Hi Rich,
Thank you for your insightful observation. The -79% maximum drawdown in 2019 indeed flags a significant risk that would generally be unacceptable in a live trading environment. The intention behind showcasing these results, particularly for an asset as volatile as Tesla, was to illustrate the performance of a basic Kalman Filter strategy across varying market conditions. It's crucial to highlight that while valuable backtesting doesn't account for all real-world trading scenarios, this strategy was not meant to be applied as-is without further optimisation.
The improved results in 2020 could be attributed to several factors, including changes in market dynamics and Tesla's unique price behaviours during that period or even when the Kalman filter's estimates aligned more closely with market movements. However, these results should be interpreted with caution.
Moving forward, it is essential to optimise the strategy further. This includes fine-tuning parameters, incorporating risk management practices like setting take profit and stop loss thresholds, and conducting extensive out-of-sample testing to validate the strategy's robustness over a more extended period and across different market conditions.
The aim here is to provide a foundation upon which traders can build and refine a strategy utilising the Kalman Filter that aligns with their risk tolerance and investment goals :).