Welcome to Francis Academic Press

Academic Journal of Business & Management, 2022, 4(11); doi: 10.25236/AJBM.2022.041106.

Carbon Trading Price Forecast Based on LSTM and ARIMA—Take the Shanghai Area for Example


Shurong Dong1, Xinyue Zhang2

Corresponding Author:
Shurong Dong

1College of Textile and Clothing Engineering, Soochow Univeisity, Suzhou, Jiangsu, 215325, China

2College of Information Science and Technology, Bohai University, Jinzhou, Liaoning, 121010, China


In order to solve environmental problems such as air pollution, China has tried to carry out carbon emission trading market. For the sake of improving the risk management ability of the carbon emission trading market and make reasonable policies, it is very important to analyze and forecast the price of the carbon emission trading market. Considering that a single model has many self-limitations, in order to ensure that the predicted results can better match the actual situation, this paper adopts the combination model of ARIMA and LSTM to study the carbon emission trading price. Based on the reasonable prediction of carbon emission trading price of Shanghai Stock Exchange in recent years, the results show that ARIMA and LSTM can well combine their mutual advantages, effectively improve the accuracy of prediction, and provide certain guarantee for the sound development of carbon emission trading market.


Carbon emissions trading, ARIMA, LSTM, CRITIC

Cite This Paper

Shurong Dong, Xinyue Zhang. Carbon Trading Price Forecast Based on LSTM and ARIMA—Take the Shanghai Area for Example. Academic Journal of Business & Management (2022) Vol. 4, Issue 11: 33-38. https://doi.org/10.25236/AJBM.2022.041106.


[1] Rahimi Z H, Khashei M. A Least Squares-based Parallel Hybridization of Statistical and Intelligent Models for Time Series Forecasting [J]. Computers & Industrial Engineering, 2018, (11).

[2] Kim H Y, Won C H. Forecasting the Volatility of Stock Price Index: A Hybrid Model Integrating LSTM With Multiple GARCH-type Models [J]. Expert Systems With Applications, 2018, (103).

[3] Khashei M, Bijari M. Fuzzy Artificial Neural Network (p, d, q) Model for Incomplete Financial Time Series Forecasting [J]. Journal of Intelligent and Fuzzy Systems, 2014, 26(2).

[4] Zhang G P. Time Series Forecasting Using a Hybrid ARIMA and Neu⁃ral Network Model [J]. Neurocomputing, 2003, (50).

[5] Sun Y, Zhao Z, Ma X, et al. Short-time Scale Gravitational Microlens⁃ing Events Prediction With ARIMA- LSTM and ARIMA- GRU Hy⁃brid Model [J]. Lecture Notes in Computer Science, 2019, (11473).