Abstract

We built a price prediction model for gold and Bitcoin based on LSTM. For the first 30 days, we adopted a wait-and-see strategy without any transactions. Starting from the 31st day, we first trained the model with the data of all past trading days. Then use the trading data of the past 30 days to forecast the market price for the next 6 days. Then, we established a trading strategy model based on linear programming and made this week's trading decisions based on the predicted value of the market price in the next 6 days. Finally, we plotted the yield curve based on asset value.

Full Text
Paper version not known

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call