FinanSE 2025

2nd International Workshop on AI Solutions for Software Engineering Challenges in Financial Firms (FinanSE 2025)

Software development has an integral role in every financial organisation; indeed, almost every service provided by a bank utilizes some form of software solution. While AI for SE research has led to solutions and innovations for many popular SE problems, there remain unresolved challenges, particularly, those challenges faced in software development in financial firms. An example of such a challenge is defect prediction, where defects are not equal as some may lead to larger reputational and financial damage than others. Consequently, testing and verification are burdened with further restraints for finance-based SE teams. Financial firms began automating processes as early as the 1960s, and as such, must maintain large legacy systems which may host critical operations. This problem is further exacerbated by the numerous mergers and acquisitions common in the financial sector, which leaves firms with a set of heterogeneous legacy systems that need to communicate with one another effectively and efficiently. Therefore, maintaining these systems while modernizing them leads to intriguing challenges, spanning from model extraction and process optimisation to code translation. Moreover, highly regulated institutions like financial firms require a high degree of transparency and accountability. These requirements facilitate the need for model fairness and explainability for any SE solution, in particular those that rely on AI.

FinanSE Workshop provides the SE community in both industry and academia with a unique opportunity to discuss such challenges and work in collaboration towards effective solutions.

Call for Papers

FinanSE’25 welcomes research papers presenting:

• Original and innovative ideas to resolve software engineering challenges in financial firms leveraging AI power
• Open research problems to pursue
• Experience reports, case studies, and tool demonstrations

We invite submissions at the intersection of financial services and AI for Software Engineering. Topics of interest include but are not limited to:

• AI/ML for Software system monitoring and analytics
• Software reliability, automated testing, and high-value defects prediction
• Software modernisation and cloud migration
• Code translation from “low resource” programming languages
• Programming without coding (natural language to software)
• Search-based software engineering and optimisation
• Model extraction for legacy software systems in low-data and highly-regulated environments
• Model explainability and fairness
• Human aspects of AI for Software Engineering in a financial market

FinanSE’25 workshop accepts both research papers and extended abstracts, presenting original contributions:

• Research papers (8 pages max, including text, figures, tables, references, and appendix) on novel approaches, tools, datasets, or studies.
• Extended abstracts (2 pages max, including text, figures, tables, references, and appendix) on novel ideas and preliminary results that have yet to be fully developed.

Motivation and Relevance

We encourage submissions that clearly articulate the software engineering challenge in financial context and practical implications of the proposed research. Authors should not only describe the technical contributions but also address why their work is essential in a financial setting, highlighting specific software engineering challenges or opportunities in areas such as trading, risk management, compliance, financial data management, or any other relevant domain.

Submission

Each submission will be reviewed by the program committee with respect to suitability for the workshop, following a double-blind process. This means that the identity of the authors must not be revealed in their submissions. Please follow the IEEE conference proceedings template to prepare your submissions, as specified in the IEEE Conference Proceedings Formatting Guidelines (title in 24pt font and full text in 10pt type, LaTeX users must use \documentclass[10pt,conference]{IEEEtran} without including the compsoc or compsocconf options).

At least one author of each accepted paper should register for the workshop and present the paper in the workshop.