Blog

Here you will find information about our past and ongoing projects, as well as opinions on current topics in Banking Analytics.
HouseNetwork-e1707236743536.jpg?fit=200%2C200&ssl=1

February 6, 2024by Cristian0

Our latest preprint, titled “Attention-based dynamic multilayer graph neural networks for loan default prediction”, introduces a novel model that could enhance the accuracy of credit risk assessments.

Credit Scoring and Correlated Default

The inspiration for this work comes from our previous studies, which clearly show that borrowers are not isolated entities, but part of a complex web of connections that can influence their probability of default. This interconnectedness suggests that a borrower’s risk of default may be impacted not just by their financial situation, but also by the network of relationships they are part of.

Our study leverages these insights, proposing a sophisticated model that combines Graph Neural Networks (GNNs) and Recurrent Neural Networks (RNNs) to assess credit risk. This way, the model can use dynamic multilayer networks, each layer reflecting a different source of network connection. The proposed model considers different types of connections between borrowers, such as geographical location and choice of mortgage provider, and the evolution of these connections over time.

How It Works

GNNs are a class of deep learning models designed to operate on graphs — structures that represent relationships between entities. These models are adept at capturing the complex patterns inherent in networks of borrowers. On the other hand, RNNs excel at processing sequential data, making them ideal for analyzing the temporal dynamics of these borrower networks.

The model introduced in our study, by our PhD student Sahab Zandi, in collaboration with Prof. Christophe Mues and Kamesh Korangi from the University of Southampton and Prof. María Óskarsdóttir from Reykjavík University, adds a layer of sophistication with an attention mechanism. This mechanism prioritizes certain time points over others, based on their relevance to the borrower’s default risk. Such an approach allows for a more nuanced analysis, distinguishing the model from traditional methods of credit scoring.

Empirical Evidence of Superior Performance

When tested against a dataset provided by U.S. mortgage financier Freddie Mac, the model not only outperformed traditional credit scoring methods but also offered more in-depth insights into the nature of default risk. We found that the model’s ability to account for the dynamic and multilayered nature of borrower connections enhanced its predictive accuracy. This suggests that the future of credit scoring lies in the ability to understand and model the complex web of relationships that influence financial behaviour.

Looking Ahead

The implications of this study are multifaceted. For lenders, adopting such models could help understand how risk propagates and affects both individual borrowers and their portfolios in a high-stakes market. For borrowers, it could translate into more access to credit by empowering so-called ‘Second Look’ models, which provide thin-file borrowers with a more detailed evaluation. Our results can be part of such evaluation. And for the field of operational research and finance at large, this study paves the way for further exploration into the use of machine learning and network science in multilayered, dynamic, environments.

As we move forward, the exploration of even more sophisticated models — incorporating additional layers to capture a broader array of connections or employing different types of GNNs and RNNs — promises to unlock new insights into credit risk and beyond. The journey towards a more interconnected and intelligent approach to credit scoring is just beginning, and its potential benefits for both lenders and borrowers are immense.

Interested in the topic? Read the working paper on ArXiV!


Untitled150x150px4.png?fit=150%2C150&ssl=1

February 4, 2024by Cristian0

A bit late to the party, but as the first paper on this topic was recently published at EJOR (ArXiV, Journal), I thought it may merit the post.

Last year at the credit scoring conference, I was interviewed by Brendan Le Grange, host of the podcast How to Lend Money to Strangers. We discussed the paper I presented there, part of Sherly’s PhD thesis, on causal models for credit limit settings. The preprint of that paper will appear soon, read the first one meanwhile!

If you want to hear more about my thoughts on credit limit setting and how it relates to causal modelling, listen to the podcast episode in this link.



December 1, 2023by Daniel Abib0

We had a great time attending the 2023 INFORMS Annual Meeting that took place between October 15th to October 18th in Phoenix, AZ. This is one of the largest conferences in the field of OR, with 6,000+ attendees and 1,400+ sessions.

The BAL had a strong presence at the conference with four presentations:

  • On October 15th, we had two presentations:
    • Cristián Bravo presented the work with Kamesh Korangi and Christophe Mues on “Large-Scale Portfolio Optimization using Graph Attention Networks”.

