Skills
Automated trading systems
High-frequency trading
Medium-frequency trading
Portfolio optimization
Risk analysis and minimization
Data mining
Stock profitability analysis
Prediction, indicators of predictability
Complex regression
Classification and clustering
Machine learning
Deep learning
Reinforcement learning
Adaptive dynamic programming
Adaptive optimal control
Genetic optimization
Unsupervised learning
Programming
C, C++, Python, MatLab, HTML/CSS
Linux, Windows
Real-time, multithreading
Languages
Creative quantitative data analyst with 10+ years of experience. Successfully combined knowledge of artificial intelligence technology and neuroscience to develop profitable high- and medium-frequency stock trading strategies. Designed methods and developed software for efficient optimization of trading model parameters and stock portfolio.
(Full resume is available upon request)
Experience
Senior Quantitative Analyst
Fresnel Research
2018-01 – 2019-06
- Developed and optimized algorithmic intraday trading models with respect to risk minimization and profitability increase.
Quantitative Analyst
Migdal Research
2017-05 – 2017-12
- Developed and optimized profitable medium-frequency intraday trading models.
Vice President
Jefferies
2012-04 – 2016-10
- Developed profitable high-frequency trading models.
- Developed profitable medium-frequency intraday trading models.
Principal Mathematician, Head of R&D Department
SXP Analytics
2008-09 – 2012-04
- Developed methods for training robust price return predictors.
- Developed methods for portfolio optimization.
- Developed methods for algorithmic categorization of stocks and created special indicators based on multiple stocks within a specific category.
- Designed special methods for filtering noise and focusing on information relevant for price return prediction.
- Developed software (C++, Linux), for implementing the above methods and solutions, including algorithm design, efficient implementation, and testing in real trading environment.
Quantitative Analyst/Software Developer
AlgoBrain
1999-09 – 2007-05
- Designed and implemented a fully automated medium-frequency algorithmic trading system.
- Used artificial neural network methodology for generation of price move predictions and trade decision making.
- Designed and implemented special algorithms for optimizing the trading system’s parameters on historical stock data.
- Performed historical stock data analysis tailored for mid-frequency trading.
Education
Ph.D. in Systems Neuroscience
Bogomoletz Institute of Physiology
1987
M.S. in Cybernetics, Computer Science
Kiev Polytechnic Institute
1980
- Graduated Magna Cum Laude.
- 1st place in student competition on automatic pattern recognition systems.
Related Scientific Publications
- Shimansky Y.P. (2011) State estimation bias induced by optimization under uncertainty and error cost asymmetry is likely reflected in perception. Biological Cybernetics. 104: 225-233.
- Shimansky Y.P. (2009) Biologically plausible learning in neural networks: a lesson from bacterial chemotaxis. Biological Cybernetics. 101: 379-385.
- Shimansky Y.P. (2004) The concept of a Universal Learning System as a basis for creating a general mathematical theory of learning. Minds and Machines. 14: 453-484.
- Shimansky Y.P., Kang, T., and He, J. (2004) A novel model of motor learning capable of developing an optimal movement trajectory on-line from scratch. Biological Cybernetics. 90: 133-45.
