University of Agder Logo
Jahn Thomas Fidje

Artificial intelligence to dominate accounting

Centre for Artificial Intelligence Research pursues a paradigm shift in accounting, driven by novel artificial intelligence techniques. We will facilitate this shift through an industrial PhD project. The PhD project will use deep learning to gain powerful insight into accounting data, including prediction of revenue loss and next best actions. In a few years, we envision that accounting will be dominated by artificial intelligence.

Artificial intelligence has in recent years had a major impact on several industries and areas. We have seen examples of intelligent systems that are better suited to diagnosing patients than doctors, are safer drivers, and are better chess players than humans. By using methods based on the same principles as our own brain, artificial intelligence has been able to analyze and understand complicated relationships in complicated data. The financial sector, dealing daily with huge amounts of numbers and data, has undergone a digitalization change, including the introduction of electronic trading. Artificial intelligence is ready to provide a paradigm shift in the accounting offices.

Morten Goodwin writing 

Deputy Director Morten Goodwin is welcoming artificial intelligence based accounting

CAIR aims to further develop methods and algorithms to automate and improve several aspects of the financial and accounting sectors. The work will be based on a type of artificial intelligence algorithms that has received much attention recent years, referred to as Deep Learning. The project will develop new variations of Deep Learning, especially with regard to achieving increased insight and deep understanding of accounting data.

Central to the project is the development of algorithms for classification problems, such as understanding trends in the accounting data and predicting problems as well as notifying about the next best action. The algorithm will, based on historical data, understand when a business is likely to get a revenue loss and propose actions that improve and, if possible, avoid the situation. Furthermore, the project will develop methods to identify and predict deviations and trends in large amounts of data where conventional methods fail.

Students

Master student Andreas Nyland Taraldsen and PhD candidates Jahn Thomas Fidje and Per-Arne Andersen. 

The research will result in a system for automatic deep understanding of accounting. In addition,  the project will provide an intelligent dialogue-based form of customer support.

The research is carried out in collaboration with Bilagos AS