Scientax: Jurnal Kajian Ilmiah Perpajakan Indonesia

Greetings for all the passionate readers of Scientax: Jurnal Kajian Ilmiah Perpajakan Indonesia

Nowadays, big data and sophisticated analytics help organizations harness their data and use it to identify new opportunities in many aspects. It also might help tax authorities, the Directorate General of Taxes (DGT), extract actionable data insights. Scientax Vol 4. No. 2 (2023) presents Artificial Neural Networks for Predicting Taxpaying Behavior of Indonesian Firms, the first study that applies the Artificial Neural Networks (ANN) model to exploit the taxpaying behavior of Indonesian firms by Examining 538,254 firm-level administrative data across fiscal years 2014 and 2019. The models predicted the firms' taxpaying behavior with an average accuracy rate above 92%. Meanwhile, using time series analytics, Forecasting Value-Added Tax (VAT) Revenue Using Autoregressive Integrated Moving Average (ARIMA) Box-Jenkins Method experimented with the ARIMA Box-Jenkins method using time-series analysis of VAT revenue data to show that forecasted VAT revenue resembles the actual VAT revenue more closely than when compared to the actual VAT target by the Indonesia government.

Furthermore, in the current global era, DGT already has more comprehensive data and information from abroad based on a global consensus through an Automatic Exchange of Information (AEoI) scheme. This existence of AEoI in the Indonesia taxation system and its role in encouraging Income Tax in Indonesia has been explored in Optimalisasi Penerapan AEoI (Automatic Exchange of Information) dalam Mendorong Pendapatan Negara atas Pungutan Pajak Penghasilan. Big data is inseparable from the quality of existing data. DGT faces challenges of a large number of registered taxpayer data and missing data, Machine Learning: Classifying Taxpayer's Supervising Zone Based on the Street Address Using Natural Language Processing Algorithm answers that problem by using the ‘Bag of Words’ model.

Facing the era of data analysis, optimizing technology using certain applications will also make DGT efficient in determining policy steps, one of which is determining priority audits for certain taxpayers. Application of data mining techniques for VAT-registered business compliance uses the RapidMiner application and decision tree techniques to create a predictive model for VAT-registered business compliance. 

However, we are currently still in transition after nearly three years of dealing with the Covid-19 pandemic. It has triggered a decline in economic growth, a rising unemployment rate, and falling inflation rates leading to deflation. Do these affect the tax revenues, especially Income Tax Article 21?  Okuns Law, Phillips Curve and Its Effect on the Growth of Income Tax Article 21 Payments During Covid-19 Pandemic examines the relationship between unemployment rates, economic growth, and inflation rates during the pandemic on income tax payments Article 21. Meanwhile, the impact of the alternative tax base measurement policy on the VAT revenue performance in the Indonesian agricultural sector will be estimated in The Impact of the Alternative Tax Base Measurement Policy on the VAT Revenue Performance in the Indonesian Agricultural Sector. In the end, DGT continues to work on improving the system by optimizing the role of big data and technology because Taxes are the Epicentrum of Growth.