Our proprietary boosting-based optimization framework for multi-expert discovery is capable to find very stable regime-independent portfolios of complementary trading strategies for different trading vehicles, profit/risk objectives, and trading frequencies. One of such fully automated multi-expert system successfully tested with real capital is for intraday medium-frequency systematic trading. While direct usage of this multi-strategy system can be attractive by itself, we find that it could be also used in the much wider application scope.
Our generic ensembles of complementary trading strategies implicitly encode a wide range of tradable market regimes, exploitable novel and rare events, and a very large number of precursor patterns that could be hard or impossible to quantify by other means. Alternatively, our regime-independent strategy ensemble can be interpreted as a large pool of experts with complementary knowledge and behavioral signatures. However, unlike real experts, it offers full detailed information of expert behavior (their micro-timing, positions, etc) in different market regimes.
Thus, one has an opportunity to observe and take into account changes in such rich multi-expert behavioral indicator for early prediction and quantification of otherwise very hard-to-model rare and/or emerging market patterns that potentially lead to profitable trading and optimal hedging. Practical applications of our strategy-based indicators include but not limited to the following:
- Prediction of Rare Events and Market Regime Changes
- Discovery and Tracking of Thousands of Evolving Predictive Patterns
- Early Detection of Emerging Tradable Patterns
- Early Detection of Changes in Correlation Patterns
- Optimal Capital Allocation, Rebalancing and Hedging
Many elements of our non-standard multi-expert framework are also successfully applied in biomedical and other fields as outlined at www.medpobs.com, www.deepmantic.com and www.aqscs.com