Prediction of Gold Prices Using LSTM-Based Recurrent Neural Networks

Abstract

In recent years, international gold prices have been constantlyrising; gold investment and preserve (or even appreciation) effects have been widely concerned by the market. Whether it is based onspeculation, investment or hedging purposes, the gold has been inorporated into the asset allocation by many investors, which hasbecome another important investment in addition to foreign currency, funds, stocks and securities. This paper discusses how to construct a prediction model using recurrent neural networks, long short-term memory, for gold prices to understand the future gold pricetrend, and to provide a reference for experts and investors.