Optimizing the moving average

This paper proposes a new and optimal moving average model that reduces the problems of alternative models. The random (noisy) nature of financial time series creates difficulties when modelling with any method. The most common linear model to deal with this issue of noise is the moving average. These filters come with the drawback of lag, a delay between the model output and the financial data. As more noise reduction is demanded from the models the lag increases. This lag is a hindrance in a market place where individuals are competing for timely and quality information. This paper derives an optimal moving average model which reduces the lag and increases the level of noise reduction. The proposed model was compared against four of the common moving averages and shown to be superior in both lag reduction and noise reduction.