Research Publications

Now showing 1 - 2 of 2

Embargo
A Reinforcement Learning Approach with Human in the Loop to Explainable Insurance Risk Scoring and Intelligent Policy Portfolio Optimization
(Institute of Electrical and Electronics Engineers, 2026-05-29) Gamage, C; Kasthuriarachchi, T; Denuwan, C; Mallawaarachchi, P; Abeywardhana, L; Nawarathne, M
Assessing individual risk accurately and optimizing insurance portfolios in real time remain major challenges due to static actuarial tables, opaque models, and fragmented analytical pipelines. This paper proposes a two-part Explainable AI (XAI) framework addressing both issues. The first component, Artificial Intelligence-driven risk scoring with human-in-the-loop (HIL) weight adjustment, uses a Proximal Policy Optimization (PPO) agent to suggest feature-based changes to an insurer's risk-equation weights. Shapley Additive Explanations(SHAP) attributions and Generative AI reasoning make these changes interpretable, allowing human reviewers to approve modifications that are immediately applied to future customers, creating a self-improving loop. The second component, AI-driven policy optimization, leverages a PPO supported by an XGBoost expense regressor, SHAP/LIME explainability, PPO agent and a Retrieval-Augmented Generation (RAG) layer for rider assignment. Both components share a data backbone of 100,000 anonymized insurance records stored in MongoDB, enabling incremental updates without reprocessing. Experiments show the XGBoost regressor achieves Root Mean Square Error (RMSE) 0.4406 and Mean Absolute Error (MAE) 0.3600, the HIL guided agent increases average episodic reward by 10.3%, and the RAG layer reaches 91.7% rider-assignment accuracy. The framework significantly enhances predictive accuracy, interpretability, regulatory traceability, and portfolio adaptability compared to traditional actuarial and black-box approaches.
Open Access
Does financial literacy matter for firms? An empirical investigation on Sri Lankan SMEs
(PloS one, 2026-07-21) Arachchi, G. K; Perera, I; Gamage, C; Wijesinghe, S; Wisenthige, K; Dayapathirana, N
Small and Medium Enterprises (SMEs) are vital to economic growth and job creation, especially in developing countries. However, their potential is not fully utilized due to challenges related to limited financial inclusion, poor resource management, and underdeveloped capital markets. Though financial literacy is well-researched in personal finance, its role as a knowledge resource at the firm level and its impact on firm performance remain underexplored. This study investigates the influence of owner-managers' financial literacy on firm performance, focusing on the mediating roles of FinTech adoption and access to finance. By taking a sample of 264 SME owner-managers in the Western Province of Sri Lanka, this study found that financial literacy significantly enhances firm performance (β = 0.241, p < .01). The findings indicate that financial literacy supports sound financial decision-making and risk mitigation and is positively associated with both FinTech adoption (β = 0.542, p < .001) and access to finance (β = 0.533, p < .001). These results underscore the necessity of enhancing financial literacy and promoting FinTech adoption to fully realize the potential of SMEs within developing economies. The study contributes a concise yet impactful framework for enhancing the performance of SMEs through the strategic application of financial literacy. Based on the study's findings, it is recommended that enterprise owners and managers prioritize achieving an adequate level of financial literacy. Furthermore, governmental institutions should revise their financial literacy programs, reconsidering their design and implementation strategies to effectively engage key personnel within enterprises. Current programs appear underutilized due to deficiencies in depth and practical applicability of the knowledge given in them.

Research Publications

Browse

Filters

Advanced Search

Filter by

Settings

Sort By

Results per page

Search Results