 

  • Daniel Abib presented the work with Cristián Bravo, Raffaella Calabrese, and María Óskarsdóttir on “Optimal Feature Split in Classification Models with Dependency”.

 

  • On October 17th, Sahab Zandi presented the work with Kamesh Korangi, María Óskarsdóttir, Christophe Mues, and Cristián Bravo on “Leveraging Dynamic Multilayer Networks for Modelling Credit Risk Contagion in SMEs”.

 

  • On October 18th, Yuhao (Jet) Zhou presented the work with Collins Ntim, María Óskarsdóttir, Matthew Davison, and Cristián Bravo on “Uncovering the Network Power Gap: A Deep Learning Approach to Investigating Gender Disparities in the Boardrooms of Canadian Public Firms”.

 

We also had fun trying a few good restaurants in Scottsdale, AZ!

This was a great chance to showcase the preprints that will come out in the next few months. Stay tuned for them!



October 6, 2023by Cristian0

We had a great time attending the Credit Scoring and Credit Control Conference XVIII that took place between August 30th to September 1st in Edinburgh, UK. This conference bridges the academic/practitioner divide and is the world’s premier conference for credit scoring and credit risk related topics.

The BAL had a strong presence at the conference with six presentations:

  • On August 30th, Cristián presented the work with our PhD student Mahsa Tavakoli, cosupervised by Rohitash Chandra from UNSW, on “Multi-Modal Deep Learning for Midcap Credit Rating Prediction Using Text and Numerical Data”.
  • On August 31st we had two presentations:
    • Our collaborator Prof. María Óskarsdóttir from Reykjavík University, Iceland, presented the work by our PhD students Sahab Zandi and Kamesh Korangi, cosupervised by Prof. Christophe Mues from Southampton University and Cristián, titled “Credit Scoring with Dynamic Multilayer Graph Neural Networks”.
    • Cristián presented the work led by our PhD student Sherly Alfonso Sánchez, cosupervised by Prof. Kristina Sendova here at Western, called “Causal Learning for Credit Limit Adjustment in Revolving Lending Under Adversarial Goals”.
  • On September 1st, we had three:
    • Daniel Abib, who joined earlier this year as a postdoc at the Lab, presented the work coauthored with Prof. Raffaella Calabrese for Edinburgh University, Prof. María Óskarsdóttir, and Cristián. The work was called “Optimal Feature Split in Credit Risk Models with Dependency”.
    • Our PhD student Kamesh Korangi presented the work from his PhD, coauthored with Christophe Mues and Cristián, on “Deep Temporal Graph Networks for Behavioural Scoring Prediction in Revolving Credit Lines”.
    • Our PhD student Sahab Zandi presented the work with coautored with Kamesh, and cosupervised by Prof. María Óskarsdóttir, Prof. Christophe Mues, and Cristián. These last two works are part of the collaboration with one of the largest consumer banks in the world. Sahab’s presentation is titled “Modelling Credit Risk Contagion for SMEs over Supply Chains using Dynamic Multilayer Networks”.

The conference provided a great opportunity to meet and network with people in the field of credit risk from both academia and industry. We were honestly surprised and happy with the reception that we had from the conference attendants. We had many interesting talks and we look forward to what will come out of these chats!

We also had a blast having a reunion with some friends and colleagues after a while in Edinburgh!

We would like to thank the organizers, Professor Galina Andreeva and Professor Jonathan Crook from the Credit Research Centre at the University of Edinburgh, plus of course our collaborator Prof. Christophe Mues for hosting this wonderful conference. We look forward to attending the next one in 2025!

.

 



September 25, 2023by Cristian0

Now that the summer is over I was invited once again to the Weekend Business panel on CBC News. You can watch it below!

