Use of Big Data in Tax Administrations

Nowadays, organizations are “flooded with data” and Tax Administrations (TAs) do not escape it. For this reason, they are increasingly using various technologies such as Big Data to be more efficient and effective in their mission.

In this article, I am going to comment basic concepts of Big Data and some cases of application of the aforementioned technology, which definitely will continue to increase.



The concepts of Big Data[1], data analysis and artificial intelligence are not new, but some technological advances in recent years have made their intensive use possible in companies and in public administration, as well as having a positive influence on TAS.

The main achievements are:

  • The great expansion of processing and storage capacity in computers associated with the reduction of their costs.

  • The increasing availability of communications networks and broadband Internet.

  • The development of effective models to capture, store and process massive data and advanced cognitive algorithms.

  • The emergence of new data sources (e.g., sensors, GPS, social networks, etc.), including electronic invoices and the exchange of tax information between countries.

The ultimate goal of Big Data is to create value, and this is largely in analytical capacity. The question is to be able to ask the data in such a way that the information collected can give the necessary answers to understand what happens, why it happens, and even what can happen. These variants are actually what we know as Predictive, Descriptive and Prescriptive Analysis[2].

Descriptive Analytics uses historical data, identifying behaviors and drawing how things are being done. It is the most used analytics, and its objective is to make an important instant image of the situation to be able to make decisions with a high degree of success.

Predictive Analytics makes it possible to create models that allow predicting what will happen in advance.

Finally, Prescriptive Analytics analyzes the data to find the solution among a range of variants. Their task is to optimize resources and increase operational efficiency. It uses simulation and optimization techniques, managing to point out which is the path that is really convenient to choose.



In the United States, the IRS uses Big Data to combat tax fraud. One of the strategies employed, social media data mining, is used to prove that people are living a more prosperous lifestyle than their tax records, this successfully saves $ 300 billion in lost taxes each year[3].

In the United Kingdom. the HMRC has developed since 2017 the Connect system, a computerized data mining system of social network analysis software that cross-checks the tax records of companies and individuals with other databases to establish fraudulent activity. The software combines analytical tools and collects the information and implements predictive analysis similar to credit rating and has dynamic benchmarking. It seeks the correlation of income with lifestyle, comparing it with multivariate statistical models.

Data comes from a variety of sources[4] including banks, land registry, credit cards, owned or sold vehicles, tax documents, city tax paid, VAT registration, last year’s tax return, any tax investigation, occasional employer income, company benefits, child benefits and child support payments, online platforms, social media all public postings, web browsing and email records.

Also in the UK, there is ADEPT (Analytics for Debt Profiling and Targeting), which is a Big Data analysis system used to manage debts[5].

In Spain, AEAT uses Big Data to track wealthy people who intend to reside abroad for tax purposes.[6].

The AEAT has already carried out specific control tasks to determine where large assets reside, through the tracking of information such as expenses in establishments or family relationships. Thanks to Big data, the agency now has an ad hoc tool to cross over about 70 different sources of information and select taxpayers with relevant assets that could be defrauding the treasury.

In addition, the Tax Control Plan 2021 of the AEAT of Spain provides for the implementation of analysis of “BigData” in the field of personal income tax, for the implementation of a project that seeks to reduce, using the experience gained, the errors of the taxpayer to file the tax returns. This is in line with international strategies and “nudge” techniques (directed to encourage and promote a correct tax behavior) based on the approach “behavioural insights” (approach towards a better understanding of the behavior of the taxpayer).

In Costa Rica[7], through the use of Big Data, tax collection was improved. The predictive model designed with data mining techniques used by the Ministry of Finance in Costa Rica detected the simulation of payments to third parties for more than $31 million.

In Mexico[8], to strengthen its mechanisms for compliance with tax obligations, the SAT uses AI, which allows collecting a large volume of data from electronic invoices.

The SAT has the potential to exploit the most sophisticated algorithms of AI, in order to improve oversight and raise Gross Domestic Product (GDP) collection by 3%.

In the case of Big Data, the SAT already solved three main problems before implementing AI: 1. Creation of algorithms. 2. Convert data into structured information. 3. Make the information accessible in real time.

In Australia, the Australian Tax Office (ATO) is building a network analysis solution called ‘ANGIE’ to help its tax evasion working group discern complex, multi-level relationships between taxpayers[9].

The solution, which will be supported by a graph database, is being developed as part of the working group’s data and analysis program.

ANGIE will automatically identify and group taxpayers to understand their relationship with each other. It will allow the working group to detect “patterns of interest” and visualize new links between clients.

In India, a Business Standard report says data collected from Insight will be segregated. This will create the taxpayer’s master profile, which will include the address, signature, and tax refund profile. There’s also a segment called business intelligence that will basically discover people who don’t comply[10].

A geographic information system will help the TA to focus on a specific area for more focused actions. It will also rank taxpayers based on parameters such as income, profits and capital gains, the report says.

In Canada, the CRA, by analyzing macro data, seeks to combat tax evasion abroad. The CRA continues to prioritize obtaining better data, improving the use of data to guide its compliance actions, and achieving results in its fight against foreign tax evasion and aggressive tax avoidance[11].

In South Korea, a big data analytics system based on artificial intelligence has been developed, which can analyze various data, including tax invoices, cash receipts, and family and friends’ data[12].



I am convinced that Big Data, such as AI and Blockchain, among other modern technologies, are here to stay and their use will continue to be enhanced in both the public and private sectors.

However, I warn that it will be necessary to analyze each particular case, considering the context of each TA, the possible application, and its benefits and costs.

It is advisable to analyze the best practices of the field and then see what problem we need to solve, to identify what manual work can be eliminated or increased through technology, and what additional information can be generated from the machine.

As with any ICT project, in order to increase the chances of success, the highest TA authorities must be involved from the beginning and closely follow its implementation.

This whole process of digitalization of TAs, including the adoption of new technologies such as Big Data, should not be carried out in isolation, but should be integrated into the digitalization of countries, within the concept of digital government.

Governments must work together with the different actors involved to ensure the proper use of AI, in an ethical and equitable way, protecting the fundamental rights of citizens and always seeking to ensure that ICTs are an integrating element with the human resources of TAs.

In short, it is vital, on the one hand, to promote technology to improve efficiency, but, on the other hand, to be attentive to its governance, avoiding possible biases in its use, always respecting the rights and guarantees of taxpayers in all areas.

[1] ICT as a Strategic Tool to Leapfrog the Efficiency of Tax Administrations / 2020 
[5] ICT as a Strategic Tool to Boost the Efficiency of Tax Administrations / 2020 

10,210 total views, 1 views today

Disclaimer. Readers are informed that the views, thoughts, and opinions expressed in the text belong solely to the author, and not necessarily to the author's employer, organization, committee or other group the author might be associated with, nor to the Executive Secretariat of CIAT. The author is also responsible for the precision and accuracy of data and sources.

Leave a Reply

Your email address will not be published.

CIAT Subscriptions

Browse through the site without restrictions. Consult and download the contents.

Subscribe to our electronic newsletters:

  • Blog
  • Academic offer (Only in spanish)
  • Newsletter
  • Publications
  • News alert

Activate subscription

CIAT Members

Representatives, Correspondent and Authorized staff (TA)