ANNE DRANOWSKI

PhD-trained Quantitative Researcher with over seven years of published research experience in quantum group representations and statistical machine learning. Skilled in translating complex mathematical theories into practical, data-driven solutions with real-world impact. Recognized for delivering thoughtful, end-to-end analytical approaches that support strategic growth and informed decision-making. Now seeking to transition into a dynamic quantitative analysis role where deep statistical expertise, intellectual rigor, and collaborative problem-solving are valued. Committed to continuous learning and innovation in high-performing, data-focused environments.

• Machine Learning for Trading, Advanced Data Analytics | Google Cloud
• Deep Learning | DeepLearning.AI
• Databases with SQL, AI with Python | HarvardX
• Corporate Finance, Financial Analysis and Valuation | Marshall

• CNN Knot Detector, 2025, Trained a custom CNN to extract topological features from complex knot diagrams with 97% accuracy. Designed end-to-end data pipeline including data augmentation, labeling heuristics, model tuning. Upgraded to Vision Transformer architecture using Hugging Face for improved generalization on complex, sparse input.
• Asymptotics of Tesler Matrices, 2024, Built scalable simulation and evaluation framework in Python to estimate Markovian asymptotics of constrained lattice paths. Used multiprocessing and NumPy for parallel Monte Carlo estimation. Accepted in EJC., https://arxiv.org/abs/2408.01513
• Topological Data Analysis for Quantum Groups, 2024, Standardized representations of topological objects in cobordism categories, enabling efficient feature engineering for homology-based data clustering, with applications in TDA., https://arxiv.org/abs/2402.11368
• Computational Fusion of Tensor Products, 2023, Developed python package for computing mutations and fusions of matrices representing bases in quantum groups. Deployed containerized infrastructure to test cluster-theoretic predictions against large combinatorial datasets via open-access platform with 50k+ users., https://arxiv.org/abs/2106.07101
• Mining Cluster Structures, 2023, Built experimental framework for generating counterexamples to cluster structure conjecture using symbolic computation and statistical inference over structure combinatorial data. Disproved longstanding hypothesis on cointegration of two fundamental bases, providing robust test for benchmarking LLM reasoning., https://arxiv.org/abs/2202.02490

• Editing: Peer-review including Electronic Journal of Combinatorics, Annals of Combinatorics, Expositiones Mathematicae, Journal of the European Mathematical Society, MathSciNet
• Committees: Evaluated faculty on USC Merit Review Committee for performance-based raises, selected recipients for USC Student Awards Resolution Committee
• Teaching: Recipient of faculty-wide DeLury Excellence in Teaching Award