UT Students collaborating with ING

In his master thesis titled 'The Creation of an Explainable Artificial Intelligence Model to Enhance Interpretability and Transparency for ING in Their Fight Against Transactional Fraud' he explores ways of enhancing transparency and interpretability of ML models for Fraud Detection Models. 

In her master thesis titled 'Applications of Early Warning Systems for Customer Segmentation of Wholesale Banking Clients' she explorer two unsupervised clustering methods K-Means and DBSCAN.

Being a part of the AI in Finance project was a transformative experience. It provided me with a unique blend of cutting-edge research and real-world applications, enabling me to develop innovative solutions in the financial sector. The knowledge and skills I gained have been instrumental in my professional growth and continue to influence my approach to leveraging AI for financial advancements.

In his master thesis titled 'Development of Financial Distress Prediction Model for the Watchlist Classification of Wholesale Banking Clients at ING' he explorers different machine learning methods for a financial distress prediction model.

Sebastian continued to work at ING. ING utilized the techniques developed within his thesis to challenge and refine their model development methodology. Specifically, his thesis investigated and enhanced new feature design using the transactional data of retail customers to predict their probability of default. His work improved the predictive power of the model, potentially resulting in fewer defaulting clients.

In his master thesis titled 'Stakeholder-Centric Approach to Applying Machine Learning to Probability of Default Models' he underscores the importants of active engagement and value creation for stakeholders within the decision-making process.

Vitalii is master’s student in Business & Information Technology, specializing in AI research and data science. He just started the preparation for his thesis assignment at ING.

 In the master thesis titled "How to effectively implement the HRDD aspect of the CSDDD in financial institutions?", Thomas explores effective strategies for integrating HRDD processes within financial institutions to comply with the CSDDD. The 7-step action research model from Warner Burke is used as a basis. This is combined with a systematic literature review and semi-structured interviews to come to a best practice & recommendation model.

Leixin Zhang is a PhD Candidate at the University of Twente. The aim is to apply her research to real-world use-cases within ING's Wholesale Banking Advanced Analytics department. ING has a RAG setup where they need to extract answers to a set of questions from a large set of documents. The intern will be asked to study the latest research developments on confidence scores for LLMs, adjust it where needed for application to our practical use-cases, and define and build a hands-on prototype.

The Wholesale Banking Advanced Analytics team is a large team of data scientists, data engineers, software developers and many more, that are focused on bringing data, machine learning and statistical modeling into the products that we build for our clients or internal users. The data scientists in WBAA furthermore have a strong desire to keep up with and be part of the latest developments in the fields of AI, tooling and statistics. Which they do by working closely together with master’s students on a variety of topics to solve academic yet practical problems.

Jens is an enthusiastic and hardworking student, with a strong focus on continuous learning. Located in the Netherlands, he is a double MSc student in the areas of Financial Engineering & Management, Data Science & Business, and Enterprise Architecture & IT Management. Moreover, his BSc in Electrical Engineering forms an ideal basis for technical problem solving within the financial industry.

His technical proficiency spans across a diverse array of programming languages and mathematical knowledge. Beyond technical expertise, he excels in communication and interpersonal skills, demonstrating a proven ability to work independently or collaboratively. These proficiencies and interests are demonstrated through various projects, publications, and positions at companies, aiming to support his interests.

In his master thesis titled 'Confidence scores for Large Language Models' he compares four confidence-estimation methods, P(True), P(IK), Semantic Entropy, and a trained corrector model, together with the raw token probability on multiple choice, across three QA datasets that span closed-book (TriviaQA), short-context multiple-choice (CosmosQA), and grounded long-document (NarrativeQA) question answering.

In his master thesis titled 'Machine Learning for Predicting Energy Performance Certificates: Evidence from a Dutch Residential Mortgage Portfolio' he examines whether missing or invalid energy performance certificate labels for residential properties can be estimated using only publicly available data.  This question is highly relevant for financial institutions, as incomplete EPC coverage limits the quality of ESG reporting, portfolio monitoring, and transition risk assessment.

In his master thesis titled 'Developing an LLM-Based Methodology for Automated Data Remediation in Credit Risk Modelling: A Case Study at a Large Dutch Bank' he investigates how a modular Large Language Model (LLM)-based methodology can be developed and evaluated to support automated data remediation in such a regulated environment, demonstrated through a case study at a large Dutch bank. Using a Design Science Research Methodology approach, the study develops a governance-aware, evidence-grounded methodology consisting of a two-stage document classification pipeline and a retrieval-augmented generation pipeline for structured information extraction.