├── Forecasting the realized volatility of stock price index A hybrid model integrating CEEMDAN and LSTM.pdf
└── README.md


/Forecasting the realized volatility of stock price index A hybrid model integrating CEEMDAN and LSTM.pdf:
--------------------------------------------------------------------------------
https://raw.githubusercontent.com/ArcherCYM/CEEMDAN-LSTM/HEAD/Forecasting the realized volatility of stock price index A hybrid model integrating CEEMDAN and LSTM.pdf


--------------------------------------------------------------------------------
/README.md:
--------------------------------------------------------------------------------
 1 | # CEEMDAN-LSTM
 2 | ***Paper-Reproduce: (ESWA) Forecasting the realized volatility of stock price index: A hybrid model integrating CEEMDAN and LSTM***
 3 | 
 4 | ---
 5 | 
 6 | ### File Information
 7 | 1. **"P888.csv"** is raw data, including <datetime, trading_date, low, volume, high, close, open, total_turnover>. You can change it to any stock data.
 8 | 2. **"Forecasting the realized volatility of stock price index A hybrid model integrating CEEMDAN and LSTM.pdf"** is the paper i reproduce.
 9 | 3. **"CEEMDAN-LSTM.ipynb"** is all the code.
10 | 
11 | ### Methods Description
12 | 1. Clean data, generate **RVs** as target and make some statistic analysis (**skewness, excess kurtosis, J-B, Q(10)**)
13 | 2. **CEEMDAN** decomposition and visualization. (PyEMD)
14 | 3. Build **LSTM model** on raw-data and decomposed data. (TensorFlow)
15 | 4. Make comparison with **SVR, AR, HAR.**
16 | 
17 | ---
18 | 
19 | ### Tips
20 | *If you have any problem, you can send an email archercym@gmail.com or make an issue directly. We can discuss together.*
21 | 


--------------------------------------------------------------------------------