Faster, more accurate iXBRL tagging through auto-tagging and machine learning

Commencing on July 1, 2018, the CIPC required that all qualifying entities prepare their Annual Financial Statements (AFS) in iXBRL format.

Our experience from other countries (where a new XBRL or iXBRL mandate is introduced) has taught us that entities initially struggle to understand the nuances of a taxonomy and the mandate, the tagging process, and concepts around XBRL/iXBRL in general.

In an aim to simplify the tagging process, IRIS CARBON®our CIPC iXBRL SaaS product, has leveraged the use of Auto Tagging and Machine Learning for iXBRL tagging. To better understand this, let’s first look at a typical tagging process.

Manual Tagging Process

XBRL or iXBRL tagging of financial data in most countries is largely a manual process. The regulator’s taxonomy (in this case, the CIPC taxonomy) is searched by the user for appropriate tags; the most preferred element is picked and applied to the concept in one’s own annual statement that requires tagging. This is a tedious process that can take several days to complete.

Automated iXBRL tagging with IRIS CARBON®’s machine learning algorithms

Drawing from IRIS’ deep expertise in XBRL/iXBRL across 22 countries, IRIS CARBON® has leveraged machine learning algorithms to automate a large part of the tagging process of annual financial statements.

Auto Tagging and Machine Learning for iXBRL tagging

Using these algorithms, IRIS CARBON® can read labels off the annual report, match patterns, understand the context of the labels, and automatically apply appropriate tags from the taxonomy.

Since accuracy is paramount, wherever IRIS CARBON® is not 100% sure of the tags, it does not auto tag the values. Instead, it provides a set of suggestions, and users can pick the right tags. This trains the platform for your next document as well.

For any residual tags where no suggestions are made available, the CIPC taxonomy bundled within the platform can be used to manually tag values.

Based on these advanced capabilities in the IRIS CARBON® solution, CIPC-regulated entities can more confidently choose to do their iXBRL tagging on their own, and rest assured knowing that our expert iXBRL conversion services are available if needed.

Benefits of iXBRL Automatic Tagging

Benefit 1 - Save Time and Cost

Our advanced algorithms and intuitive tagging approaches save you significant time (with up to 95% of the AFS getting auto tagged even for first time filers). Not only do you save many hours, if not days, of your valuable time, you also save money, and simplify your iXBRL reporting process.

Benefit 2 - Greater Accuracy of Data

iXBRL implementations across the world have ensured standardization of financial reports. However, this still does not address another fundamental challenge of tagging financial information: the data might be structured but is the tagging accurate?

Our platform, for the CIPC iXBRL mandate, has an auto-tagging accuracy of 100%. Elements that are not tagged automatically are posed as a suggestion.

Given the complexity of today’s regulatory environment, intelligent technology implemented correctly can ensure consistency, lower the probability of human error, and significantly reduce an organization’s time and effort spent in the regulatory compliance process.

IRIS is a pioneer in the XBRL reporting space since 2005. IRIS has a global footprint in over 22 countries. With an experience of over 14 years, 5+ million filings for 1.5+ million entities, IRIS is a world-leader in structured data space. IRIS’ clients include security commissions, central banks, business registries, stock exchanges, public companies, private companies, banks, and mutual funds.

For a demonstration of automated tagging using your own AFS, contact us today at info@iriscarbon.com.

Contact us for automated tagging using your own AFS

SCHEDULE A FREE DEMO

Auto Tagging and Machine Learning