Exchange Rate Forecasting Based on Deep Learning and NSGA-II Models

Today, the global exchange market has been the world’s largest trading market, whose volume could reach nearly 5.345 trillion US dollars, attracting a large number of investors. Based on the perspective of investors and investment institutions, this paper combines theory with practice and creatively puts forward an innovative model of double objective optimization measurement of exchange forecast analysis portfolio. To be more specific, this paper proposes two algorithms to predict the volatility of exchange, which are deep learning and NSGA-II-based dual-objective measurement optimization algorithms for the exchange investment portfolio. Compared with typical traditional exchange rate prediction algorithms, the deep learning model has more accurate results and the NSGA-II-based model further optimizes the selection of investment portfolios and finally gives investors a more reasonable investment portfolio plan. In summary, the proposal of this article can effectively help investors make better investments and decision-making in the exchange market.

Ensemble Method for Forex Rate Prediction using OHLC Data

Forex rate is a crucial indicator of the economic health of the country. Accurate prediction of forex rates thus becomes essential to take necessary steps to ensure the sound economic health of its citizens. Due to the chaotic and nonsta-tionary nature of the data, its prediction becomes a complicated task. Through the results obtained from various researches, it becomes evident that hybrid models have outperformed individual base learners in resembling the actual data generation process and forecasting future data. In this paper,an ensemble-based approach is adopted to enhance forecasting accuracy. The model is trained on the OHLC data (high, low, open, and close) of the previous day for enhanced exchange rate prediction of USD compared to different currencies. This paper applies a hybrid model of Convolution Neural Network ,Long Short Term Network and Support Vector Regression trained on the previous peak data. Results obtained after experiments indicate that a hybrid model improved the prediction accuracy when compared to individual models.