About
I am a data scientist and operational researcher based in Peterborough, UK. My work sits at the point where a forecast becomes a decision: which products to reorder, which delivery slots to offer and at what price, and how to plan when demand is sparse or irregular.
From 2024 to 2026 I was the KTP Associate on a Knowledge Transfer Partnership between Priory Direct and the University of Kent, where I designed and built a forecasting and procurement decision system covering more than 1,200 products. My doctoral research at the University of Essex developed forecast-informed pricing, demand-management and routing methods for attended home delivery, published in the European Journal of Operational Research and Annals of Operations Research. In 2025 I placed sixth of around 180 participants in VN2, the first public inventory-planning competition.
My education runs from software engineering (BSc) through artificial intelligence (MSc, with Distinction) to operational research (PhD). That order explains how I work: I can build the system, I understand the models, and I judge both by the quality of the decision they support. Before moving to the UK I spent six years as a researcher and software developer working on natural-language processing for Arabic text and metaheuristic optimisation, and two years lecturing in computer science.
I am currently completing a manuscript from the KTP work, revising a paper from my doctoral research, and extending my engineering practice through an MLOps programme and study of agentic AI systems. The latter is learning in progress rather than established professional experience, and I describe it that way.
Two general versions, generated from the same record as this site. Both are PDFs.
Priory Direct and the University of Kent (Knowledge Transfer Partnership) · United Kingdom
Designed and built a forecasting and procurement decision-support system for a UK packaging e-commerce business, covering more than 1,200 products, as the Associate employed on a 30-month Knowledge Transfer Partnership.
University of Essex · Colchester, United Kingdom
Supported undergraduate and postgraduate teaching across computer science and mathematical sciences modules.
University of Essex · Colchester, United Kingdom
Doctoral research on forecast-informed pricing, demand management and routing for attended home delivery, using real-world data from Ocado.
Services Centre of Qom Islamic Seminary · Qom, Iran
Applied research and software development in natural-language processing for Arabic text, metaheuristic optimisation and knowledge organisation.
Pooyesh Higher Education Institute · Qom, Iran
Taught programming, algorithms, data structures and applied computing modules.
University of Essex, United Kingdom
Thesis: Dynamic Pricing and Emission Control for E-Grocery Fulfilment.
K. N. Toosi University of Technology, Iran
Research in genetic programming, machine learning and optimisation, leading to three peer-reviewed publications.
Payame Noor University, Iran
In-progress items are listed as such until completed.
Statistical methods (ETS, ARIMA, Theta), intermittent-demand methods, gradient boosting (XGBoost, LightGBM) and global neural forecasting; chronological backtesting, model selection by demand type, fallbacks and uncertainty.
Evidence: KTP case study →Turning forecasts into replenishment recommendations with lead times, service levels and supplier constraints; evaluating ordering policies against holding and shortage cost.
Evidence: KTP case study and VN2 result →Dynamic pricing, customer choice, opportunity-cost estimation, vehicle routing with time windows, dynamic programming, simulation and stochastic optimisation.
Evidence: Doctoral research →Python (pandas, NumPy, SciPy, scikit-learn, Statsmodels), SQL (SQL Server, SQLite, PostgreSQL), R, MATLAB; SAP Business One as a data source; Git, testing, reproducible pipelines; Power BI for stakeholder reporting.
Evidence: About →Peer-reviewed publication in OR and AI journals; undergraduate and postgraduate teaching in AI, machine learning, statistics and programming.
Evidence: Research and Teaching →