Data lab

Supporting the digital transformation of the financial industry with R&D data science projects

Get in touch with us to understand how we can help you

Contact us

Who We Are

Our team of data scientists combines established expertise and technical knowledge to conduct end-to-end R&D data science projects with cutting-edge solutions development.

ILB Data Lab is able to support you on the different steps of an R&D data science project: from feasibility study to operational tool development, through state-of-the-art review, working closely with academic experts to run projects with scientific rigor. Our experience with financial industry use cases contributes to provide to our partners operational deliverables that can be used internally.
Our close links with ILB ESG Lab bring the needed green finance knowledge for data science projects in the ESG world, to offer this combined expertise to practionners.

Statistical analysis

Produce valuable insights from your data and highlight the key indicators with interactive tools.

Data scrapping

Gather essential data to enhance your business cases and challenge the limits of what is feasible.

State-of-the-art modeling

Master a large toolbox of methods from econometrics to advanced data science (machine and deep learning, NLP…) to run R&D projects.

Data strategy

Facilitate the building of internal teams and help them identify or prioritize use cases using our financial industry expertise and links with researchers.

Case studies

ESG data extraction via Natural Language Processing

Developed tools to extract new and clear-cut information related to ESG topic within financial and extra-financial corporate reports.

Why? Offset the lack of quality data among ESG indicator to enhance insights and metrics of business-related topics such as portfolio alignment, physical risk assessment...

  • Refined corporate NACE classification using siames transformers.
  • Created a fine-tuned entity extraction tool to precisely extract relevant information related to assets, geolocations, metrics… within corporate reports.
  • Leveraged few-shot learning techniques to detect sectorial exclusion policies to meet responsible investing guidelines.

NLP, Green Finance, Investment Banking, Risk

Leveraging banking data for credit risk estimation

Implemented a credit risk score using banking data for clients with no credit history.

Why? Serve more widely clients with no credit history and use the information included in banking data for credit worthiness and repayment behaviour.

  • Analyzed the sociodemographic and risk profile of clients with no credit history.
  • Implemented a pipeline to process banking data and extract relevant KPIs using domain knowledge and statistical characteristics.
  • Developed a reusable methodology for integrating banking data in Machine Learning models.

Credit Risk, Machine Learning, Banking data, Retail banking, Inclusion

Money laundering and terrorism financing detection

Leveraged state-of-the-art graph neural network approaches to improve suspicious activity detection.

Why? Tackle the increasing regulation pressure and continuous surveillance needs regarding anti-money laundering and counter terrorist financing.

  • Benchmarked existing supervised, unsupervised and weakly supervised techniques to detected suspicious activities.
  • Open-sourced ad-hoc study to assess the relevance of graph neural networks applied to incomplete transactional graphs.
  • Improved existing detection tool by capitalizing on graph autoencoded embeddings with operational and conclusive results.

Deep Learning, Graphe, Retail Banking, Investment Banking

Sinistrality prediction of a car insurance portfolio

Developed predictive models of sinistrality for a car insurance portfolio. Highlighted the explaining factors.

Why? Include them into the partner's prevention roadmap to reduce sinistrality.

  • Deep-dived on data to understand and aggregate them at the appropriate level.
  • Collaborated with academic experts on statistics for actuarial science to challenge benchmark actuarial models for sinistrality with machine learning.
  • Shared an interactive support tool to understand sinistrality drivers.

Data Analysis, Machine Learning, Insurance, Prevention

Graph Neural Networks for Identity and Access Management

Joined a dedicated task force on AI applied to cybersecurity. Tackled their number one priority use case about internal access rights handling.

Why? Reduce the increasing risk that cybersecurity poses for the banking industry.

  • Interviewed most of the bank cybersecurity experts, to analyse potential issues to work on and useful data sources.
  • Analyzed all the bank employees access rights to understand the drivers of anomalous accesses combinations.
  • Developed a pipeline based on unsupervised training of Graph Convolutional Networks to identify potential abnormal users.
  • Synthetized results in an HTML dashboard with potential toxic users highlighted, to be easily used on several scopes (applications, teams…).

Cyber, Bank, Deep Learning, Graph

Creation of a 2°C CAC40

Performed a feasability study to create a financial index aligned with a 2°C transition pathway. Built on the release of the first 360 review of associated metrics by the ILB.

Why? Address the increasing demand from investors on indexes aligned with decarbonization scenarios since 2015 (Paris Agreements).

  • Designed closely with the authors of the Alignment Cookbook, from ILB GSF network.
  • Explored several methodology options (data providers, index creation, weights repartition, exclusion filters, quantity to maximise, performance metrics, etc).
  • Allowed the partner to better understand current limitations of alignment metrics and its first aligned index release delayed by a few years.

Optimization, Green Finance, Portfolio Alignment, Investment banking

Contact us

Our Address

28 Pl. de la Bourse, 75002 Paris

Email us

contact.datalab@institutlouisbachelier.org