A Novel Automated Financial Transaction System Using Natural Language Processing

  • Sachin AgarwalEmail author
  • Prasenjit Mukherjee
  • Baisakhi Chakraborty
  • Debashis Nandi
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 921)


This paper proposes an automated financial transaction system (AFTS) that accepts a natural language transaction from a user in a query-response model that will be automatically converted to corresponding journal and ledger entries. This model uses the POS tags assigned to each token in a transaction to determine the name of account associated with the transaction and insert them in semantic table. The Journal and ledger entries will be produced from the semantic table. The type of transaction means debit or credit detection is dependent on relationship attributes in the semantic table. The proposed system generates journal and ledger entries from natural language transaction text in automated way. The proposed model uses a well-organized database to store keywords that helps to determine the account name and the type of transaction in time of semantic analysis.


AFTS Financial Transaction System Natural language query Query-Response Model Automated accounting 


  1. 1.
    Pagrut, A., Pakmode, I., Kariya, S., Kamble, V.: Haribhakta, Y: Automated SQL query generator by understanding a natural language statement. Int. J. Nat. Lang. Comput. (IJNLC) 7(3), 1–11 (2018)CrossRefGoogle Scholar
  2. 2.
    Kunte, A.S., Hasbe, A., Chavan, A., Patil, K.: Natural language query processing. Int. Res. J. Eng. Technol. (IRJET) 5(3), 2731–2733 (2018)Google Scholar
  3. 3.
    Mukherjee, P., Chakraborty, B.: Automated knowledge provider system with natural language query processing. IETE Tech. Rev. 33(5), 525–538 (2016)CrossRefGoogle Scholar
  4. 4.
    NLTK 3.0 Documentation. Accessed 06 May 2018
  5. 5.
    Loper, E., Bird, S.: NLTK: The Natural Language Toolkit. In: ETMTNLP ‘02 Proceedings of the ACL-02 Workshop on Effective tools and Methodologies for Teaching Natural Language Processing and Computational Linguistics, Philadelphia, Pennsylvania, vol. 1, pp. 63–70 (2002)Google Scholar
  6. 6.
    Yumusak, S., Dogd, E., Kodaz, H.: Tagging accuracy analysis on part-of-speech taggers. J. Comput. Commun. 2, 157–162 (2014)CrossRefGoogle Scholar
  7. 7.
    Akers, G.A., Kuno, S.: Automated system for generating natural language translations that are domain-specific, grammar rule-based and/or based on part-of speech. US6278967B1. cited by, Logovista Corp, 31 August 1992
  8. 8.
    Abebe, S.L., Tonella, P.: Natural language parsing of program element names for concept extraction. In: IEEE 18th International Conference on Program Comprehension (ICPC), pp. 156–159. University of Minho, Braga, Minho, Portugal (2010)Google Scholar
  9. 9.
    Iswandi, I., Suwardi, I.S., Maulidevi, N.U.,: Designing rules for accounting trans-action identification based on Indonesian NLP. In: Annual Applied Science and Engineering Conference (AASEC), Bandung, Indonesia, vol. 180, no. 1 (2016)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Sachin Agarwal
    • 1
    Email author
  • Prasenjit Mukherjee
    • 1
  • Baisakhi Chakraborty
    • 1
  • Debashis Nandi
    • 1
  1. 1.Department of Computer Science and EngineeringNational Institute of TechnologyDurgapurIndia

Personalised recommendations