Sep 2026· Open Access Journal of Artificial Intelligence and Technology· 0 citations
TL;DR
The Adaptive Repayment Optimisation Engine is introduced, a novel framework that applies constrained stochastic optimisation to the design of loan repayment schedules for small and medium-sized enterprises (SMEs) and contributes to the operations research literature by bridging stochastic programming, explainable AI, and financial regulation in a novel application domain.
Abstract
This paper introduces the Adaptive Repayment Optimisation Engine (AROE), a novel framework that applies constrained stochastic optimisation to the design of loan repayment schedules for small and medium-sized enterprises (SMEs). Unlike fixed-payment or simple revenue-share structures currently dominant in UK SME lending, AROE decomposes each borrower’s cash flow into trend, seasonality, cyclicality, and idiosyncratic volatility components, then uses Monte Carlo simulation and bounded quasi-Newton optimisation to find repayment schedules that minimise the probability of payment distress subject to lender return constraints. A generative AI explanation layer then translates the mathematical output into natural language rationale serving three audiences: borrower, underwriter, and regulator. We validate the framework on a synthetic universe of 10,000 UK SMEs calibrated to ONS, British Business Bank, and sectoral insolvency data across ten SIC-aligned industry sectors and twelve UK regions. Computational experiments demonstrate that AROE optimised schedules reduce payment distress probability by a mean of 7.7–26.6% compared to equivalent fixed-payment benchmarks, with the largest improvements observed in sectors exhibiting high revenue volatility and pronounced seasonality (Construction, Accommodation s Food, Retail). We discuss the implications for FCA Consumer Duty compliance, IFRS 6 provisioning, and the commercial viability of the approach as a SaaS product for lending platforms. The framework contributes to the operations research literature by bridging stochastic programming, explainable AI, and financial regulation in a novel application domain.
Automated market makers (AMMs) are a cornerstone of decentralised finance (DeFi). Constant product markets with concentrated liquidity, such as UniswapV3, are now a well-established design. In these markets, liquidity providers (LPs) face a sequential decision problem: they must decide when to rebalance their positions and which price ranges to allocate capital to as market conditions evolve. We formulate dynamic liquidity provision as a stochastic impulse control problem and use reinforcement learning (RL) to solve it, focusing on providing interpretable solutions. We show that learned policies exhibit rich state-dependent behaviour, allocating liquidity according to mispricing, rebalancing costs, uncertainty, inventory exposure, and heterogeneous risk preferences. These behaviours help compress the left tail of the Profit and Loss (PnL) distribution and avoid catastrophic outcomes under high uncertainty. Finally, we benchmark the RL agents against baseline and sophisticated agents from the AMM microstructure literature and analyse their performance.
Georgios Chionas, Charalampos Kleitsikas, Stefanos Leonardos et al.· 0 citations
Decentralized Finance (DeFi) lending protocols currently rely on heuristic, utilization-based bonding curves that mandate severe over-collateralization, systematically excluding under-collateralized assets like corporate invoices. This paper introduces a mathematically optimal pricing mechanism for decentralized credit: the Reverse Kelly Automated Market Maker (rkAMM), the core engine of our proposed lending framework. By inverting the Kelly Criterion, traditionally used for optimal bet sizing, we construct a dynamic interest rate discovery protocol that explicitly prices individual loan risk. The rkAMM ingests real-time Probability of Default (PD) streams from an off-chain Explainable AI oracle and dynamically calculates the exact interest rate required to sustain target liquidity provider (LP) yields. We mathematically derive the Reverse Kelly pricing function ($r = \frac{y + PD}{1 - PD}$), proving its strictly convex superiority over Aave and Compound's static utilization curves in managing capital efficiency. Furthermore, we deploy the rkAMM architecture via Solidity smart contracts, optimizing for gas-efficient 1e18 (WAD) floating-point arithmetic. To ensure decentralized transparency, our simulation infrastructure leverages MLflow for tracking yield hyperparameters, Data Version Control (DVC) linked to DagsHub for versioning Real-World Asset (RWA) data arrays, and localized edge-inference via Ollama (Llama-3) and Hugging Face (FinBERT) for zero-cost predictive modeling. Monte Carlo simulations across 10,000 macroeconomic stress scenarios confirm that the rkAMM maintains protocol solvency and stabilizes LP yields at 12-15\% net of expected credit losses. This work provides the foundational financial engineering required to bridge the \$2 trillion global supply chain finance gap using permissionless blockchain infrastructure.
