The Interdisciplinary Centre for Security, Reliability and Trust (SnT) at the University of Luxembourg has entered a collaborative research partnership with financial firm Clearstream, part of Deutsche Börse Group, and consulting firm escent. Over the next four years, a joint research project will explore how Artificial Intelligence (AI) and Natural Language Processing (NLP) can be used to simplify and standardise requirements analysis for IT projects in the financial industry. The project aims eventually to render processes more cost- and time-efficient.
In IT projects, stakeholders must clearly and precisely define user requirements to decide, with the agreement of all stakeholders, on the necessary capabilities and characteristics of a system. This task is especially laborious in the financial industry because of strict legal and regulatory provisions and the multiple stakeholders involved. The new strategic initiative, run in collaboration with escent, a consulting firm specialised in business analysis and requirements engineering, looks to automate the laborious analysis tasks present in Clearstream’s already mature IT system requirements engineering practices.
Requirements typically contain content written in both software modelling and natural descriptive languages. Reconciling the two can be a significant challenge. The objective is therefore to develop software solutions enabling analysts to consistently manipulate – and detect inconsistencies between – both types of content. Further, the project will develop tools to derive acceptance criteria – the ‘pass or fail’ conditions a system must meet in order for it to be accepted by a client – from these requirements documents.
Prof. Lionel Briand, Vice-Director of SnT, emphasised the importance of precise and consistent requirements: “Nearly 50% of budget overruns in IT projects are caused by inadequate requirements which ripple through system design and deployment. Together with our partners, we will work at the cutting edge of new technology to introduce automation to the requirements engineering process – reducing incompleteness, inconsistency, and ambiguity to a minimum – and facilitating the analysis of system compliance.”
Philippe Seyll, Co-CEO of Clearstream Banking S.A., said: “At Clearstream, we are taking a collaborative approach when engaging with new technology trends. As a Luxembourg-based company, for us, this research partnership with the University of Luxembourg’s SnT is the ideal way to combine business know-how and scientific research capabilities to investigate how new technologies, such as AI and NLP, can help move our industry forward. We look forward to working with our partners on this new project.”
Benoit Cardinael, escent Co-Founder, added: “escent constantly monitors emerging trends in the field of requirements engineering. Defining efficiently high-quality requirements is key to the success of complex IT projects. This research partnership provides us with the unique opportunity to leverage our field expertise of current requirements engineering practices to steer research towards the highest adding value areas. We are thrilled to be associated to this initiative!”