Asset Forecasting Analysis Based on ARIMA Model and BP Neural Network

This paper forecasts the trend of asset based on historical prices. First, through establishment exponential smoothing method, ????????????????????, BP neural network and other models, trader invest in three assets: gold, bitcoin cash USB. The thesis is price to predict assets, determine whether traders should purchase, hold or sell what percentage asset, evaluate its future value. first predicts returns volatility two assets. In initial forecast, method ???????????????????? model are used premiums returns. earnings middle late forecast. for 60 days, we sit tight wait data accumulate. After by looking back at setting appropriate technical indicators, secondary curve risk exposure gold Bitcoin can be obtained respectively. Once have curves, commission, expected rate return, markets combined, will set up a scoring system score daily trading feasibility. Finally, simulate transaction, allocate investment share, get accumulation curve, complete decision.