Web-Books
in the Austria-Forum
Austria-Forum
Web-Books
Tagungsbände
Intelligent Environments 2019 - Workshop Proceedings of the 15th International Conference on Intelligent Environments
Page - 36 -
  • User
  • Version
    • full version
    • text only version
  • Language
    • Deutsch - German
    • English

Page - 36 - in Intelligent Environments 2019 - Workshop Proceedings of the 15th International Conference on Intelligent Environments

Image of the Page - 36 -

Image of the Page - 36 - in Intelligent Environments 2019 - Workshop Proceedings of the 15th International Conference on Intelligent Environments

Text of the Page - 36 -

Predicting he InterbankCapital AdequacyLevelBased nFinancialData Analysis YaojunDUa,FangjunWANGa andLipingSHENa aSchoolofElectronic InformationandElectricalEngineering Shanghai JiaoTongUniversity, Shanghai,China Abstract.Theadequacyof interbankcapital is affectedbymanyfactors, including the tightnessof theentirefinancialmarket and theups-and-downsof interest rates. It has great significance for commercial banks and other non-bank institutions to diagnose thedisturbance factorsof interbankcapital, andpredict futurecapital ad- equacy level in advance to deploy appropriate countermeasures accordingly. This paper attempts to analyze the relevant factors affecting the interbank capital and topredict the adequacy level of interbankcapital basedon structured andunstruc- turedfinancial data. For unstructureddata,we crawl the texts fromSinaFinancial Newsandthenmakepre-processing, includingwordsegmentation,emotionalword extraction andword-to-vector transformation. For structured data the preprocess- ing includes paddingmissing value, data normalization, feature selection and da- ta dimensionality reduction. The predictionmodelswe tried includeGBDT,XG- Boost, LSTM,SVM, andPerceptron. Experiments show that two-category (loose and tight) average accuracy of the overall adequacy level of interbank capital can achievemore than94.5%. Keywords. Interbank Capital Adequacy Level, Prediction, Natural Language Processing (NLP),FinancialDataAnalysis 1. Introduction Commercial banks have a special and important role in the entire financial systemand even in thenational economy.Thecapital adequacy level is ameasureof abank’s avail- able capital to protect depositors and promote the stability and efficiency of financial systemsaround theworld. It usually indicatesmoney supply and the ability of themar- ket regulationpolicy to support financial products. The indicators includebroadmoney supply (M2), stamp duty, central bank interest rates, etc. The prediction of the capital adequacy of commercial banks can provide decision-making support for the assets al- location, risk control and interbank lending, and enhance the liquidity of the inter-bank moneymarket, andvery important,playsapositive role in theearlywarningoffinancial risks. With the rapiddevelopment of information technology, bigdata analysis andartifi- cial intelligence, thefinancial industry is also actively trying tousenew technologies to solve traditional problems.At present, academic researches onfinancialmarketmostly focuson theanalysis of structureddata, and fewresearch studies thepredictionof capi- o t Intelligent Environments 2019 A. Muñoz et al. (Eds.) © 2019 The authors and IOS Press. This article is published online with Open Access by IOS Press and distributed under the terms of the Creative Commons Attribution Non-Commercial License 4.0 (CC BY-NC 4.0). doi:10.3233/AISE190020 36
back to the  book Intelligent Environments 2019 - Workshop Proceedings of the 15th International Conference on Intelligent Environments"
Intelligent Environments 2019 Workshop Proceedings of the 15th International Conference on Intelligent Environments
Title
Intelligent Environments 2019
Subtitle
Workshop Proceedings of the 15th International Conference on Intelligent Environments
Authors
Andrés Muñoz
Sofia Ouhbi
Wolfgang Minker
Loubna Echabbi
Miguel Navarro-Cía
Publisher
IOS Press BV
Date
2019
Language
German
License
CC BY-NC 4.0
ISBN
978-1-61499-983-6
Size
16.0 x 24.0 cm
Pages
416
Category
Tagungsbände
Web-Books
Library
Privacy
Imprint
Austria-Forum
Austria-Forum
Web-Books
Intelligent Environments 2019