Predicting Firms’ Taxpaying Behaviour Using Artificial Neural Networks: The Case of Indonesia

Due to the complexity of tax and the time and resources needed to monitor and examine tax returns,tax noncompliance is challenging to detect. Big data and sophisticated analytics might help taxauthorities extract actionable data insights. Using income tax record data, this paper employs anArtificial Neural Networks (ANN) model to predict and discover the determinants of firms’ taxpayingbehaviour. To the best of the author’s knowledge, this study is the first to apply ANN to exploit thetaxpaying behaviour of Indonesian firms. This work examined 538,254 firm-level administrative dataacross fiscal years 2014 and 2019 to predict the magnitude of tax payment based on seven variablesof interest: types of tax returns, gross profit margin, operating profit margin, other business incomeratio, other business expense ratio, positive fiscal adjustment ratio, and negative fiscal adjustmentratio. Multi-Layer Perceptron Neural Network-based models were trained to predict three categoriesof taxpaying measurement—i.e, Corporate Tax Turnover Ratio (CTTOR)—across varying magnitudesof annual turnover. The models predicted the firms' taxpaying behaviour with an average accuracyrate above 92%. The implementation of artificial intelligence also allows this study to identifyheterogeneous channels responsible for firms’ taxpaying behaviour across groups. This study findsother business income and positive fiscal adjustment to be significant predictors of taxpayingbehaviour 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 will assistdecision-makers in tax administrations about potential areas of misreporting, enabling them todevelop evidence-based and effective policy actions.