George Nigmatulin

George Nigmatulin

PhD Researcher in Machine Learning and Quantitative Finance

Curriculum Vitae

EDUCATION

University of Oxford (Oxford, United Kingdom). Oct 2024 – Dec 2027 (exp.)
Department of Engineering Science / Machine Learning Research Group
  • Doctor of Philosophy in Engineering / Quantitative Finance and Machine Learning, Supervisor: Professor Stefan Zohren
  • Scholarship: ESRC Grand Union Doctoral Training Partnership (DTP) Data Skills Studentship
  • Research project: "Causal Survival Analysis in Limit Order Books: Estimation Fill Probabilities"
Moscow Institute of Physics and Technology (Moscow, Russia) The Phystech School of Applied Mathematics and Computer Science.
Sep 2020 – Jun 2022
  • Master's degree in applied mathematics and physics / GPA 4.8 out of 5.0 for 2 years, top 5% of the class
  • Scholarship: Government academic scholarship for only A-mark students
  • Graduation project: "Anomaly Detection-Aided Active Learning on smartwatches data"
Orenburg State University (Orenburg, Russia)
Sep 2016 – Jun 2020
  • Bachelor's degree in applied mathematics and computer science / GPA 5.0 out of 5.0 for 4 years, top 1% of the class
  • Scholarships: Government academic scholarship for only A-mark students, Increased Scholarship for Research Activities
  • Graduation project: "Research of machine learning models for predicting and optimizing ATM service"

WORK EXPERIENCE

Machine Learning Research Group (Oxford, United Kingdom)
Sep 2024 – Present
  • Research Engineer / Quantitative Finance Stream
  • Developing Machine Learning framework to analyze the Price Impact of Market Orders, Limit Orders and Cancellations. Utilizing autoregressive modeling to account for history-dependent effects, improving forecast accuracy and trade execution efficiency for small tick stocks by capturing internal order book fluctuations
  • Creating a Generative AI model for sequence prediction in NASDAQ limit order books, leveraging a deep state space model and custom tokenizer to simulate realistic order flows. Increasing mid-price return forecast accuracy and a correlation with realized returns, enhancing potential for reinforcement learning in high-frequency trading applications
Samsung R&D Institute (Remote, South Korea)
Jul 2021 – Jun 2024
  • Machine Learning Engineer / Sensor Solution Team
  • Developed Sweat loss estimation algorithm. Accelerometer-based Neural Network estimates running distance (MAPE =7.7%, R2=0.95) and Polynomial Kernel Ridge Regression estimates the loss in ml (RMSEBWP=0.3%, R2=0.79)
  • Developed regression models for estimation of BFM (Body fat mass), SMM (Skeletal muscle mass), ICW & ECW (Intracellular / Extracellular water) by a multi-frequency signal (released in Samsung's Galaxy Watch 4)
  • Developed Body Temperature algorithm for a smartwatch. SVM on perfusion signals detect the presence of heat (Accuracy=0.91, F1=0.87) and Ridge Regression estimates the core temperature in ℃ (MSE=0.19, R2= 0.77) based on dynamical, thermal, environmental and anthropometric data. Best performance among competitors
Bank Orenburg (Orenburg, Russia)
Jun 2019 – Jul 2020
  • Analyst, Data Scientist / Information technology Department
  • Forecasted the ATM daily cash demands based on Triple Exponential Smoothing, ARIMA, Neural Networks, SSA
  • Developed a discrete model of optimal cash management in ATM branches using dynamic programming, which increased profitability compared to the classical model by 30%

Professional skills

Languages: English - Advanced C1, Russian – Native
Programming: Languages: C++ / C#, Python, R, Matlab, Matcad, Octave, SQL
DevOps: Linux, Bash, SSH, Git, DVC, Hadoop, Docker, AWS, Cookiecutter-data-science, WandB, MLFlow

Quantitative Research toolkit

ML packages: Scikit-learn, SciPy, LightGBM, Catboost, SHAP, Prophet, Numpy, Pandas, Matplotlib, Seaborn
Deep Learning: TensorFlow, PyTorch
Finance: Yfinance, Statsmodels, Tsfresh, FinancePy, Quantpy, Pyfolio, Backtrader, Quantstats, Interactive Brocker
Area of specialization: Machine learning, Deep Learning, Causal and Bayesian methods, Uncertainty quantification, Optimal control, System analysis, Quantitative Finance, Strategies, Predictive Modelling, Portfolio optimization.

Pdf version of Curriculum Vitae

https://drive.google.com/file/d/16Fcq8b-fn2SDC3vSC8bn-utplYZdkIih/view?usp=share_link