Useful Generative AI Coming to Accounting and Reporting

People are starting to figure out how to apply generative artificial intelligence to accounting and reporting processes.  Here are three examples:

  • Engine B's Copilots:  As explained in this press release, Engine B is bringing "copilots" that leverage generative AI to audit, tax, and accounting markets.
  • Workiva's Generative AI: Watch the video about half way down the page.  It shows how generative AI can be used effectively in the process of creating reports.
  • PWC's Consulting Chatbot: This is a collaboration between OpenAI and PWC to offer consulting on complex issues such as tax, legal, and human resources.
  • Jinsei.ai is a startup that is unifying generative AI, machine-learning, and rules-based AI.
There are very likely others creating similar solutions that leverage GPT4 transformers working on specific large language models (LLMs).  Those solutions will very likely prove to provide benefits.  But this will only be the beginning.

Imagine combining technologies, creating a hybrid of GPT4 transformers, specific large language models, and rules based deductive reasoning that leverage properly created XBRL taxonomies that describe financial reporting schemes. A unified LLM and knowledge graph that offers the best of both worlds.

Today, financial reporting schemes are books or maybe content management systems containing information organized for humans to read.  So, that information is semi-structured; but the structure is for the presentation of information in paragraphs, tables, and such for an accountant to read.  So, consider something like the documentation of a typical financial reporting scheme exemplified here in this PDF that documents, describes, and specifies AASB 1060 which is effectively financial reporting for small and medium sized enterprises in Australia.

Just parsing that PDF (with a tool like this) will not get you where you want to be. Why? The reason is that the document is in no way connected so something like an XBRL taxonomy for AASB 1060 which provides explicit rule-based information.

But what if you did connect the PDF and the XBRL taxonomy?  I created a prototype of what I am talking about, see page 13 of this document, which shows this mapping of the financial reporting scheme disclosure rules with the XBRL taxonomy terms using hashtags:

So, imagine having a well constructed ontology-like thing (a.k.a. knowledge graph) that is connected to a specific large language model which included the accounting and reporting rules specified by a standards setter or regulator for a specific financial reporting scheme connected to a knowledge graph that explained that information precisely and accurately in a manner that is readable, and therefore understandable, by machine-based processes.  All this is hooked to the logical model of a financial report represented in the form that is usable  by software.  Tie all this together into one framework, create a method for processing all this and what do you get?  A paradigm shift.

But don't make the mistake of imagining one instance of what I am describing.  Even better, imagine a framework for creating hybrid artificial intelligence solutions for any financial reporting scheme.


Now, imagine connecting all that to a software application for creating financial reports.  What do you get?  Well, if the software is built correctly you get an expert system for creating financial reports.

Now, tie all of the above together with some other technologies that seem to be converging such as blockchain, triple-entry accounting, REA, semantic spreadsheets, Lean Six Sigma and you get a whole bunch of possibilities that open up.  You get a great transmutation.

Additional Information:

Comments

Post a Comment

Popular posts from this blog

Relational Knowledge Graph System (RKGS)

Image
Relational Knowledge Graph System (RKGS) is an interesting idea that combines the relational paradigm and the knowledge graph paradigm.  This documentation, Why RKGS , explains the idea. This gets even more interesting with the notion of "relational AI".  RelationalAI is described as follows by the company of the same name, Relational.ai : “RelationalAI is a cloud-based relational knowledge graph management system, with state of the art probabilistic processing and declarative reasoning at scale to make developing Data Applications a superpower for your business.” This notion of knowledge graphs represented in relational databases fits into my belief that knowledge graphs have two aspects: the expression SYNTAX and the logic of what is expressed or SEMANTICS. While the LOGIC of a knowledge graph is always the same regardless of technical syntax used to express that logic; there are many, many different technical syntaxes that can be used to represent a knowledge graph. There
Read more

Getting Started with Auditchain Luca

Image
The Innovator's Dilemma points out that disruptive innovations often look like toys that are doing everything wrong. Auditchain Luca , which is part of the Auditchain Suite , is a unique approach to creating a knowledge graph .  To experience using Auditchain Luca, have a look at the Getting Started with Auditchain Luca instructions. Be sure to grab the Excel and JSON import files used for this getting started exercise.   This getting started exercise uses one of several different approaches to getting information into a tool for constructing and viewing professional quality knowledge graphs .  Additional getting started guides will be made available over time. Auditchain Luca might not make sense to you if you don't understand the paradigm shift that is occurring and if you have not shifted your mental map. For the next step in your journey, consider trying creating a report using a financial reporting scheme template . If you are struggling to figure out how to register or
Read more

Evaluating the Quality of XBRL-based Financial Reports

Image
From the time public companies started submitting XBRL-based financial reports to the U.S. Securities and Exchange Commission, I have been looking at those reports, trying to understand the XBRL-based reports, and trying to figure out how to get them right.  That information was used to figure out how to create software applications that help professional accountants get these reports right. Here is information that summarizes my testing and results which I stopped doing March 31, 2019: Analysis of the high level accounting relationships in the 10-Ks of about 5,716 financial reports  (5,063 public companies, about 89.1% got all these high level accounting relationships consistent with expectation, 623 were inconsistent and manual confirmation revealed the inconsistency was an error) Documentation that helps you understand 26 different types of errors in XBRL-based reports High quality documentation of hundreds of errors in XBRL-based reports submitted by public companies to the SEC Doc
Read more