","year":"2020","journal-title":"Knowl.-Based Syst."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"163034","DOI":"10.1109\/ACCESS.2019.2935417","article-title":"On Recommendation of Learning Objects Using Felder\u2013Silverman Learning Style Model","volume":"7","author":"Nafea","year":"2019","journal-title":"IEEE Access"},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Huang, X., Tang, Y., Qu, R., Li, C., Yuan, C., Sun, S., and Xu, B. (2018, January 9\u201311). Course Recommendation Model in Academic Social Networks Based on Association Rules and Multi-Similarity. Proceedings of the 2018 IEEE 22nd International Conference on Computer Supported Cooperative Work in Design (CSCWD), Nanjing, China.","DOI":"10.1109\/CSCWD.2018.8465266"},{"key":"ref_15","doi-asserted-by":"crossref","unstructured":"Obeidat, R., Duwairi, R., and Al-Aiad, A. (2019, January 26\u201328). A Collaborative Recommendation System for Online Course Recommendations. Proceedings of the 2019 International Conference on Deep Learning and Machine Learning in Emerging Applications (Deep-ML), Istanbul, Turkey.","DOI":"10.1109\/Deep-ML.2019.00018"},{"key":"ref_16","doi-asserted-by":"crossref","unstructured":"Emon, M.I., Shahiduzzaman, M., Rakib, M.R.H., Shathee, M.S.A., Saha, S., Kamran, M.N., and Fahim, J.H. (2021, January 5\u20137). Profile Based Course Recommendation System Using Association Rule Mining and Collaborative Filtering. Proceedings of the 2021 International Conference on Science and Contemporary Technologies (ICSCT), Dhaka, Bangladesh.","DOI":"10.1109\/ICSCT53883.2021.9642633"},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Baskota, A., and Ng, Y.K. (2018, January 6\u20139). A Graduate School Recommendation System Using the Multi-Class Support Vector Machine and KNN Approaches. Proceedings of the 2018 IEEE International Conference on Information Reuse and Integration (IRI), Salt Lake City, UT, USA.","DOI":"10.1109\/IRI.2018.00050"},{"key":"ref_18","doi-asserted-by":"crossref","unstructured":"Liang, Y., Duan, X., Ding, Y., Kou, X., and Huang, J. (2019, January 10\u201312). Data Mining of Students\u2019 Course Selection Based on Currency Rules and Decision Tree. Proceedings of the 2019 4th International Conference on Big Data and Computing, Guangzhou, China.","DOI":"10.1145\/3335484.3335541"},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Oreshin, S., Filchenkov, A., Petrusha, P., Krasheninnikov, E., Panfilov, A., Glukhov, I., Kaliberda, Y., Masalskiy, D., Serdyukov, A., and Kazakovtsev, V. (2020, January 27\u201329). Implementing a Machine Learning Approach to Predicting Students\u2019 Academic Outcomes. Proceedings of the 2020 International Conference on Control, Robotics and Intelligent System (IRCS), Xiamen, China.","DOI":"10.1145\/3437802.3437816"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Srivastava, S., Karigar, S., Khanna, R., and Agarwal, R. (2018, January 11\u201312). Educational Data Mining: Classifier Comparison for the Course Selection Process. Proceedings of the 2018 International Conference on Smart Computing and Electronic Enterprise (ICSCEE), Shah Alam, Malaysia.","DOI":"10.1109\/ICSCEE.2018.8538434"},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Jiang, W., Pardos, Z.A., and Wei, Q. (2019, January 4\u20138). Goal-Based Course Recommendation. Proceedings of the 9th International Conference on Learning Analytics & Knowledge (LAK), Tempe, AZ, USA.","DOI":"10.1145\/3303772.3303814"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"106732","DOI":"10.1016\/j.knosys.2020.106732","article-title":"RBPR: A Hybrid Model for the New User Cold Start Problem in Recommender Systems","volume":"214","author":"Feng","year":"2021","journal-title":"Knowl.-Based Syst."