Here you will find information about our past and ongoing projects, as well as opinions on current topics in Banking Analytics.

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:

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:

June 26, 2023by Cristian0

Always fun to be on the CBC News’ Weekend Business Panel. This week I was asked to talk about the price fixing fine on Canada Bread, Equifax’s reporting small businesses have significantly increased their credit card debt (and reduced loans), and the most livable cities ranking from The Economist.

With respect to the second point, in general it is not a good sign. It is not clear why businesses are using more revolving debt (no good reason though), but the reduction in traditional lending does reflect lower investment in the future. I think the pinch of inflation plus high cost of debt is being felt more widely already. The FT called it the “pain phase” earlier this week: the period where rates are high, but inflation still hasn’t come down.

See my thoughts below!

June 8, 2023by Cristian0

The Bank of Canada raised the interest rate once again, shocking a section of the market. I honestly expected this as the fundamentals aimed at it, with inflation still high, a tight labour market, the US still very aggressively raising rates, and the time it takes for people to renew their mortgages and take higher rates. Also, relative to inflation interest rates are still around historical averages.

It sadly does mean higher debt costs for everyone. This will also mean a slowdown in the medium term, but how big will this be (either a recession or not) is anyone’s guess. Canada has a safer banking system, so interest rate risks are significantly lower, giving more runway to the BoC for future rises.

CTV News London interviewed me about this yesterday. I speak around 6 minutes in.

May 29, 2023by Cristian0

I had the opportunity to be at CBC News‘ Power and Politics on Friday speaking about the debt ceiling. First time in a TV studio! Time went so fast I didn’t even mentioned anything about the specific impact on the stock and bonds markets of either a shutdown or a default. As there is a deal now, my second point on the specifics of the deal are more important. Any deal could impact Canada’s bottom line for years to come. So far, it seems like a general reduction in spending growth to no more than 1% yearly, rather than specific programs cut, we’ll know in the next few days. These are good news for Canada in general, at least much better than cuts that could threaten specific strategic industries.

The interview is below, I start at 29:18.

Extending the coverage, the Canadian Press interviewed me about it. The interview was then featured at The Toronto Star, here. Also, CIXXFM here in London took a bit of a different path, focusing more on the personal finance side of it (don’t panic!!). This interview can be read here.


May 20, 2023by Cristian0

I had the true honour of being invited by Prof. Ali Hirsa to present at this excellent workshop. The organizers review 1400 abstracts published during the year and select the ones that according to them reflect the most significant research at the intersection of ML and Finance. Our work with Kamesh Korangi and Christophe Mues, “A transformer-based model for default prediction in mid-cap corporate markets” [paper, ArXiV], was one of them!

Excellent roster of speakers, including people from MIT, Stanford, Blackrock, Morgan Stanley, and of course, the hosts Columbia and Bloomberg. Everything went amazing except that the IT team lost a few of my slides, but I think the audience did not mind very much. I look forward to keep engaged with such an excellent team moving forward. Here are a few pictures of the event.

Cristián on the stage before his presentation at the Alfred Lerner Hall

The presentation was at the amazing Alfred Lerner hall at Columbia University. 400 attendants from industry and academia were present.

The stage at the Alfred Lerner hall

April 24, 2023by Cristian0

Stock image of code of ethics

During 2022 I had the pleasure of participating on a series of workshops discussing the challenges in AI applied to financial institutions. I was part of a group of 30 professionals from industry and academia. The forum was organized by the Office of the Superintendent of Financial Institutions (OSFI), Canada’s prudential banking regulator. These discussions will inform the future regulation in the area that OSFI is targeting for release later in the year.

The report discusses the EDGE model for financial institutions: Ethics, Data, Governance, and Explainability. It aims to provide general guidelines to strike the right balance between regulation and innovation. I greatly enjoyed all discussions that led to this report, in my minor capacity as participant.

Give it a read in this link.

April 17, 2023by Cristian0

I was on the CBC panel again this weekend! This week we spoke about the BoC’s decision to keep the monetary policy rate steady, the Mercer report on Millennial renters needing 50% more upon retirement (not a fan of the study) and Amazon’s Bedrock & Titan, although my producer cut me off because we were running out of time. I had a lot more to say about AI!

What I didn’t say on Saturday: I believe we will end up in a three-tiered world: A first world of companies developing these models (having the technological capacities and data availability to properly train them). A second world of companies that can take outputs of these models, or available public models and fine-tune them over either private or public infrastructure (BloomberGPT for example and several research projects I am working on). And a third world of companies that will be technology takers and deploy these technologies either via live services (such as Amazon Bedrock) or via prepackaged assistants (such as LLM-powered Bing or Microsoft’s Copilot).

See the panel below.