The TL;DW version is:

  • Latest inflation numbers: Not very good news as inflation seems to be supply-side, so it is much harder to control. Gas prices will also negatively affect the price of food even more for the next quarter at least. This means that interest rates will remain high for a while, possibly even into 2025. Also, deflation is not a bad thing if it is transitory and aimed at first necessity goods, as opposed to affecting consumption in the long run.
  • The UAW strike: Not really my topic, but my comment here was that the strike was expanded significantly and that can impact car prices in the future as it will now target in-demand cars. Also, some factories in Canada may be facing temporary work stoppages. 
  • Equifax report on the increase in lending application fraud: while this is a relatively minor issue, it mixes two different things. First, mortgage fraud is on the rise. Most of this type of fraud is misrepresentation of income, which may be considered a white lie by some borrowers (16% according to a relatively old survey), but it actually is fraud and can have serious consequences for borrowers. The second is auto and credit card fraud. This one is mostly done by criminals that steal identities. The recommendation here is clear: monitor your credit at least monthly and if you see anything that you don’t recognize, immediately contact your financial institution.

I’m on next on October 14 and November 4.



August 15, 2023by Cristian0

I had a great time presenting a keynote and a paper at the SIGKDD 2023, one of the elite conference in computer science. In my personal opinion, the KDD is the top applied data science conference, as NeurIPS is a bit too theoretical, while the KDD is a bit more integrative. Lots of papers this year in network science and causal learning, which was encouraging when evaluating the current research lines of the group.

I presented two works in the Machine Learning in Finance workshop of the conference:

  • The keynote “Leveraging Deep Learning for Multimodal Data Analysis in Credit Risk Assessment“, where I summarized the latest work of the lab in using multimodal data for the analysis of credit risk in midcaps and retail lending. I presented results of our latest preprints (paper on midcapspaper on mortgages) and preliminary results on using LiDAR for mortgage analysis and social network analysis for credit risk modelling. I shared the stage again with three other keynotes from Bloomberg and Blackrock, the same groups that presented in the Columbia-Bloomberg seminar in May we also presented in, and with Srijan Kumar from Georgiatech. Srijan was keynote in the NeurIPS workshop we presented our paper on influencer detection (NeurIPS paper, journal preprint). The machine learning in finance world seems to be pretty small!
  • The paper “Graph Attention Networks for Portfolio Optimisation: Empirical Evidence for Mid-Caps” by our PhD student Kamesh Korangi. Kamesh couldn’t attend as the US visas are taking forever. In this talk I showed the preliminary results of our work on using GATs for optimizing portfolios. We are really excited about this work! I can’t wait to show the world about in the near future. Stand by for the preprint, it should be available in a few months. The presentation itself will be available in a few weeks, I’ll update this post when it is.

It was a fantastic experience to attend the KDD in person. Sadly, we weren’t able to do so in 2020 due to the pandemic, where we presented the preliminary results of our paper in default propagation across multilayer networks (KDD paper, YouTube video with the presentation at CORS 2021, extended journal paper). It was great to be able to present now and share with so many top researchers.

The conference was in Long Beach, so I also got to have some great weather.

Cristian in front of the sunny Long Beach Convention Center

The acceptance rate of the conference was higher than previous years, around 20%. However, the MLF workshop was even more selective with only around 10% of the papers being selected for spotlight talks! It was great to be in such an exclusive group.

Slide with the acceptance rate of the KDD conference per areas. Finance is 22%.

Also, it was great to see so many Latin Americans there! We had a few meetings and even some went salsa dancing. We were very pleased to also meet with Ricardo Baeza-Yates, a legend in the field.

Latin Americans sharing a lunch at the KDD.

Overall, it was a great experience. Hopefully we’ll be able to attend to KDD 2024 in Barcelona!



July 18, 2023by Cristian0

Another interest rate hike, another hit to Canadians to keep inflation in check, another time journalists reach out to the BAL for insights. I was on CTV national speaking about it. You can see the interview in this link. What’s cool about this link (active for 30 days) is that it also shows how many people viewed the interview. 3,520,000 persons. Wow, I’m amazed about the reach of these activities and humbled I get the chance to speak directly to so many Canadians. Thank you to everyone that tuned in and I hope I helped explain what’s going on!

The second coverage was at CTV London. This one did have a shareable link, and a piece of written news. The written news is in this link, and I’ve also embedded the interview below.