},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Chen, Z., Song, W., and Liu, L. (2017, January 10\u201312). The Application of Association Rules and Interestingness in Course Selection System. Proceedings of the 2017 IEEE 2nd International Conference on Big Data Analysis (ICBDA), Beijing, China.","DOI":"10.1109\/ICBDA.2017.8078708"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Mondal, B., Patra, O., Mishra, S., and Patra, P. (2020, January 13\u201314). A Course Recommendation System Based on Grades. Proceedings of the 2020 International Conference on Computer Science, Engineering and Applications (ICCSEA), Gunupur, India.","DOI":"10.1109\/ICCSEA49143.2020.9132845"},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Bozyigit, A., Bozyigit, F., Kilinc, D., and Nasiboglu, E. (2018, January 19\u201321). Collaborative Filtering Based Course Recommender Using OWA Operators. Proceedings of the 2018 International Symposium on Computers in Education (SIIE), Jerez, Spain.","DOI":"10.1109\/SIIE.2018.8586681"},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"19550","DOI":"10.1109\/ACCESS.2019.2897979","article-title":"A Score Prediction Approach for Optional Course Recommendation via Cross-User-Domain Collaborative Filtering","volume":"7","author":"Huang","year":"2019","journal-title":"IEEE Access"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Dwivedi, S., and Roshni, V.K. (2017, January 3\u20134). Recommender System for Big Data in Education. Proceedings of the 2017 5th National Conference on E-Learning & E-Learning Technologies (ELELTECH), Hyderabad, India.","DOI":"10.1109\/ELELTECH.2017.8074993"},{"key":"ref_28","doi-asserted-by":"crossref","unstructured":"Adilaksa, Y., and Musdholifah, A. (2021, January 16\u201317). Recommendation System for Elective Courses using Content-Based Filtering and Weighted Cosine Similarity. Proceedings of the 2021 4th International Seminar on Research of Information Technology and Intelligent Systems (ISRITI), Yogyakarta, Indonesia.","DOI":"10.1109\/ISRITI54043.2021.9702788"},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Alghamdi, S., Sheta, O., and Adrees, M. (2022, January 29\u201331). A Framework of Prompting Intelligent System for Academic Advising Using Recommendation System Based on Association Rules. Proceedings of the 2022 9th International Conference on Electrical and Electronics Engineering (ICEEE), Alanya, Turkey.","DOI":"10.1109\/ICEEE55327.2022.9772526"},{"key":"ref_30","unstructured":"Bharath, G.M., and Indumathy, M. (2021, January 2\u20134). Course Recommendation System in Social Learning Network (SLN) Using Hybrid Filtering. Proceedings of the 2021 5th International Conference on Electronics, Communication and Aerospace Technology (ICECA), Coimbatore, India."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Kamila, V.Z., and Subastian, E. (2019, January 3\u20134). KNN and Naive Bayes for Optional Advanced Courses Recommendation. Proceedings of the 2019 International Conference on Electrical, Electronics and Information Engineering (ICEEIE), Denpasar, Indonesia.","DOI":"10.1109\/ICEEIE47180.2019.8981450"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"95608","DOI":"10.1109\/ACCESS.2021.3093563","article-title":"Multiclass Prediction Model for Student Grade Prediction Using Machine Learning","volume":"9","author":"Bujang","year":"2021","journal-title":"IEEE Access"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Verma, R. (2018, January 29\u201330). Applying Predictive Analytics in Elective Course Recommender System While Preserving Student Course Preferences. Proceedings of the 2018 IEEE 6th International Conference on MOOCs, Innovation and Technology in Education (MITE), Hyderabad, India.","DOI":"10.1109\/MITE.2018.8747128"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Uskov, V., Bakken, J., Byerly, A., and Shah, A. (2019, January 8\u201311). Machine Learning-based Predictive Analytics of Student Academic Performance in STEM Education. Proceedings of the 2019 IEEE Global Engineering Education Conference (EDUCON), Dubai, United Arab Emirates.","DOI":"10.1109\/EDUCON.2019.8725237"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Revathy, M., Kamalakkannan, S., and Kavitha, P. (2022, January 20\u201322). Machine Learning Based Prediction of Dropout Students from the University Using SMOTE. Proceedings