MULTI-LABEL CLASSIFICATION IN HIERARCHICAL TAXONOMIES (TAXONOMY-AWARE ML)

The project "Multi-Label Classification in Hierarchical Taxonomies (Taxonomy-Aware ML)" has been successfully designed and developed as a robust and semantically coherent solution for the automated classification of data into hierarchically structured label spaces.   By implementing the Local Classifier per Parent Node (LCPN) strategy with Logistic Regression and TF-IDF feature extraction, the system effectively models parent-child relationships within the taxonomy and guarantees that all predictions are hierarchically consistent. This eliminates the fundamental flaw of conventional flat classifiers that produce logically invalid label assignments.   The empirical results confirm that the taxonomy-aware approach not only ensures logical validity but also enhances overall predictive performance — particularly for rare and fine-grained labels that benefit from sharing statistical strength with their parent categories. The high precision score of 89.5% demonstrates the reliability of the LCPN predictions. The interactive Streamlit dashboard ensures complex technical outputs are accessible to both expert researchers and non-technical users.   Overall, this project demonstrates that incorporating domain knowledge in the form of hierarchical taxonomy structure into the machine learning pipeline leads to more reliable, interpretable, and semantically meaningful classification systems, readily applicable to academic literature classification, product taxonomy management, bioinformatics annotation, and legal document categorization.

1. Silla, C.N. and Freitas, A.A. (2011). A survey of hierarchical classification across different application domains. Data Mining and Knowledge Discovery, 22(1-2), pp.31-72. 2. Vens, C., Struyf, J., Schietgat, L., Dzeroski, S. and Blockeel, H. (2008). Decision trees for hierarchical multi-label classification. Machine Learning, 73(2), pp.185-214. 3. Zhang, M.L. and Zhou, Z.H. (2014). A review on multi-label learning algorithms. IEEE Transactions on Knowledge and Data Engineering, 26(8), pp.1819-1837. 4. Read, J., Pfahringer, B., Holmes, G. and Frank, E. (2011). Classifier chains for multi-label classification. Machine Learning, 85(3), pp.333-359. 5. Pedregosa, F. et al. (2011). Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12, pp.2825-2830. 6. Shimura, K., Li, J. and Fukumoto, F. (2018). HFT-CNN: Learning Hierarchical Category Structure for Multi-label Short Text Categorization. Proceedings of EMNLP 2018, pp.811-816.