Abstract
The paper aims to predict the service channel payment Volume from electricity customer, so as to support the managers of companies in each province to allocate the channel resources scientifically. In terms of methods, by exploring the relevant data of the big data platform, it is found that there were few factors influencing the payment Volume. Therefore, the time series algorithm was adopted to establish the prediction model, and then established the ARIMA model to predict the payment Volume by only taking the impact of time on the business volume of payment from various channels into consideration. Firstly, smooth data processing was carried out. Then, parameters of the model were confirmed through ACF and PACF, fitting model, and the model was evaluated from the perspective of statistical hypothesis. Finally, the prediction was performed, the final mean absolute error of the model (MAE) is 14.81%, and the root mean square error (RMSE) is 14920. The model satisfied the normal hypothesis test, and the predicted results were within the confidence interval between 80% and 95%, so the model had good effect and reached the application level.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Change history
10 July 2020
In the originally published version of chapter 28, the first affiliation included an error. The first affiliation has been corrected from “USA State Grid Corporation Customer Service Center, Tianjin 300000, China” to “State Grid Corporation Customer Service Center, Tianjin 300000, China”.
References
Geng, R.: Research on nonlinear correction of electrochemical sensors based on PSO-SVM. Xi?an University of Science and Technology (2016)
Cheng, W., Yang, J.: ?Handheld Power? blooms in Beijing. State Grid 9, 1673?4726 (2015)
Zhai, W., Guo, H., Fan, M., et al.: Discussion on classification methods of unbalanced data sets. Comput. Sci. 39(b06), 304?308 (2012)
Pan, Y.: Application of time series analysis in finance. Econ. Trade Pract. 18, 1671?3494 (2017)
He, H.: Research on passing weight discrimination of bridge overloaded vehicles based on time-varying reliability. Hunan University (2016)
Chen, X., Xu, L., Hao, Y., Zhang, J., Jiang, C., Pan, T.: Model fitting of photosynthesis light response curve of Pinus massoniana. J. Jiangxi Agric. Univ. 10, 1001?8581 (2017)
Qin, X.: Combined forecast analysis of China?s GDP. Mod. Bus. Ind. 7 (2016)
Ma, S.: Prediction of total retail sales of consumer goods in China based on ARIMA model. Mod. Bus. 1, 1673?5889 (2015)
Li, Y.: Fault diagnosis and GUI design of internal combustion engine based on time series analysis. Xidian University (2014)
Zhang, W.: Research on time series prediction of foreign exchange rate based on ARIMA model. J. East China Jiaotong Univ. 5, 1005-0523 (2009)
Li, X.: Simple season model and product season model of ARIMA recognition using SAS. Comput. Knowl. Technol. (Acad. Exch.) 2, 1009?3044 (2007)
Song, J.: Mathematical statistical analysis of actual operational data of interconnected power grids. Dalian University of Technology (2006)
Zhang, Z.: Research on Key technology of statistical tolerance design and inspection. Zhengzhou University (2014)
Xie, C.: Analysis of the total retail sales of social consumer goods in Suzhou. Master. Suzhou University (2015)
Li, R.: Research on the Relationship between Retail Business and Population Development in Beijing. Master. Capital University of Economics and Business (2007)
Tang, G.: Application of time series analysis in economic forecasting. Stat. Inf. Forum P90?P94 (2005)
Chen, Y.: Empirical analysis of factors affecting the total retail sales of social consumer goods in China. New Fin. P29?P29 (2011)
Pang, H., et al.: Pathway analysis using random forests classification and regression. Bioinformatics 22(16), 2028?2036 (2006)
Fang, W., Wu, J., Zhu, J., et al.: Review of random forest methods research. J. Stat. Inf. 26(3), 32?38 (2011)
Yao, X., Wang, X., Zhang, Y., et al.: Overview of feature selection methods. Control Decis. 27(2), 161?166 (2012)
Ma, J., Xie, B.: Comparison of random forest and bagging classification trees for classification. J. Stat. Inf. 25(10), 18?22 (2010)
Zhang, J., Xie, N., Zhang, X., Yue, K., Li, W., Kumar, D.: Machine learning based resource allocation of cloud computing in auction. CMC Comput. Mater. Continua 56(1), 123?135 (2018)
Yin, W., Zhang, X., Abulimiti, B., Liu, Y., Yan, Y., Zhou, F., Jin, F.: Electronic structure and physical characteristics of dioxin under external electric field. CMC Comput. Mater. Continua 55(1), 165?176 (2018)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Lihua, G., Yan, S., Kunpeng, L., Longzhu, Z., Yi, Z. (2019). Prediction on Payment Volume from Customer Service Electricity Channel. In: Sun, X., Pan, Z., Bertino, E. (eds) Artificial Intelligence and Security. ICAIS 2019. Lecture Notes in Computer Science(), vol 11633. Springer, Cham. https://doi.org/10.1007/978-3-030-24265-7_28
Download citation
DOI: https://doi.org/10.1007/978-3-030-24265-7_28
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-24264-0
Online ISBN: 978-3-030-24265-7
eBook Packages: Computer ScienceComputer Science (R0)