I had a bit of a slip that made the segment: what I wanted to say was that one of the factors within core inflation is service inflation, and that one hasn’t come down. Also, this round we had a surprisingly strong demand for goods. According to the BoC this is both due to savings from the pandemic that households are spending, and also because of very strong demand from the US for our goods.

The BoC is much more pessimistic about when they will control inflation, targeting now the second semester of 2025. This would come, however, with no recession. This is very uncertain though, as they themselves acknowledge. We’ll have to see.

In a more personal opinion, I believe the BoC is ok with a moderate recession as long as inflation comes back down, so they rather overdo it. Inflation expectations are really high both in consumers and businesses. These decisions are aimed at convincing everyone that they will keep hiking rates as long as necessary. I, for one, believe them.



Our research focuses on using reinforcement learning (RL) to address the credit limit modification problem for companies offering credit card products. This involves two main challenges: defining the RL problem for this specific task and training the RL agent without conducting online experiments with customers.

To define the RL problem, we consider the financial history of credit card holders and the expected losses due to defaults when deciding whether to increase or maintain their credit limits. The actions available are increasing the limit or keeping it the same. We calculate the reward function based on the expected profit, considering the revolving aspect of credit card usage. This differs from previous studies that overlooked this aspect in profit calculations.

To train the RL agent offline, we use a two-stage model to simulate the balance after taking an action. This involves selecting the balance type and predicting the balance amount using a regressor model. Through our experiments, we found that our trained Double-Q learning agent outperformed other strategies, including the one used by Rappi, a Latin American fintech company known for its delivery and commerce services that has also ventured into banking with its RappiCard credit card, and that was our collaborator in this research.

Our research contributes by providing a conceptual framework for applying RL to credit limit adjustments and emphasizes data-driven decision-making rather than relying solely on expert judgments. Furthermore, we discovered that incorporating additional predictors did not improve the performance of our simulator. This implies that fintech companies do not necessarily have an advantage over traditional banking institutions in this specific task.  Figure 1  provides an overview of the proposed methodology’s general workflow.

 

 

 

 

 

 

 

 

 

 

 

Figure 1: Methodology’s general workflow.

Link to the working paper: https://arxiv.org/abs/2306.15585



June 28, 2023by Daniel Abib0

By Mahsa Tavakoli @Bal:

Our research study was undertaken with the aim of enhancing the accuracy of predicting company credit ratings, a critical factor in evaluating their financial stability. Unlike previous studies that solely focused on structured data, such as numbers and figures, we recognized the significance of incorporating other, non-structured information. Thus, our primary objective was to evaluate the effectiveness of employing advanced deep learning models to merge both structured and unstructured data, particularly textual information. Through this approach, we sought to provide a more comprehensive analysis and improve the overall predictive capabilities of the models. In our quest for the optimal approach, we conducted thorough testing of various fusion strategies and deep learning models, including CNN, LSTM, GRU, and BERT. To our surprise, we discovered that a CNN-based model (Figure 2), which effectively amalgamated data from diverse sources, outperformed more intricate models. Leveraging this model enabled us to achieve highly precise credit rating predictions.

Furthermore, we delved into the contribution of different data types to these predictions. Textual data, such as insights shared by company managers, played a pivotal role, particularly during challenging periods like the COVID-19 pandemic. This underscored the significance of contextual information and managerial perspectives in accurately predicting credit ratings.

Additionally, our research encompassed a comparative analysis of ratings provided by various agencies. Moody’s credit ratings emerged as the frontrunner, surpassing those of other agencies like Standard & Poor’s and Fitch Ratings, especially in medium-term predictions.

Collectively, our research provides a comprehensive framework that empowers rating agencies and financial institutions to make well-informed decisions when assigning credit ratings. By incorporating a combination of structured and unstructured data and leveraging the most effective deep learning models, they can significantly enhance the precision of credit rating predictions, thereby augmenting their overall decision-making process.

Fig1: Blending Textual Managers’ Insights and Companies Numerical Data for Precise Credit Rating Predictions

Fig2: Architecture of the CNN ensemble for the best model, showing
the convolution and dropout layers with two streams of data that includes
text and numerical data (N1, N2, N3, N4).

Link to the working paper: https://arxiv.org/abs/2304.10740