Research of Quantative Trading Strategy Based on LSTM

Abstract

Making strategies to maximize returns has always been the biggest problem almost every investor faces in the process of investment. In this paper, we will establish a model to analyze the internal characteristics of gold and bitcoin price data for further price prediction, which is of great help in formulation of trading strategy for the future. In Section 2 we hope to analyze the price trend of gold and bitcoin. At the beginning we establish a model based on ARIMA and get a relatively good prediction result. However, considering the errors may occur when the backward prediction unit gets long in this model, we try to use LSTM algorithm to better extract the nonlinear characteristics of the two time series of price. Through LSTM algorithm we get a much better result, and thus we choose LSTM as our final prediction model after comprehensive comparison. In Section 3, we use the predicted results to make trading strategies. We first divide investors into reckless and prudent types and establish models under different assumptions respectively. Then by applying greedy algorithm and establishing risk quantification model we approach the global optimal solution respectively. In the end, after testing the model and confirming its excellent performance, we summarize the advantages and shortcomings about this model comprehensively. Moreover, much more conclusions are drawn to analyze the possible model update in future.Price Prediction