Layered Exchange Rate Prediction Model Based on LSTM

Abstract

The prediction of exchange rate is very important for both countries and enterprises. At present, the latest prediction technology is training BP neural network through the recent exchange rate data, and it takes effect in some degree. In view of the limitations of the existing BP neural network, an improved hierarchical network model based on Long Short-Term Memory (LSTM) is proposed. The model increases the time depth of the data, and uses attention mechanism to process the historical data of different time levels, which makes the prediction ability of the model stronger. Taking the exchange rate of US dollar / rupee as an example, by comparing with the basic LSTM model and BP neural network, it is proved that the proposed model has a better effect.