Количественный аналитик

Описание

Bogdan Alexandrov
Moscow, Russia |Bogdan.Alexandrov@skoltech.ru |8 977 168 55 41 |tg: b0gcham5
https://www.linkedin.com/in/bogdan-alexandrov |https://github.com/BogChamp
Education Skoltech
, MS in Data Science Sept 2022 – June 2024
• GPA: 3.9/4.0
• Coursework: Limit order book queue modelling: a Reinforcement learning approach. Repository:
github.com/BogChamp/lob-backtest.
Moscow State University , BS in Computer Science Sept 2018 – June 2022
• GPA: 4.7/5.0
• Coursework: The study of methods of automatic generation of input data for testing modules for processing
web page templates. Repository: github.com/BogChamp/fuzzing.
Additional Courses AIMasters
, Moscow
Sept 2023 – nowadays
• Courses: Machine Learning/Deep Learning ,Algorithms and Data structures ,Optimization Methods ,Game Theory ,
Mathematical Statistics and Applications .
Center of Mathematical Finance , Moscow Oct 2023 – Dec 2023
Experience Internship
, Piklema-Moscow May 2023 – July 2023
• Formulated the problem of optimal distribution of trucks in a quarry using an integer programming problem
• Simulated the operation of dump trucks at the quarry and conducted experiments to solve the problem of
optimal distribution
• Tools: Python, CasADi.
Projects Backtest
github/lob_backtest
• As part of the thesis, a simulator of the exchange for backtesting was developed. It takes into account network
latency, and also sorts out collected order book updates and trades in correct order.
Feature extraction from exchange data github/features_acceleration
• Implemented fast feature engineering from exchange data using Polars and Numba.
RL methods for cart pole swing up and stabilization github/rl_project
• Pipelines have been developed for training the agents of REINFORCE and A2C.
Option pricing github/task_options
• Implemented code for pricing European and American options, and for evaluating their greeks.
Detection of critical points of a time series github/MSD
• A pipeline for training the Barrow twins model was implemented to obtain time series embeddings for finding
critical points.
Expertise Languages:
C++, C, Python.
Frameworks: PyTorch, Numpy, Pandas, Polars, XGBoost, CatBoost, scikit-learn, HuggingFace(basic).
Theory: ML, DL, RL, NLP, CV, Stochastic Modeling, Statistics.