DMITRY KLIMENKO

Quantitative Researcher

klimenko.dnk@gmail.com

Summary
For over a decade, one person held the belief that the Ultimate Automated Quant Machine could be built to trade financial instruments in a way that's impossible for Humans.

Combining sophisticated data with powerful in-house methods and AI technology, Dmitry creates autonomous solutions for generating consistent, significant returns. Experienced in all aspects of MFT/LFT Quant-aspects. From building infrastructure to developing models, managing risks, and controlling systematic trading portfolios.

Master of Computer Science
Ph.D. in Mathematical and Quantitative Methods in Economics

Greencard holder (by EB-1A/E11, Extraordinary ability in Quantitative Research) [Read More]
SKILLS
  • Programming:
    • Python (Numpy, Pandas, Numba, scikit-learn, PyTorch, matplotlib)
    • C#
    • C / C++
    • Design of Architecture for complex solutions.
    • Distributed multiserver calculation.
    • Live-trading systems.
  • Analytical:
    • Mathematical and Statistical methods.
    • Deep Learning (CNN, Transformers, GAN, VAE, RNN, LSTM, GRU)
    • Reinforcement Learning
    • Neuroscience-inspired DNN technologies (AI Memory units, dynamic RL-based attention, self-prediction training, and advanced neural net architecture.)
    • Machine Learning
    • Genetic / Evolution Algorithms.
    • Nonconvex, multi-constraints, numeric optimization.
  • Financial:
    • Systematic trading MFT/LFT (1 min. - month)
    • Equity, FX, CFD, Indices, Commodities, Futures, ETF, Crypto
    • Stat-arb, market-neutral trading based on predictions made by statistical models fed by Alphas, market, and alternative data (+NLP).
    • Technical Analyse
    • Portfolio Constructions
    • Financial Time Series Forecasting
    • Risk analysis (VAR, Robustness test, Overoptimization checks, Trading strategies validation)
WORK EXPERIENCE
Mar 2023 - Present
Mar 2023 - Present
QUANTITATIVE RESEARCHER / DEVELOPER
Quant Trading Startup, Florida, USA
        • Developed an automated medium frequency (Hours - Days) trading system for Equity, Futures, ETF, CFD, FX. Stat-arb, market neutral.

        • Based on the idea of market decomposition to virtual basic elements (which are not observed directly). These market components are significantly more stable over time, with much lower noise. The in-house mathematical models highlighted how to solve the tasks of mining strong Alpha signals, modeling robust forecasts, task-specific portfolio constructions, advanced risk management, and methods to evaluate and validate results.

        • The core system aims to generate multiple synthetic financial instruments with tangible trading potential at every moment. Instead of gathering suitable trade conditions by monitoring tradable assets, the solution is to craft the synthetic instrument as a portfolio of assets with a ready-to-trade possibility. The idea is to create opportunities by amplifying expected price move prediction while, at the same time, dimming the unknown parts.
        June 2021 - Jan 2023
        June 2021 - Jan 2023
        QUANTITATIVE / AI RESEARCHER INSPIRED BY COMPUTATIONAL NEUROSCIENTIST
        Non-Compete period up to the end of 2022, Florida, USA - mimic Brain components and apply scientific / engineering methods to solve challenging AI/ML/Quant tasks.
          • Aiming to solve diverse Quantitative trading questions. Inspired and reverse engineer the insights I get from computational Neuroscience.

