A CASE-BASED REASONING FRAMEWORK WITH SOFT SIMILARITY AND SUBMODULAR OPTIMIZATION FOR PERSONALIZED CAREER GUIDANCE

Shodmonov Davronjon Abduvaliyevich

Authors

Shodmonov Davronjon Abduvaliyevich Samarkand Branch of Tashkent University of Information Technologies named after Muhammad al-Khwarizmi

Keywords:

Case-Based Reasoning, Conversational CBR, Career Guidance, Hybrid Similarity, Submodular Optimization, Educational Data Mining, Explainable AI

Abstract

The increasing availability of longitudinal academic data in higher education creates new opportunities for personalized and evidence-based career guidance. However, many existing AI-driven guidance systems rely on black-box predictive models and provide limited interpretability or actionable recommendations. This paper proposes a principled Case-Based Reasoning (CBR) framework for personalized career guidance that leverages institutional academic data and historical student trajectories.
The proposed approach models each graduate as a structured case comprising academic profiles, temporal learning trajectories, contextual attributes, observed outcomes, and contributing actions. A hybrid similarity function is employed to retrieve relevant cases from heterogeneous educational data, while a soft-retrieve aggregation mechanism ensures robustness under partial observability and noisy inputs. To bridge the gap between relevance estimation and actionable guidance, the reuse phase is formulated as a constrained submodular optimization problem, enabling the selection of compact and feasible action sets with theoretical approximation guarantees.
Theoretical analysis establishes stability of the soft-retrieve mechanism, probabilistic consistency of outcome inference, and near-optimality of the reuse strategy. Experimental evaluation on real institutional data collected through a higher education management information system demonstrates that the proposed framework consistently outperforms classical CBR and baseline machine learning approaches in outcome prediction. Moreover, submodular reuse optimization significantly improves action recommendation quality by increasing competency coverage and reducing redundancy, particularly in low-cardinality settings that are most relevant for practical advising.
The results indicate that combining case-based reasoning with submodular optimization offers a robust, explainable, and deployable solution for personalized career guidance in higher education.

References

1. Herath, G. A. C. A.; Kumara, B. T. G. S.; Rathnayaka, R. M. K. T.; Ishanka, U. A. P. Computer-Assisted Career Guidance Tools for Students’ Career Path Planning: A Review on Enabling Technologies and Applications. Education Sciences, 2023.

2. Trujillo, F.; Pozo, M.; Suntaxi, G. Artificial Intelligence in Education: A Systematic Literature Review of Machine Learning Approaches in Student Career Prediction. Education and Information Technologies, 2025.

3. Manganello, F. Machine Learning for Post-Diploma Educational and Career Guidance: A Scoping Review in AI-Driven Decision Support Systems. Frontiers in Education, 2023.

4. Aamodt, A.; Plaza, E. Case-Based Reasoning: Foundational Issues, Methodological Variations, and System Approaches. AI Communications, vol. 7, no. 1, pp. 39–59, 1994.

5. Kolodner, J. L. Case-Based Reasoning. San Francisco, CA, USA: Morgan Kaufmann, 1993.

6. Watson, I. Applying Case-Based Reasoning: Techniques for Enterprise Systems. San Francisco, CA, USA: Morgan Kaufmann, 1997.

7. López de Mántaras, R.; McSherry, D.; Bridge, D.; et al. Retrieval, Reuse, Revision and Retention in Case-Based Reasoning. The Knowledge Engineering Review, vol. 20, no. 3, pp. 215–240, 2005.

8. Aha, D. W.; Breslow, L. A.; Muñoz-Avila, H. Conversational Case-Based Reasoning. Applied Intelligence, vol. 14, no. 1, pp. 9–32, 2001.

9. Hillig, S.; Müller, R. How Do Conversational Case-Based Reasoning Systems Interact with Their Users? A Literature Review. User Modeling and User-Adapted Interaction, 2019.

10. Zarandi, M. H. F.; et al. A Fuzzy Case-Based Reasoning Approach to Value Engineering. Expert Systems with Applications, vol. 38, no. 10, pp. 12127–12135, 2011.

11. Khan, M. J. Performance Evaluation of Fuzzy Clustered Case-Based Reasoning. Expert Systems with Applications, vol. 41, no. 4, pp. 1656–1666, 2014.

12. Lorenzi, F.; Ricci, F. Case-Based Recommender Systems: A Unifying View. In: Intelligent Techniques for Web Personalization, LNCS 3169, Springer, 2005, pp. 89–113.

13. Lahoud, C.; et al. A Comparative Analysis of Recommender Systems for University Major and Career Domain Guidance. Education and Information Technologies, 2023.

14. Zhang, X. Logistics Project Risk Response Decision-Making for Global Supply Chain Resilience and Agility: An Optimised Case-Based Reasoning Approach. Journal of Intelligent & Fuzzy Systems, 2025.

15. Vazquez, M. Case-Based Reasoning in Educational Ethics: Phronēsis and Epistemic Blinders. Educational Philosophy and Theory, 1996.

16. Nemhauser, G. L.; Wolsey, L. A.; Fisher, M. L. An Analysis of Approximations for Maximizing Submodular Set Functions-I. Mathematical Programming, vol. 14, no. 1, pp. 265–294, 1978.