Feb 2020 – Mar 2021 · 1 yr 1 mo · Manchester, United Kingdom

• Pricing & predictive modelling of multi-million pound commercial debt portfolios using quantitative analytics, machine learning and simulation methods.
• Developed a novel methodology to solve a portfolio construction problem using mixed integer linear programming for forward flow purchases.
• Migrated financial modelling framework from Excel to Python, improving stress-testing/ scenario analysis capabilities.
• Implemented and optimised machine learning models (Decision Trees, Random Forests, Gradient Boosting etc.) for forecasting payment behaviour (collections, payments, and settlements).
• Created a machine learning model evaluation tool for feature importance analysis and model explainability.
• Extensive use of object-oriented Python with adherence to PEP standards.
• Wrote investment memos and internal scientific research papers.
• Developed, packaged, and maintained an internal Python library for pricing and analytics.
• Extensive use of high-performance computing methodologies (JIT compilation, vectorisation, multiprocessing/multithreading) and high-spec Azure virtual machines.
• Pandas, NumPy, Scikit-Learn, SciPy, TensorFlow, Keras, Numba, Joblib, multiprocessing, PuLP, Azure, Databricks

Jun 2019 – Sep 2019 · 3 mos · Birmingham, United Kingdom

• 𝑨𝒓𝒕𝒊𝒇𝒊𝒄𝒊𝒂𝒍 𝑵𝒆𝒖𝒓𝒂𝒍 𝑵𝒆𝒕𝒘𝒐𝒓𝒌𝒔 𝒇𝒐𝒓 𝑩𝒍𝒂𝒄𝒌-𝑺𝒄𝒉𝒐𝒍𝒆𝒔 𝑶𝒑𝒕𝒊𝒐𝒏 𝑷𝒓𝒊𝒄𝒊𝒏𝒈 𝒂𝒏𝒅 𝑷𝒓𝒆𝒅𝒊𝒄𝒕𝒊𝒐𝒏 𝒐𝒇 𝑰𝒎𝒑𝒍𝒊𝒆𝒅 𝑽𝒐𝒍𝒂𝒕𝒊𝒍𝒊𝒕𝒚 𝒇𝒐𝒓 𝒕𝒉𝒆 𝑺𝑨𝑩𝑹 𝑺𝒕𝒐𝒄𝒉𝒂𝒔𝒕𝒊𝒄 𝑽𝒐𝒍𝒂𝒕𝒊𝒍𝒊𝒕𝒚 𝑴𝒐𝒅𝒆𝒍
• Supervised by Dr Daniel J. Duffy
• Focused on the feasibility of using neural networks for option pricing and representation of stochastic volatility models.
• Developed a neural network framework to price Call and Put options whilst preserving second order derivatives of the model outputs to ensure option Greeks can be calculated.
• Developed a neural network framework to predict the implied volatility generated by the SABR stochastic volatility model.
• Implemented an image-based implicit learning method to directly predict implied volatility surfaces.
• Experiments show that the neural network architecture is able to accurately predict the price of options, implied volatility, and implied volatility surfaces under the normal and log-normal SABR models.
• Extensive use of Python with NumPy, SciPy, Pandas, TensorFlow, Keras, Scikit-learn.
• See the links on where the thesis can be downloaded.

Apr 2019 – May 2019 · 1 mo · Birmingham, United Kingdom

• • Developed a C++ program to compute the implied volatility of options using the Newton-Raphson method and the Secant method.

Dec 2018 – Jan 2019 · 1 mo · Birmingham, United Kingdom

• Developed a C++ program to value European style options under the Heston stochastic volatility model using a Monte Carlo method.
• Valued European style Calls, Puts, and lookback options with both fixed and floating strike.

Sep 2018 – May 2019 · 8 mos · Birmingham, United Kingdom

• Used Python and the Interactive Brokers Python API to develop a portfolio optimiser with the objective to maximise net profits over its deployment period subject to a VaR constraint.
• Picked 5 assets available on IB's trading platform.
• Estimated VaR using a GARCH method.
• Identified compound returns as a market invariant for stocks.
• Projected Invariants to the investment horizon using time weighted probabilities and recovered a distribution of the projected portfolio PnL at the investment horizon.
• Evaluated portfolio performance at the investment horizon with an objective to maximise returns (objective function).
• Optimised portfolio allocations using a mean-variance method to maximise the objective function.
• Dynamically reweighted the portfolio at different time intervals.
• Backtested the strategy using historical price data.
• Deployed the method trading live on IB Trader Workstation using the python API.

Jun 2019 – Jun 2019 · 0 mo · West Midlands, England, United Kingdom

• 1 week city prep programme.
• Operated as a sales trader, market maker and execution trader using Amplify’s market simulation software.
• Managed a global multi-asset portfolio through macro driven volatility with an objective to outperform the benchmark.
• Developed macroeconomic understanding of international financial markets and how they respond to breaking news and analysis.

Jul 2014 – Dec 2018 · 4 yrs 5 mos · Coventry

• Part-time work whilst studying.
• Consistently demonstrate excellent team-work and customer service skills.