Hierarchical classification for account code suggestion

Abstract

As part of invoice processing, businesses are required to manually classify each line item on an invoice to a specific financial account. This can be time-consuming and challenging when there is a large set of account codes to choose from. Failing to select the correct account will lead to errors in financial reporting which can be misleading for stakeholders and have adverse effects during a financial audit. The emergence of cloud-based accounting platforms has introduced potential areas for automated support across invoice processing tasks such as helping bookkeepers to select the correct financial account. Traditionally, account code suggestion is framed as a multi-class classification task, however, we explore the applicability of using a hierarchical single-label classifier. Account codes can be expressed as taxonomic classes, either explicitly through the chart of accounts or implicitly through associations with reconciled bank accounts. Our research provides evidence to support that the exploitation of hierarchical information from induced taxonomies can be highly advantageous for improving classification and recommendation performance. Furthermore, we introduce Top-K Parent Boosting, a novel post-processing strategy. We demonstrate the suitability of Top-K Parent Boosting for DAG structures and highlight its superiority in improving recommendation performance over former strategies.