Internship Master thesis project in Efficient Neural Models for Large-Scale Entity Matching

As the largest bank in the Netherlands ING sees the majority of all payments made by Dutch entities. People and businesses interact by making payments to each other. Salary payments payments for rent utilities groceries payments for materials services resources. Through billions of payments the millions of entities form a large network. Of our own clients entities that have an account with ING we have information but for accounts at other banks that send payments to or receive payments from ING accounts we generally do not. We would like to use the payments sequences that accounts at other banks send to or receive from ING accounts to distill information about the account holders.
Wholesale Banking Advanced Analytics department (WBAA) at ING provides data analysis and data science solutions for the banks Wholesale banking branch.

Entity Matching is one of the fundamental data science challenges within financial institutions. In many operational processes we need to be able to link companies in a dataset to our own client base rapidly and often at scale. For instance this could involve matching a dataset of companies involved in money laundering published by a journalism collective a dataset with external CO2 emissions for clients and their suppliers or names in transactions to our clients.

This problem is challenging due to:
1.) The naïve solution of comparing all records being too computationally complex in practice (e.g. O(n*m) could take months or years for large datasets).
2.) The information available for companies differs and is noisy.

Project description
This master thesis is a research project aimed at rigorously investigating whether compact neural architectures can meaningfully outperform our current TFIDFbased entitymatching systemthe strongest baseline in productionunder realistic deployment constraints. The work centers on the endtoend research cycle: conducting indepth literature exploration formulating hypotheses and designing implementing and empirically evaluating lightweight model families such as crossencoders biencoders and other efficient variants for shorttext entity normalisation. The student will deeply examine fundamental tradeoffs between predictive performance inference speed memory footprint and largescale catalogue feasibility generating novel insights into model behaviour and operational constraints. The projects outcome will be a scientifically grounded comparative analysis and a researchdriven recommendation for a productionready architecture that balances performance with efficiency.

The team
The amazing team of data scientists at Wholesale Banking Advanced Analytics has solved this problem at scale and the first in the world to open-source our solution. See

WBAA 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 masters students on a variety of topics to solve academic yet practical problems.

How to succeed
We hire smart people like you for your potential. Our biggest expectation is that youll stay curious. Keep learning. Take on return well back you to develop into an even more awesome version of yourself.

Our team has extensive experience with student supervision. Are you a masters student looking for a thesis project and are you interested in this one

Do you furthermore

• Have solid experience with Python
• Have machine learning experience
• Have solid skills in statistics and linear algebra (matrix rank singular values matrix decomposition )
• Get at least six months to do your thesis project
• Aim to go for a publication
• Bring good vibes to your fellow data scientists

Then we offer a master thesis project a compensation of 700 euros per month close supervision and a tight community of data scientists to interact with and learn from.

Rewards and benefits

This is a great opportunity to train with highly skilled people who are experts in their field. Youll do a lot and learn a lot not only about your specialist area and the bank but also about yourself and whether this type of environment is right for you.

Youll also benefit from:

• Internship allowance of 700 EUR based on a 36 hours work week.
• Your own work laptop.
• Hybrid working to blend home working for focus and office working for collaboration and co-creation.
• Personal growth and challenging work with endless possibilities.
• An informal working environment with innovative colleagues.

During the duration of your internship at ING it is mandatory to be enrolled at a Dutch university (or EU-university for EU passport holders).

Questions
Contact the recruiter attached to the advertisement. Want to apply directly Please upload your CV and motivation letter by clicking the Apply button.

About our internships

Every year more than 350 students join our internship program. While there are no guarantees about your future many of our former interns move into a permanent role or onto our International Talent Programme (traineeship).

Whatever happens an internship at ING is the ideal opportunity to meet a wide variety of people to build up your own network and to learn about many different aspects of banking put simply its a great start to your career.