            Moreover, there have been no big breakthroughs in AI since Transformers.
            The Brain-Like DNN has undergone no intensive unmercenary compute units.
            And could be run entirely on my PC, which made my home far too warm, for Florida summer.
            Apr 2018 - May 2021
            Apr 2018 - May 2021
            SENIOR QUANTITATIVE RESEARCHER
            SHUAA Capital, Abu Dhabi, United Arab Emirates - [AUM ~ $14B+] - Leading and Oldest (founded 1979) Asset Management and Investment Banking Company. Initially, I joined ADFG, which acquired SHUAA in 2019.
            • Presented a vision of a Quantitative Machine with an extendable suite of modules for researching, developing, and implementing diverse trading strategies semi-automatically. Powered by novel AI/ML/Quant technologies.
            • Built a comprehensive quant-infrastructure, including data module, custom fast and accurate backtesting engine, multiserver computation grid, in-house multi-constrained stochastic numeric optimization module, time-series forecasting solution.
            • Stat-arb, portfolio Equity strategy, Intraday Equity CFD strategy, med-frequency ETF, futures, CFD, FX trading with 30%-70% annual profit and allowed max. risk levels at 10%. Calmar ratios: 3.0 – 5.0.
            • Generated market-neutral Long/Short, always fully invested US equity conservative portfolio strategy bypassing COVID market shock with an all-time max drawdown of 0.9%, generating 31% annual profit. (Feb 2019 - May 2021)
            • Established a new legal entity in 2019 with Dmitry as the head of Quants dedicated to developing "The Quant Machine" project.
            • In 2021, a notable UAE financial institution acquired the company for its technologies.
            Jan 2017 - Oct_2017
            Jan 2017 - Oct_2017
            SENIOR QUANTITATIVE TRADING ANALYST
            Collective2.com, Remote - Leading US P2P trading platform, that connects investors with traders.
            • Developed semi-automated tools for trading system research leveraging the latest advances in Artificial Intelligence and Machine Learning technologies.
            • Proposed solutions to identify changes in market conditions when trading strategies underperform and utilized AI/ML algorithms to facilitate improved performance.
            Aug 2013 – Nov 2016
            Aug 2013 – Nov 2016
            CHIEF QUANTITATIVE ANALYST
            FxPro.com, Limassol, Cyprus – World Leading Retail CFD/FX Broker
            • Pioneered an analytical environment, which became a new standard in FxPro. 70+ in-house analytical modules, API, and easy visual editing for customizing report templates. Advanced analyses of clients' training and systematic strategies revealed valuable business insights.
            • Deployed solution for massive analysis of client trading activity to identify market shift signals and abnormalities in advance. Risk and Dealing departments could be prepared days ahead.
              The system alerts substantial anomalies on EURCHF weeks before the SNB 2015 crush event. FxPro remained operational that day, while many major and oldest retail brokers worldwide didn't surpass the shock. ( How Forex Brokers Went Bankrupt Overnight amid EURCHF Flash Crash - Infographic )
            • MFT trading on FX, Futures, Equity CFD, and Commodities. Trading based on ML/TA signals and In-House Forecasting Engine.
            • Examined 7.3 million clients' trading reports. Uncovered precious business insights led to delivering dealing system modifications. Consequently, the Dealing department revenue increased 36% from $88 RPM to $120 RPM (Revenue Per Million volume)
            • Engineered software for in-depth analyses of trading strategy reports. Determine trading style, and generate trading forecasts to identify Risk probabilities, hidden risk scenarios, and appropriate enhancement ideas to provide the final report.
              Became the core part of award-winning products. (Awards: "Best Automated Trading Platform 2013" from International Finance Magazine Award; and "Best Forex Product of the Year 2014" from UK Forex Awards)
            Oct 2012 – Aug 2013
            Oct 2012 – Aug 2013
            SENIOR QUANTITATIVE RESEARCHER
            Life Financial Group, Moscow, Russia - AUM ~$600M USD

            • Designed and developed 20+ different Med-frequency FX/CFD/Futures strategies. 37% PnL with max risk at 5% achieved.
            Jan 2011 – Jul 2012
            Jan 2011 – Jul 2012
            QUANTITATIVE PORTFOLIO MANAGER
            FEx-Cor, Moscow, Russia - Private Asset Management Company. AUM ~$25M USD. Acquired by Investment Company in July 2012.
            • Developed systematic-trading strategies portfolio. Become TOP out of 1000+ trading strategies worldwide at the "Currensee" FX/CFD P2P trading platform. Generated profit of portfolio (JUL2011 – JUL2012) 63% with max risk-level at 10%, managed $25M+.
              EDUCATION
              Oct 2010 - Sep 2013
              Oct 2010 - Sep 2013
              PhD, MATHEMATICAL AND QUANTITATIVE METHODS IN ECONOMIC SCIENCES - ABD
              Tomsk State University of Control Systems and Radioelectronics, Tomsk, Russia - www.tusur.ru/en
              Sep 2004 - Aug 2010
              Sep 2004 - Aug 2010
              MASTER OF COMPUTER SCIENCE - GPA: 4.6 / 5.0
              Tomsk State University of Control Systems and Radioelectronics, Tomsk, Russia - www.tusur.ru/en
              • Winner of Russian Business analyses competition BIT from 700 companies in a country and one of two selected by Microsoft and Intel to represent Russia worldwide in California, USA. (Became the top 20 projects worldwide)
              • Awarded by the US Civilian Research & Development Foundation as a "Best Business Model." (Project: Simple Trade Solutions (sTs), tools for trading)