Development and testing of investment strategies using derivatives

The article presents a critical analysis of modern practices for developing and testing investment strategies based on the use of derivative financial instruments. The main objective is to demonstrate how these instruments, when integrated into a structured methodological approach, can improve risk management, optimize volatility-adjusted returns, and increase the organization's resilience to market shocks. The study is based on an applied approach illustrated by the experience of a financial sector player who developed a full cycle of creating, validating, and implementing speculative strategies in futures markets, in particular futures contracts and options. The main focus is on the integration of hybrid models combining machine learning (Random Forest, XGBoost) and classical econometric methods, as well as the development of a rigorous backtesting protocol that takes into account real transaction costs, liquidity effects, and slippage. The results show that despite the inherent complexity of derivatives, their targeted use within a controlled investment strategy can significantly improve risk-adjusted performance. In addition, the introduction of cross-cutting organizational structures (agile teams) and the development of a controlled speculation culture represent significant steps towards more flexible and responsive corporate governance. Finally, the study highlights current regulatory challenges and methodological limitations and opens up promising research directions in the areas of standardization of strategy validation processes, real-time model adaptation, and the creation of robustness indicators applicable to emerging markets.