of the 2022 4th International Conference on Smart Systems and Inventive Technology (ICSSIT), Tirunelveli, India.","DOI":"10.1109\/ICSSIT53264.2022.9716450"},{"key":"ref_36","doi-asserted-by":"crossref","unstructured":"Shah, D., Shah, P., and Banerjee, A. (2017, January 5\u20138). Similarity Based Regularization for Online Matrix-Factorization: An Application to Course Recommender Systems. Proceedings of the 2017 IEEE Region 10 Conference (TENCON), Penang, Malaysia.","DOI":"10.1109\/TENCON.2017.8228164"},{"key":"ref_37","unstructured":"Kolena (2024, November 16). Transformer vs. RNN: 4 Key Differences and How to Choose. Available online: https:\/\/www.kolena.com\/guides\/transformer-vs-rnn-4-key-differences-and-how-to-choose\/."},{"key":"ref_38","unstructured":"Appinventiv (2024, October 21). Transformer vs RNN in NLP: A Comparative Analysis. Available online: https:\/\/appinventiv.com\/blog\/transformer-vs-rnn\/."},{"key":"ref_39","doi-asserted-by":"crossref","unstructured":"Barbon, R.S., and Akabane, A.T. (2022). Towards Transfer Learning Techniques\u2014BERT, DistilBERT, BERTimbau, and DistilBERTimbau for Automatic Text Classification from Different Languages: A Case Study. Sensors, 22.","DOI":"10.3390\/s22218184"},{"key":"ref_40","unstructured":"ArXiv (2024, November 15). A Systematic Review of Challenges and Proposed Solutions in Multimodal Fusion. Available online: https:\/\/arxiv.org\/html\/2505.06945v1."},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.inffus.2021.11.011","article-title":"Tabular Data: Deep Learning is Not All You Need","volume":"81","author":"Armon","year":"2022","journal-title":"Inf. Fusion"},{"key":"ref_42","unstructured":"Copyleaks (2024, November 15). What Is Multimodal AI?. Available online: https:\/\/copyleaks.com\/blog\/what-is-multimodal-ai."},{"key":"ref_43","unstructured":"Milvus (2024, November 15). What Are the Advantages of Multimodal Search Over Single-Modality Approaches. Available online: https:\/\/milvus.io\/ai-quick-reference\/what-are-the-advantages-of-multimodal-search-over-singlemodality-approaches."},{"key":"ref_44","unstructured":"Index.dev (2024, November 15). Unimodal vs. Multimodal AI: Key Differences Explained. Available online: https:\/\/www.index.dev\/blog\/comparing-unimodal-vs-multimodal-models."},{"key":"ref_45","unstructured":"Ergoneers (2024, November 15). Multimodal Analysis Advantages. Available online: https:\/\/ergoneers.com\/why-use-multimodal-analysis\/."},{"key":"ref_46","unstructured":"Soppe, K.F.B., Bagheri, A., Nadi, S., Klugkist, I.G., Wubbels, T., and Wijngaards-De Meij, L.D.N.V. (2025). Predicting First-Year Dropout from Pre-Enrolment Motivation Statements Using Text Mining. arXiv."},{"key":"ref_47","first-page":"e13","article-title":"Predictive Model to Identify College Students with High Dropout Rates","volume":"25","year":"2023","journal-title":"Rev. Electr\u00f3n. Investig. Educ."},{"key":"ref_48","first-page":"102214","article-title":"Predicting Student Dropouts with Machine Learning","volume":"77","author":"Vaarma","year":"2024","journal-title":"Technol. Soc."},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Rebelo Marcolino, M., Porto, T.R., Primo, T.T., Targino, R., Ramos, V., Queiroga, E.M., and Cechinel, R.M.C. (2025). Student Dropout Prediction Through Machine Learning and Administrative Data. Sci. Rep., 15.","DOI":"10.1038\/s41598-025-93918-1"}],"container-title":["Machine Learning and Knowledge Extraction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/4\/138\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T14:15:24Z","timestamp":1762352124000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2504-4990\/7\/4\/138"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,5]]},"references-count":49,"journal-issue":{"issue":"4","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["make7040138"],"URL":"https:\/\/doi.org\/10.3390\/make7040138","relation":{},"ISSN":["2504-4990"],"issn-type":[{"value":"2504-4990","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,5]]}}}