Second Edition

Deloitte/BT Quant Competition 2023

Summary of the contest
Second Edition, academic contest open to multiple Master programs in Romania (1st and 2nd year students), in
the area of Data Science / Machine Learning / Econometrics, including but not limited to:
➢ ASE Cibernetica – all masters
➢ Universitatea Bucuresti – Master Data Science
Master Artificial Intelligence
Master Probabilitati si Statistica in Finante
➢ Univ Babes-Bolyai Cluj – Master Econometrie si Statistica Aplicata
➢ Univ Babes-Bolyai Cluj – Master Data Science for Industry and Society
➢ Univ Babes-Bolyai Cluj – Master Analiza Datelor Complexe
➢ Univ A.I. Cuza Iasi – Master Data Mining (Cibernetica si Statistica)
➢ Universitatea de Vest Timisoara – Master Big Data (data science, analytics and technologies)

Students are given a real-world professional assignment and will be assessed jointly by their Professor and
by a jury of Deloitte & BT professionals.

The outcome of the program for students include financial awards for top 3 participants (below the net
amounts), as well as multiple invitations for collaboration (hiring) in the Risk Advisory team at Deloitte and at
Banca Transilvania:
1st place: €2000
2nd place: €1500
3rd place: €1000
2
Timeline
PROBABILITY OF DEFAULT MODELLING
USING MACROECONOMIC FACTORS

Timeline Overview Outcome

✓ Work in teams of 2 students. ✓ Best teams will be selected by
Semi-finals Start: 20 April ✓ Develop a forward looking Deloitte/BT in order to go to the
End: 30 May probability of default model next stage.
using macroeconomic data ✓ Finalists will be announced during
✓ Use SAS, R, Python, Other. the week of 19-25 June.

Timeline Overview Outcome

✓ Work individually. ✓ The results will be presented in a
Start: 26 June ✓ Address a task that will be session, in front of a jury of
Finals End: 16 July communicated after the semi- Deloitte/BT professionals.
finals. ✓ Winners (top 3) of the program
✓ Use SAS, R or Python, Other. will be awarded a financial prize.

3
Main objectives of the program

Corporate Social Recruiting

Responsibility ✓ This program is an
✓ Give back to future opportunity for
generations. participating entities
✓ Participate in the training (Deloitte and BT) to
of students. connect to a new talent
✓ Provide students a solid pool and to assess the
career path. skills of future hires.

Market visibility
Partnership with
✓ Create interest in our
Universities industry and in what we
✓ Corporate investment in do.
education. ✓ Encourage other potential
✓ Present real-world partners (Banks) to join
assignments in an academic the program during future
setting. sessions.

4
For students: why Deloitte

Machine International Career Path Make an impact

Learning projects that matters

• Apply cutting edge • The Romanian • At Deloitte we offer a • Deloitte is not only
machine learning branch is very well clear career path, leading the
methods in Finance. integrated into the where you will be profession but
wider followed by a reinventing it for the
• Gain solid knowledge
Central/Eastern- mentor and given a future. We’re also
of credit risk in
Europe Deloitte transparent roadmap committed to
finance, as well as
hub. with career creating
financial regulations.
milestones and opportunity and
• Most of our projects
• Apply programming objectives. leading the way.
are international
tools such as SAS, R
assignments, • We look out for one • We approach our
and Python.
where we collaborate another and prioritize work with a
with Deloitte teams respect, fairness, collaborative
and Client teams development, and mindset, teaming
from other countries: well-being. across businesses,
UK, Italy, Slovakia, geographies, and
Denmark, Lithuania, skill sets to deliver
Bulgaria, Slovenia, tangible,
Albania, Kazakhstan, measurable,
etc. attributable
impact.

5
For students: why Banca Transilvania

Applied Work with the Grow with us Continuous

knowledge best development

• Apply the statistic, • Take the opportunity • Join a team of • Be part of the risk
econometric and to work with the professionals which mitigation process
machine learning largest and one of act based on and help prevent
techniques on real data. the most dynamic principles such as significant
banks on the knowledge unexpected losses.
Romanian market. sharing, respect,
• Use some of the most fairness.
popular programming • Continuously develop
environments such as • Face the challenges your skills and
SAS or R. of the financial • Unite forces within a knowledge, both
sector and find powerful team in quantitative and
optimal solutions order to obtain the financial.
to them. best outcome.

6
Assignment - Overview and Dependent variable calculation

▪ Context: Time series models are often used in the estimation of forward-looking component of
probability of default models used in quantification of losses according to the IFRS 9 standard.
Their role is very important in capturing the effect of macroeconomic factors and other exogenous
risk drivers that may affect the level of credit risk of a loan portfolio. In order to build such a
model a bank usually calculates the observed PD or the so-called observed default rate (DR). The
outcome of the DR is 12 months, this is equivalent to a PD for the next 12 months.
▪ The assignment of this contest will challenge you to make a model that is suitable to quantify the
forward-looking component, you will start with the calculation of the target/dependent variable and
potentially end with producing the output of such a model, the forecasts.
▪ Database: information at client level. It will be provided prior to the start date, via a Deloitte
Shared Server. This will be the source of calculation for the dependent risk driver.
▪ Macroeconomic info: The independent risk drivers should be of macroeconomic nature, it is public
information. The participants are expected to gather these risk drivers from the internet (ex:
Eurostat, INSSE, BNR, World Bank etc.)
▪ Main assignment (“the semi-finals”):
➢ The model can be developed in SAS/R/Python/Eviews/SPSS/Excel/etc. The exercise will take
place in teams of 2 students and has two parts:
1) Calculate the dependent variable to be modeled from the Database: observed default rate
with outcome of 12 months.
• At a given reporting date the observed default rate is calculated as: number of defaulted
clients in the next 12 months divided by the total number of performing clients at
reporting date. For example, if there are 150 performing (non-default) clients in
December 2021 (e.g. a reporting date) out of which 30 have at least one default event
during Jan-Dec2022, then the observed default rate at December 2021 is 30/150=20%.