Sai Srikanth Madugula, Peplluis Esteva de la Rosa, Daya Shankar· 0 citations
Traditional portfolio management systems often rely on static rules or fixed prompts, which limits their ability to adapt to changing market conditions. This paper proposes a closed-loop multi-agent decision framework that introduces prompt-level learning as a scalable alternative to full model retraining. The architecture comprises specialised agents for market signal extraction, sentiment analysis, macroeconomic interpretation, risk control, and portfolio construction, all coordinated through the DSPy framework and powered by Llama 3.1 8B.A key contribution is a feedback-driven optimisation mechanism that refines agent prompts using realised trading outcomes without human intervention. Moderate drawdowns trigger incremental prompt updates, while severe drawdowns activate full prompt reconfiguration. Empirical evaluation on a six-year dataset (2015–2020) shows that the system achieves cumulative returns above 80% with improved risk-adjusted performance (Sharpe > 1.5), outperforming a SPY buy-and-hold benchmark, including during the COVID-19 market disruption. Overall, the results highlight the potential of prompt-level adaptation for building robust and autonomous financial decision systems.
Kandarp Mukeshkumar Sharda, Aliyu Sani Sambo· NLP & Big Data· 0 citations
Markowitz defined portfolio risk as an internal property, built from the covariance among a book's own holdings rather than the distance to any index. Seventy years of simplification reversed that. The market beta of CAPM, the fixed style and industry axes of Barra-type models, and the promotion of benchmark deviation to the definition of risk all traded the inward view for an external one. Risk became distance from an index. For a fund that fits no benchmark, that trade fails. A global book concentrated in a few markets and a few innovation sectors has no natural index to deviate from, and the active-risk number it produces measures the mismatch, not the risk. We return to the covariance. Principal component analysis (PCA) recovers the systematic structure inside the portfolio directly from its own returns. PCA has always carried one cost: its factors resist a plain-English reading. We clear that with a generative-AI labelling layer. It names the leading factors, ranked by their actual contribution to risk rather than by universe variance, and a deterministic rubric keeps it from inventing structure the loadings do not contain. Around this sit four independent signals. Density-based clustering with a mismatch ratio flags groups whose risk outruns their capital. A sign-invariant PCA Risk Score (PRS) marks the names that build the dominant factor bets. A standalone Bleed score catches the slow capital destroyers PCA cannot see. A trailing-return timing gate routes disagreements between the risk signals and recent price action to human judgment. We run the full engine on a proxy global-innovation book of thirty names over one year.
Swaraj Gambhir, T. George, K. Sivasankar· 0 citations
Payroll-anchored retail borrowers—individuals whose monthly remuneration is routed into an account at the lending institution through a salary-project arrangement—constitute the volume backbone of unsecured consumer lending in Kazakhstan, generating the largest origination flow, the lowest realized default rate, and the majority of the systemic regulatory and capital sensitivities of second-tier banks. Payroll anchoring also changes the lender’s information set, which motivates a study of how that advantage translates into model performance and borrower outcomes. We design and internally validate an explainable hybrid artificial-intelligence framework stratified by client tenure into two production models: a Weight-of-Evidence (WOE) logistic-regression scorecard for new salary-project applicants, and a hybrid scorecard for repeat applicants, in which a stacked ensemble of LightGBM, CatBoost and a multi-head self-attention neural network contributes a single WOE-encoded predictor to a second-stage L2-regularized logistic regression. The hybrid recovers a substantial share of the ensemble’s discriminatory lift while preserving an auditable, monotone scorecard at the point of decision, and isotonic recalibration restores the predicted probabilities of default to the empirical bad-rate scale required for IFRS 9 expected-credit-loss accrual and risk-based pricing. We report discrimination, calibration and stability evidence under a strict anti-leakage protocol and set out the structural preconditions under which the architecture transfers to other emerging-market payroll-anchored portfolios. We are explicit about scope: a true out-of-time validation and a full group-conditional fairness audit are identified as required next steps rather than claimed here. The contribution is a reproducible, interpretable scoring design that exploits payroll visibility while retaining full coefficient interpretability inside the production decision engine.
Gulnaz Zakariya, A. Moldagulova, Nor’ashikin Ali· Applied Informatics· 0 citations
We develop a continuous-time structural dynamic model to determine the exact insolvency regions of banks arising from the non-linear interaction between liquidity and credit risk. While existing literature predominantly treats these risks in isolation or via reduced-form specifications, we explicitly model the feedback loop where funding shocks and regulatory constraints force balance-sheet adjustments that can lead to endogenous insolvency. By incorporating Basel III regulatory requirements (LCR and NSFR) into a stochastic optimal control framework, we solve for the exact insolvency boundary using the Hamilton-Jacobi-Bellman (HJB) equation. To bridge the gap between theoretical complexity and supervisory practice, we derive and validate a surrogate analytical approximation function that allows for real-time monitoring. Calibrated using granular balance-sheet data from the Iranian banking sector, our model reveals significant non-linear threshold effects: the joint occurrence of liquidity stress and credit portfolio defaults disproportionately accelerates the transition toward insolvency compared to their individual effects. The proposed surrogate function offers supervisors a computationally efficient tool for stress testing and early warning systems. Our findings provide novel insights into financial frictions in emerging markets and offer a rigorous framework for integrated risk management.
A new method for surgically removing training examples from a model reveals that as datasets grow, the link between what a model learns and what it produces dissolves.
