Journal Home > Volume 24 , Issue 1
Tsinghua Science and Technology 2019, 24(1): 77-85 https://doi.org/10.26599/TST.2018.9010007
Open Access | Issue | Published: 08 November 2018

LSTM Based Reserve Prediction for Bank Outlets

Show Author's Information Yu Liu,  Shuting Dong,  Mingming Lu,  Jianxin Wang( )
School of Information Science and Engineering, Central South University, Changsha 410083, China.
Keywords:
time series prediction, reserve prediction, Long Short Time Memory (LSTM) network, date property
Cite this article:
Liu Y, Dong S, Lu M, et al. LSTM Based Reserve Prediction for Bank Outlets. Tsinghua Science and Technology, 2019, 24(1): 77-85. https://doi.org/10.26599/TST.2018.9010007
Download citation
EndNote(RIS)
BibTeX

514

Views

27

Downloads

Citations

16

Crossref

N/A

WoS

25

Scopus

5

CSCD

Abstract Full text About this article

Reserve allocation is a significant problem faced by commercial banking businesses every day. To satisfy the cash requirement of customers and abate the vault cash pressure, commercial banks need to appropriately allocate reserves for each bank outlet. Excessive reserve would impact the revenue of bank outlets. Low reserves cannot guarantee the successful operation of bank outlets. Considering the reserve requirement is effected by the past cash balance, we deal the reserve allocation problem as a time series prediction problem, and the Long Short Time Memory (LSTM) network is adapted to solve it. In addition, the proposed LSTM prediction model regards date property, which can affect the cash balance, as a primary factor. The experiment results show that our method outperforms some existing traditional methods.


menu
Abstract
Full text
Outline
About this article

LSTM Based Reserve Prediction for Bank Outlets

Show Author's information Yu Liu, Shuting Dong, Mingming Lu, Jianxin Wang( )
School of Information Science and Engineering, Central South University, Changsha 410083, China.

Abstract

Reserve allocation is a significant problem faced by commercial banking businesses every day. To satisfy the cash requirement of customers and abate the vault cash pressure, commercial banks need to appropriately allocate reserves for each bank outlet. Excessive reserve would impact the revenue of bank outlets. Low reserves cannot guarantee the successful operation of bank outlets. Considering the reserve requirement is effected by the past cash balance, we deal the reserve allocation problem as a time series prediction problem, and the Long Short Time Memory (LSTM) network is adapted to solve it. In addition, the proposed LSTM prediction model regards date property, which can affect the cash balance, as a primary factor. The experiment results show that our method outperforms some existing traditional methods.

Keywords: time series prediction, reserve prediction, Long Short Time Memory (LSTM) network, date property

References(19)

[1]
Box S. and Schmidhuber J., Long short-term memory, Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997.
DOI Google Scholar
[2]
Kashyap A. K., Rajan R., and Stein J. C., Banks as liquidity providers: An explanation for the coexistence of lending and deposit-takin, The Journal of Finance, vol. 57, no. 1, pp. 33-73, 2002.
DOI Google Scholar
[3]
Hancock D. and Wilcox J. A., Intraday management of bank reserves: The effects of caps and fees on daylight overdrafts, Journal of Money, Credit and Banking, vol. 28, no. 4, pp. 870-908, 1996.
DOI Google Scholar
[4]
Heller D. and Lengwiler Y., Payment obligations, reserve requirements, and the demand for central bank balances, Journal of Monetary Economics, vol. 50, no. 2, pp. 419-432, 2003.
DOI Google Scholar
[5]
Wang L., Chai Y., and Liu Y., Analysis of specialized production of transaction services based on essential services quantity, Tsinghua Science and Technology, vol. 22, no. 5, pp. 529-538, 2017.
DOI Google Scholar
[6]
Gray S., Central Bank Balances and Reserve Requirements. Washington, DC, USA: International Monetary Fund, 2011.
DOI
[7]
Ashcraft A., McAndrews J., and Skeie D., Precautionary reserves and the interbank market, Journal of Money, Credit and Banking, vol. 43, no. 370, pp. 311-348, 2011.
DOI Google Scholar
[8]
Calomiris C. W., Getting the right mix of capital and cash requirements in prudential bank regulation, Journal of Applied Corporate Finance, vol. 21, no. 1, pp. 33-41, 2012.
DOI Google Scholar
[9]
Krause A. and Giansante S., Liquidity and solvency shocks in a network model of systemic risk: The impact of minimum capital and reserve requirements, in Proc. 25th Australasian Finance and Banking Conf., Sydney, Australia, 2012, p. 381.
[10]
Khashei M. and Bijari M., A novel hybridization of artificial neural networks and ARIMA models for time series forecasting, Applied Soft Computing, vol. 11, no. 2, pp. 2664-2675, 2011.
DOI Google Scholar
[11]
Cai X., Venayagamoorthy N., and Venayagamoorthy G. K., Time series prediction with recurrent neural networks trained by a hybrid PSO–EA algorithm, Neurocomputing, vol. 70, nos. 13–15, pp. 2342-2353, 2007.
DOI Google Scholar
[12]
Giles C. L., Lawrence S., and Tsoi A. C., Noisy time series prediction using recurrent neural networks and grammatical inference, Machine Learning, vol. 11, nos. 1&2, pp. 161-183, 2001.
DOI Google Scholar
[13]
Chandra R., Competition and collaboration in cooperative coevolution of Elman recurrent neural networks for time-series prediction, IEEE Transactions on Neural Networks and Learning Systems, vol. 26, no. 12, pp. 3123-3136, 2015.
DOI Google Scholar
[14]
Anava O., Ning E., Mannor S., and Pescosolido B. A., Online learning for time series prediction, in Proc. 26th Annual Conf. on Learning Theory, 2013, pp. 172-184.
[15]
Van Gestel T., Suykens J. A. K., and Baestaens D. E., Financial time series prediction using least squares support vector machines within the evidence framework, IEEE Transactions on Neural Networks, vol. 12, no. 4, pp. 809-821, 2001.
DOI Google Scholar
[16]
Ke Y., Cao Y., Ouyang X., Li W., and Wang J., Unit interval vertex deletion: Fewer vertices are relevant, Journal of Computer and System Sciences, vol. 95, pp. 109-121, 2018.
DOI Google Scholar
[17]
Shi F., Chen J., Feng Q., and Wang J., A parameterized algorithm for the Maximum Agreement Forest problem on multiple rooted multifurcating trees, Journal of Computer and System Sciences, vol. 97, pp. 28-44, 2018.
DOI Google Scholar
[18]
Luo H., Li M., Wang S., Liu Q., Li Y., and Wang J., Computational drug repositioning using low-rank matrix approximation and randomized algorithms, Bioinformatics, vol. 34, no. 11, pp. 1904-1912, 2018.
DOI Google Scholar
[19]
Lu C., Yang M., Luo F., Wu F.-X., Li M., Pan Y., Li Y., and Wang J., Prediction of lncRNA-disease associations based on inductive matrix completion, Bioinformatics, .
DOI Google Scholar
Publication history
Copyright
Rights and permissions

Publication history

Received: 17 July 2017
Accepted: 07 August 2017
Published: 08 November 2018
Issue date: February 2019

Copyright

© The author(s) 2019

Rights and permissions

Return