Improving Invoice Allocation in Accounting—An Account Recommender Case Study Applying Machine Learning

Markus Esswein (), Joerg H. Mayer, Diana Sedneva, Daniel Pagels and Jean-Paul Albers
Additional contact information
Markus Esswein: University of Duisburg-Essen
Joerg H. Mayer: Darmstadt University of Technology
Diana Sedneva: University of Duisburg-Essen

A chapter in Digital Business Transformation, 2020, pp 137-153 from Springer

Abstract: Abstract Covering transactions between buyers and sellers, invoices are essential. However, not all invoices can be directly matched to a purchase order due to missing order numbers, differences in terms of the invoice amount, quantity and/or quality. Following design science research (DSR) in information systems (IS), the objective of this article is to propose a new kind of an account recommender by applying machine learning. We take a chemical company as our case study and build a prototype that today handles more than 500,000 invoices without purchase order per year more accurately and efficiently than manual work did before. Finally, we propose five design guidelines to drive future research as follows: (1) Truly understand the business need; (2) More data can only get you so far; (3) Give the machine a good starting position; (4) Computing power is crucial; (5) Do not burn your bridges yet (manual intervention).

Keywords: Account recommender; Invoices without a purchase order (“SAP financials (FI) postings w/o a purchase order”); Cognitive-based automation; Machine learning (ML); Nearest neighbor classification; Design science research (DSR) in information systems (IS). (search for similar items in EconPapers)
Date: 2020
References: Add references at CitEc
Citations:

There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:lnichp:978-3-030-47355-6_10

Ordering information: This item can be ordered from
http://www.springer.com/9783030473556

DOI: 10.1007/978-3-030-47355-6_10

Access Statistics for this chapter

More chapters in Lecture Notes in Information Systems and Organization from Springer
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().