Inflation Forecast Based on BP Neural Network Model

Abstract:

This paper analyzes inflation forecast based on BP neural network model. Firstly, it reviews some references about BP neural network and finds that it is a nonlinear adaptive data-driven model with induction ability and a wide range of function approximation ability so that BP neural network could be applied into forecast research. Secondly, it builds up the BP neural network model to predict CPI, selecting the four indicators, which are excess liquidity, exchange rates, inflation expectation and macro-economic leading index. Then it carries out empirical experiment and takes advantage of the monthly data of the above four indicators from March 2005 to December 2012 to forecast CPI. The results show that when prediction period is 3 months, the maximum absolute error between forecast value and real value is 0.0139, and the minimum absolute error is 0.0005. When prediction period is 6 months, the maximum absolute error is not more than 0.02. It proves that BP neural network model can predict coming CPI trend at least 6 months according to the existing data and it means it is suitable for the study of inflation forecast.

• Periodical: Advanced Materials Research (Volumes 989-994)
• Pages: 5536-5539
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.989-994.5536
• Online since: July 2014
• Authors: Yue Chun Wen, Li Na Tan*, Hai Long Wu
• Keywords: Bp Neural Network Model, CPI, Inflation Forecast

References

[1] Rumelhart, David E., and James L. McClelland. On learning the past tenses of English verbs. Institute for Cognitive Science, University of California, San Diego, (1985).

[2] Han, Chang-Wook. Fuzzy Neural Network-based Time Delay Prediction for Networked Control Systems. Appl. Math 8. 1 (2014): 407-413.

DOI: 10.12785/amis/080151

[3] Kuo, Sheng-Feng, et al. A comparative study on the estimation of evapotranspiration using back propagation neural network: Penman–Monteith method versus pan evaporation method. Paddy and Water Environment 9. 4 (2011): 413-424.

DOI: 10.1007/s10333-011-0289-8

[4] Hong, Ying-Yi, Huei-Lin Chang, and Ching-Sheng Chiu. Hour-ahead wind power and speed forecasting using simultaneous perturbation stochastic approximation (SPSA) algorithm and neural network with fuzzy inputs. Energy 35. 9 (2010): 3870-3876.

DOI: 10.1016/j.energy.2010.05.041

[5] Huang, Sunan, and Kok Kiong Tan. Intelligent friction modeling and compensation using neural network approximations. Industrial Electronics, IEEE Transactions on 59. 8 (2012): 3342-3349.

DOI: 10.1109/tie.2011.2160509

[6] Barra, Adriano, Giuseppe Genovese, and Francesco Guerra. The replica symmetric approximation of the analogical neural network. Journal of Statistical Physics 140. 4 (2010): 784-796.

DOI: 10.1007/s10955-010-0020-y

[7] Wang, Jianjun, and Zongben Xu. New study on neural networks: the essential order of approximation. Neural Networks 23. 5 (2010): 618-624.

DOI: 10.1016/j.neunet.2010.01.004