Using predictive analysis to improve invoice-to-cash collection

ABSTRACT

It is commonly agreed that accounts receivable (AR) can be a source of financial difficulty for firms when they are not efficiently managed and are underperforming. Experience across multiple industries shows that effective management of AR and overall financial performance of firms are positively correlated. In this paper we address the problem of reducing outstanding receivables through improvements in the collections strategy. Specifically, we demonstrate how supervised learning can be used to build models for predicting the payment outcomes of newly-created invoices, thus enabling customized collection actions tailored for each invoice or customer. Our models can predict with high accuracy if an invoice will be paid on time or not and can provide estimates of the magnitude of the delay. We illustrate our techniques in the context of real-world transaction data from multiple firms. Finally, simulation results show that our approach can reduce collection time up to a factor of four compared to a baseline that is not model-driven.

REFERENCES

• 1: Bailey, D. R., Butler, B., Smith, T., Swift, T., Williamson, J., Scherer, W. T. Providian Financial Corporation: Collections Strategy, Systems Engineering Capstone Conference, University of Virginia, 1999
• 2: Eibe Frank , Ian H. Witten, Generating Accurate Rule Sets Without Global Optimization, Proceedings of the Fifteenth International Conference on Machine Learning, p.144-151, July 24-27, 1998
• 3: Hastie, T., Tibshirani, R., Friedman., J. The Elements of Statistical Learning. Springer Verlag, New York, NY, 2001
• 4: John, H. G., Langley, P. Estimating Continuous Distributions in Bayesian Classifiers. In: Eleventh Conference on Uncertainty in Artificial Intelligence, San Mateo, 1995, 338--345.
• 5: Milack, J. Receivables Management and Collection Enforcement, Accenture. http://www.accenture.com/NR/rdonlyres/694215F2-A16A-4BF8-90AA-C9E508E29EC0/0/receivables.pdf
• 6: J. Ross Quinlan, C4.5: programs for machine learning, Morgan Kaufmann Publishers Inc., San Francisco, CA, 1993
• 7: Robert E. Schapire, The Strength of Weak Learnability, Machine Learning, v.5 n.2, p.197-227, Jun. 1990 [doi>10.1023/A:1022648800760]
• 8: Shao, M., Zoldi, S., Cameron, G., Martin, R., Drossu, R., Zhang, G., Shoham, D. Enhancing delinquent debt collection using statistical models of debt historical information and account events, U.S. patent 7,191,150, June 2000
• 9: http://www.crfonline.org/orc/ca/ca-7.html.
• 10: http://www.oracle.com/global/uk/portal/special_edition_order_management_datasheet.pdf
• 11: http://www.sap.com/industries/wholesaledistribution/businessprocesses/ordertocash.epx
• 12: http://www.talgentra.com/content/Using%20Predictive%20Modelling.pdf?dltitle=Using%20Predictive%20Modelling.pdf
• 13: http://www.cforia.com/products.htm
• 14: http://www.intelligentresults.com/products/

INDEX TERMS

Primary Classification:
  G. Mathematics of Computing
  G.3 PROBABILITY AND STATISTICS
      Subjects: Correlation and regression analysis

Additional Classification:
  G. Mathematics of Computing
  G.3 PROBABILITY AND STATISTICS
      Subjects: Experimental design

  I. Computing Methodologies
  I.3 COMPUTER GRAPHICS
      I.3.8 Applications
  I.6 SIMULATION AND MODELING
      I.6.3 Applications

  J. Computer Applications
  J.1 ADMINISTRATIVE DATA PROCESSING
      Subjects: Business; Financial (e.g., EFTS)

General Terms:
Design, Economics, Experimentation, Performance

Keywords:
accounts receivable, invoice to cash, knowledge discovery, order to cash, payment collection, predictive modeling