School for Business and Society
Don Ainomugisha
- PhD student
Profile
Thesis supervisors
Thesis Title
A Principled Integration and Assessment of Statistical Machine Learning in Financial Investing through Time-Series Momentum
Research
Research topic
Exploring effective and efficient employment of statistical prediction to trend financial investing
Research interests
- Statistical machine learning for asset management
- Time‑series momentum and trend‑following strategies
- Cost‑aware portfolio optimisation and execution
- Market regime-specific financial investment strategies
- Robustness and parsimony across assets, horizons and market regimes
- Reinforcement learning for sequential investment decisions
Biography
Biography
Don Ainomugisha is a PhD researcher in Management at the School for Business and Society, University of York. His doctoral project, “Reviving the Trend: A Principled Integration and Assessment of Statistical Machine Learning in Financial Investing through Time‑Series Momentum,” develops a cost‑aware, regime‑sensitive framework that compares classic, modern and hybrid learning methods for trend‑following across global asset classes.
Originally trained as a civil engineer (BSc, University of Cape Town), Don spent several years applying quantitative modelling to large‑scale hydrological and transport‑infrastructure projects in sub‑Saharan Africa. A growing fascination with financial markets led him to the MSc in Risk Management and Financial Engineering at Imperial College London, where he specialised in machine‑learning‑driven portfolio optimisation, stochastic calculus and systematic trading.
Professionally, Don has held roles as an Investments Operations Analyst at Stars Investments, where he streamlined treasury analytics and performance reporting, and as an academic tutor at the University of Cape Town, where he nurtured analytical thinking in engineering cohorts. These experiences underpin his research agenda, which sits at the intersection of statistical machine learning, cost‑aware and regime-conditioned investment portfolio construction and reinforcement learning for investment decisions.
Don’s overarching aim is to translate rigorous, transparent research into practitioner‑ready tools that enhance the robustness, parsimony and economic value of systematic investment strategies in diverse asset classes and geographic contexts.
⠀