Artificial Neural Networks for predicting taxpaying behaviour of Indonesian firms

Abstract

Big data and sophisticated analytics might help tax authorities extract actionable data insights. In response, this paper employs an Artificial Neural Networks (ANN) model to predict and discover the determinants of firms’ taxpaying behaviour. Examining 538,254 firm-level administrative data across fiscal years 2014 and 2019, this study is the first to apply ANN to exploit the taxpaying behaviour of Indonesian firms. Multi-Layer Perceptron Neural Network-based models were trained to predict three categories of taxpaying measurement—i.e., Corporate Tax Turnover Ratio (CTTOR)—across varying magnitudes of annual turnover. The models predicted the firms’ taxpaying behaviour with an average accuracy rate above 92%. This study also reveals heterogeneous channels responsible for firms’ taxpaying behaviour across groups. The findings demonstrate other business income and positive fiscal adjustment to be significant predictors of taxpaying behaviour for small and medium firms. In contrast, operating profit margin, other business expenses, and negative fiscal adjustment are prominent predictors for large corporations. The findings of this study can provide valuable assistance to decision-makers and relevant stakeholders in tax administrations by identifying potential areas of misreporting in annual tax returns. This evidence-based approach could enable tax administrations to develop more effective policies while potentially reducing the need for extensive monitoring and associated costs.