—- Pioneered application of advanced machine learning techniques for detection of complex and rare patterns in space weather forecasting and financial markets [1999–2006]

—- Pioneered application of boosting-based combination of analytical and domain-expert models and indicators in finance and econometrics [2005-2006].

—- Proposed generic boosting-based optimization framework for the discovery of regime-independent portfolios of trading / investment strategies [2006].

—- Proposed usage of boosting-based ensembles for generic representation of complex and rare states in financial markets, biomedicine and other fields [2007-2011].

—- Proposed further enhancements for representation of complex and rare states via combination of boosting-based ensembles, topological measures and deep learning [2011-2021].

• Leveraging Neural-Networks, Boosting and Domain-Knowledge to Discover Physiological Indicators with Minimal Sensitivity to Data Resolution (2022)
• Discovery of early-alert indicators using hybrid ensemble learning and generative physics-based models (2022)
• Discovery of Hybrid Ensemble Models Resilient to Input Resolution Deterioration (2021)
• Topological Representation of Rare States Using Combination of Persistent Homology and Complexity Measures (2020)
• Boosting-based frameworks in financial modeling: Application to symbolic volatility forecasting, Advances in Econometrics, Volume 20B, 123 (2006)
• Boosting-based framework for portfolio strategy discovery and optimization, New Mathematics and Natural Computation, vol. 2, No. 3 (2006)
• Market-neutral portfolio of trading strategies as universal indicator of market micro-regimes: From rare event forecasting to single-example learning of emerging patterns, in IEEE Proceedings of ICICIC, Kumamoto, Japan (2007)
• Discovery of multi-spread portfolio strategy for weakly-cointegrated instruments using boosting-based optimization, In Proceedings of the 5-th International Conference on Computational Intelligence in Economics and Finance (2006)
• Ensemble Decomposition Learning for Optimal Utilization of Implicitly Encoded Knowledge in Biomedical Applications (2011)
• Synergy of physics-based reasoning and machine learning in biomedical applications: towards unlimited deep learning with limited data (2019)
• Leveraging domain-expert knowledge, boosting and deep learning for identification of rare and complex states (2019)
• Advantages of Hybrid Deep Learning Frameworks in Applications with Limited Data (2018)
• Multi-expert evolving system for objective psychophysiological monitoring and fast discovery of effective personalized therapies (2017)
• Generic Ensemble-Based Representation of Global Cardiovascular Dynamics for Personalized Treatment Discovery and Optimization (2016)
• Multi-Complexity Ensemble Measures for Gait Time Series Analysis: Application to Diagnostics, Monitoring and Biometrics (2015)
• Universal multi-complexity measures for physiological state quantification in intelligent diagnostics and monitoring systems (2013)
• Robust algorithmic detection of cardiac pathologies from short periods of RR data (2013)
• Diagnostics of complex and rare abnormalities using ensemble decomposition learning (2011)
• Generic regularization of boosting-based algorithms for the discovery of regime-independent portfolio strategies from high-noise time series, in IEEE Proceedings of the 4-th International Conference on Innovative Computing, Information and Control (2009)
• Support vector machine as an efficient framework for stock marketvolatility forecasting, Computational Management Science, 3, 147 (2006)
• Volatility forecasting from multiscale and high-dimensional marketdata, Neurocomputing, 55, 285 (2003)
• Discovery of multi-component portfolio strategies with continuoustuning to the changing market micro-regimes using input-dependentboosting, In Proceedings of the Third International Conference onComputational Finance and its Applications (2008)
• Support vector machine as an efficient tool for high-dimensional dataprocessing: Application to substorm forecasting, J. Geophys. Res.,106, 29911 (2001)
• Optimization of the neural-network geomagnetic model for forecastinglarge-amplitude substorm events, J. Geophys. Res., 106, 6247 (2001)