A Trend Tracking Strategy for Gold Future: An Artificial Neutral Network Analysis

In this paper, we construct a simple data-driven trend tracking strategy for gold future in a view of contrarians. The artificial neutral network (ANN) is adopted to determine the price trend signal, by which the degree of tightness could be adjusted based on observed data. We attempt to capture the small profits when the price is deviated from the Bollinger band in the gold future market by intraday trading. High frequency data of gold future is used to train and test the strategy. Despite of the trading cost, the back-tests show that our strategy has delivered positive returns and is adaptive to different price trends. Finally, we evaluate the profitability with the consideration of trading cost, revealing that the strategy is applicable in practice.