From traditional investing to advanced algorithmic trading with machine learning
Our story begins with traditional investment approaches—managing 401(k)s, IRAs, and standard brokerage accounts. While these conventional methods served us well for years, including notable gains during the COVID market volatility, we experienced the classic retail investor challenge of failing to capture profits at optimal moments. This experience sparked our interest in developing more systematic approaches to the markets.
In January 2022, we expanded our focus to day trading, eager to apply more active management principles to our investment approach. Like many traders entering this space, we initially explored the crowded ecosystem of trading "gurus" and subscription services promising unrealistic returns. These expensive lessons coincided with a challenging market environment, leading to disappointing results that tested our resolve.
The turning point in our journey came when we discovered the unique advantages of futures markets. The combination of capital efficiency through leverage, absence of time decay, and extended trading hours presented compelling opportunities—provided risk could be properly managed. Rather than approaching these markets with discretionary trading, we recognized the potential for systematic, rules-based strategies.
Our background in technical analysis provided the foundation, but we needed to translate this knowledge into automated systems that could execute without emotional interference. This marked our transition from chasing trading signals to developing quantitative trading algorithms.
We devoted ourselves to algorithm development, testing basic technical analysis concepts within automated frameworks. The initial results were promising enough to encourage further research and system development. Eventually, we constructed several viable strategies and began live trading with modest capital.
As many algorithmic traders discover, the transition from backtest to live trading revealed challenges that required addressing. Strategy decay—the phenomenon where live performance fails to match backtested results—forced us to reconsider our development approach. This led to intensive research into robust algorithm design, focusing on parameters like walk-forward optimization, out-of-sample testing, and Monte Carlo simulations to build more resilient systems.
Our most significant breakthrough came with the integration of machine learning techniques. This advancement took our strategy performance to unprecedented levels, enabling our systems to identify subtle patterns and relationships that traditional technical indicators could not capture. The ML enhancement serves as a sophisticated filter for our trading signals, dramatically improving execution quality.
While our backtests show impressive results, it's important to emphasize that we're still in the early stages of consistently trading these algorithms with real capital. As any experienced algorithmic trader knows, the transition from backtest to live trading involves numerous challenges and adjustments. We're currently in this implementation phase, working to realize a portion of the performance shown in our backtests.
We've chosen to share our journey from traditional investor to algorithmic trading firm because we understand the challenges that individual traders face. The path is filled with obstacles—expensive subscriptions that don't deliver, misleading "guru" advice, emotional trading decisions, and the difficulty of developing truly robust strategies that perform in real market conditions.