7
Assignment – Time series model and Forecasts

2) Develop a time-series statistical model for the estimation of the default rate using macroeconomic risk drivers. The dependent
variable is the observed default rate from point 1). You can identify and download drivers from INSSE, BNR, Eurostat, etc.
• Potential models: linear regression, autoregressive (AR), autoregressive moving average (ARMA), autoregressive with
distributed lags (ARDL), models to address seasonality endogenously (e.g. SARIMAX), random forest, neural networks, RNN,
LSTM, etc.
o Assess model performance through specific validation tests: p-values, R-squared, relevant business sign of macro drivers
(e.g. negative GDP sign), best linear unbiased estimator BLUE tests (no collinearity, stationarity of drivers,
homoscedasticity, no autocorrelation, normality of errors, linear functional form). If BLUE tests fail, we expect an
explanation for the failure, it is not necessary that all BLUE tests are passed. For non-linear models, apply BLUE tests
where appropriate and discuss, and also apply relevant techniques for model explainability.
o Bonus points: (1) generate a second “alternative” model using a different modeling technique (e.g. if the main model is a
linear regression, an alternative model can be AR), (2) model with more than 2 relevant macroeconomic drivers, (3)
obtaining at least a 70% R-squared or equivalent with all validation tests accounted for on linear regression (4) usage of
transformed risk drivers (e.g. LAGs, differences, logs, etc. and determining their optimal combination in the model); (5)
conduct scenario analysis to study the effect of shocks on predicted default rates, determine an appropriate size of the
shock and provide economic interpretations;
o Prepare model documentation (minimum 5 slides in PowerPoint).
NOTE: You do not need to apply all modelling techniques or use all types of drivers. You are free to choose one or more from the
requirements above. Apply the relevant statistical tests, show your work and ensure it is reproducible.
➢ Additional assignment (“the finals”): will be communicated to qualified teams. The work in the finals will be done individually by each
student.

8
Evaluation
The analyses will be evaluated by a jury consisting of Deloitte and Banca Transilvania professionals.
Different criteria will be evaluated:

Model Quant bonus points Quality of deliverables

▪ Correctness of the observed default ▪ 5%: Alternative model 1. Presentation: comprehensive
rate calculation presentation of steps and conclusions
▪ 10%: More than 2 independent risk (PPT and analytical results);
▪ Relevant value for R square, > 40%. drivers
2. Technical implementation: clean,
▪ Validation tests outcome ▪ 10%: Getting very good R2 and functional and efficient codes that a
validation outcome on linear regression third party can rerun to obtain the
▪ Correctness of the forecasts calculated
same results.
with the model ▪ 10%: Usage of transformed
independent risk drivers

▪ 10%: Effect of shocks

➢ Objective measure ➢ Semi-objective measure ➢ Subjective measure

25% 45% 30%

9
Inscriptions

▪ For inscriptions, please send to ppetroiu@deloittece.com one e-mail per team with the table below filled for
the 2 team members:

Team member 1 Team member 2

First name
Last name
Email address
University
Master

▪ Inscriptions will be open during the interval 1 – 19 April.

▪ The database and model assignment will be made available through a dedicated server (“the SharePoint”):
https://deloitteconnect.deloitte.com/project/69-23135/content/documents

• Deloitte Project Manager for all questions: ostoica@deloittece.com

• Banca Transilvania Project Manager for all questions: andrei.rusu@btrl.ro

10
Submission of assignment results

▪ Team and individual assignment materials will be delivered to the jury through the SharePoint.
▪ For the first stage (the semi-finals), each team of 2 students will receive a Sharepoint of the team, where
all results will need to be uploaded before the deadline. Each team will have access only to its allocated
sharepoint.
▪ All results need to be submitted in English and will need to include:
➢ Programming codes used to generate the results and that a member of the Jury could rerun to check
consistency.
➢ Analytical files (i.e. excel files) presenting each step of the modeling project.
➢ Documentation (i.e. PPT of minimum 5 slides) summarizing model results.

11
Deloitte refers to one or more of Deloitte Touche Tohmatsu Limited, a UK private company limited by guarantee (“DTTL” ), its network of member firms,
and their related entities. DTTL and each of its member firms are legally separate and independent entities. DTTL (also referred to as "Deloitte Global")
does not provide services to clients. Please see www.deloitte.com/ro/about to learn more about our global network of member firms.

© 2023 For information, contact Deloitte Central Europe

Banca Transilvania is the largest bank in Romania and the main financer of the economy, covering all the client segments and business lines within the
financial sector. With a story dating back almost 30 years, BT now has a market share of over 19%, 3.4 million clients, more than 9,000 employees, online
banking solutions and 500 units in 180 cities. It is the only Romanian banking brand that is part of the Brand Finance Banking 500 (2022). Driven by
more than just baking, BT wants to have a positive impact in Romania, both for the people and for the business and the environment.