DoctorConstantine Zakkaroff
Senior Lecturer
Department of Accounting and Information Systems
- Senior LecturerDepartment of Accounting and Information Systems
RESEARCH INTERESTS
Dr Constantine Zakkaroff’s current research is strongly interdisciplinary, grounded in Information Systems and computational/digital methods, and expressed through collaborations across health, industry, and public-sector/legal contexts. Across these research directions, his distinctive contribution is the application of advanced digital data management, analytics, modelling workflows, and computational tools to enhance research outcomes through modern methods in machine learning, data visualisation, and medical image analysis.
Data-Driven Discrete-Event Simulations for Pricing Optimisation in the Rental Car Industry
A key research strand focuses on the development of high-fidelity stochastic discrete-event simulation tools for the car rental industry, designed to support capacity-pricing and profit optimisation decisions. This work includes implementation of a state-of-the-art simulation framework driven by real-world statistical inputs (including New Zealand border movement data from Stats NZ), allowing more realistic modelling and forecasting of rental agency profitability and pricing strategies.
Videofluoroscopy Analysis for Swallowing Disorders Research
Another research direction is in medical image analysis, applying modern medical imaging processing and machine learning methods to automate analysis of videofluoroscopy studies used in dysphagia research. This work aims to produce tools that improve kinetic studies accuracy to support clinical diagnostic and therapeutic outcomes for patients with swallowing disorders.
Taxation Review Authority (TRA) Case Database and Dashboard
A third research direction contributes digital and analytical expertise to research on New Zealand’s Taxation Review Authority (TRA) case history. The initial stage focuses on building an interactive database and dashboard to support historical case exploration, followed by a second stage involving AI/Machine Learning-based summarisation of legal case details to enable deeper thematic and jurisprudential insight.