Research

Problem

Classical allocators minimize variance and treat drawdown depth and recovery time as constraints rather than first-class objectives.

Method

Models drawdown geometry and recovery stability directly. Allocates capital to maximize resilience rather than minimize variance. Evaluated on 31 years of multi-asset data with out-of-sample validation across independent splits.

Contributions

• Sharpe 1.54 and max drawdown 9.11% versus buy-and-hold 0.52 and 55.19%.
• Resilience-first objective that admits nonlinear drawdown penalties.
• Out-of-sample validation across independent splits.

Problem

Blink-phase segmentation from vertical EOG signals supports dry eye assessment but is sensitive to morphological variation across cohorts.

Method

A CNN-BiGRU sequence model trained on vertical EOG traces to segment blink phases across normal and dry-eye cohorts. Strict leave-one-subject-out validation across 43 subjects.

Contributions

• CNN-BiGRU sequence model that generalises across normal and dry-eye morphologies.
• Leave-one-subject-out validation across 43 subjects.
• First-author work conducted during the Indiana University Bloomington research internship.

Problem

Policy-gradient methods degrade under non-stationary reward landscapes due to limited exploration diversity.

Method

A swarm-style exploration loop on top of policy-gradient RL. The agent maintains a population of candidate directions instead of relying on a single gradient step. Robustness tested under shifting reward structures.

Contributions

• Swarm-augmented exploration robust to non-stationary rewards.
• Drop-in compatible with standard policy-gradient pipelines.
• Empirical gains in regimes where vanilla policy gradient methods fail.

Problem

Top-k retrieval over-fetches documents, increasing latency and compute cost. The overhead is particularly costly on edge devices.

Method

A PPO-trained selector replaces top-k with adaptive retrieval. The reward is shaped by downstream generation quality and on-device latency. Drop-in compatible with existing LLMs and retrievers.

Contributions

• Document selection in RAG framed as a reinforcement learning problem with sparse, cost-aware rewards.
• Edge-feasible deployment without modification to underlying models.
• Selected as Best Paper Candidate at ICEdge 2025 (lecture track).

Problem

Early-stage startups have access to AI tooling but lack frameworks to convert it into strategic advantage.

Method

Mixed-methods analysis across healthcare, finance, retail, and education case studies, synthesised with recent AI entrepreneurship literature into a single framework for AI adoption in small teams.

Contributions

• A framework linking AI/ML adoption to strategic agility, operational efficiency, and innovation capacity.
• Identification of technical, ethical, and regulatory barriers with proposed mitigations.
• Best Paper Award at ICEI 2025.

Problem

Several hypercube variants lack closed-form expressions for the Wiener index.

Method

Combinatorial derivation of exact Wiener index expressions for hypercubes and selected variants.

Contributions

• Closed-form Wiener index expressions for hypercubes and variants.
• Verifiable proof structure with explicit bookkeeping.
• Connections to network distance metrics in graph learning.

Problem

Human portfolio managers carry well-documented cognitive biases that large language models do not share, motivating the substitution of an LLM for the biased human interpreter inside a portfolio agent.

Method

ORACLE fuses an LLM observer, a sentiment block, and Hidden Markov regime estimates into a single belief vector consumed by a regime-conditioned PPO executor. Evaluated with walk-forward analysis on a multi-asset universe against a fair classical baseline.

Contributions

• A negative result: the LLM-augmented agent fails to beat a fair classical baseline, with an ablation isolating where each component helps or hurts.
• A causal audit showing the LLM signal is heeded but miscalibrated, which suggests some human biases are adaptive priors a general-purpose LLM does not carry.
• A reproducible benchmark and evaluation protocol for LLM-augmented portfolio agents.

Problem

Sovereign wealth funds are commonly modelled as static allocation pools. This treatment ignores their dynamic risk behaviour during crises.

Method

Reformulates SWFs as dynamic risk systems through stochastic control and causal ML under regime uncertainty. Critical review of stability, volatility, and crisis transmission across decades of macro-financial data.

Contributions

• Reframes SWFs as dynamic risk systems rather than static portfolios.
• Stochastic-control and causal-ML lens for behaviour under regime change.
• Submitted to the Journal of Financial Stability.

Problem

Streaming graph partitioners place vertices without information about future graph evolution. Performance degrades on drifting workloads.

Method

Per-vertex residency prediction with utility-based migration admission. Benchmarked against seven partitioners on synthetic and real temporal networks, with offline-oracle decision-quality analysis.

Contributions

• Per-vertex residency prediction robust to distribution drift.
• Utility-based migration admission with positive expected payoff requirement.
• Offline-oracle analysis separating policy quality from bookkeeping noise.

Problem

Imitation of black-box trading strategies without recovering the underlying objective fails under distribution shift.

Method

Two-stage IRL plus RL pipeline. Inverse RL recovers the latent reward behind observed trading behaviour. RL re-optimises against the recovered reward with risk-aware and transaction-cost-aware shaping. Evaluated on historical equity and derivatives data with reproducibility-first methodology.

Contributions

• Recovers an interpretable reward from observed trajectories before re-optimisation.
• Risk- and transaction-cost-aware reward shaping in stage two.
• In preparation for an AI/finance venue.

Problem

The conference version of ARISE established empirical robustness. The journal extension requires theoretical analysis of when and why swarm-perturbed policy gradients converge.

Method

Convergence and exploration-exploitation trade-off analysis for swarm-based perturbation in policy-gradient RL, paired with expanded empirical evaluation across non-stationary benchmarks.

Contributions

• Convergence and exploration-exploitation analysis for swarm-perturbed policy gradients.
• Expanded empirical sweep on non-stationary benchmarks.
• Journal extension of ARISE (WCSC 2026), in preparation.

Problem

Static variance-minimising allocators average across market regimes. Cross-asset dependencies shift over time, degrading single-model performance through regime change.

Method

Two-level meta-learning GNN with a transformer-based temporal encoder over dynamic correlation graphs of the top 108 S&P 500 constituents. Meta-learning adjusts parameters across market regimes.

Contributions

• Preliminary out-of-sample cumulative return of 708% with Sharpe approximately 2.02.
• Statistically significant risk-adjusted performance versus zero-return benchmarks (p < 0.001, bootstrap and z-tests).
• Working paper in preparation.