*Join the TD Asset Management Team!*

### COMPANY PROFILE

TD Asset Management Inc. (TDAM) is a leading asset manager in Canada with an expanding global presence. TDAM offers an extensive history of innovative solutions designed to provide better risk-adjusted returns with a long track record in integrating public and private market capabilities.

**Industry **: Finance**Founded **: 1987

### PARTICIPATION

Are you interested in solving concrete industrial problems while developing a unique work experience? Fill in the participation form below. We will review your eligibility and provide you with the registration link later.

### PROBLEM DESCRIPTION

**Portfolio risk forecast**

In practice, portfolio managers use either the fundamental model or the statistical model, or a combination both, to model the volatility of a portfolio’s future performance.

- The
**fundamental model**specifies characteristics that influence the covariances of equity returns. For example, stocks in the same industry will have more correlated returns with each other than stocks in different industries. Financial leverage or the size of firms also seem to explain part of the common variation in returns. Using a list of these characteristics and their time series as well as historical stock returns, it is possible to estimate the covariance matrix of risk factor returns in order to calculate a security’s exposure to these factors. In addition, by aggregating them we are able to calculate the risk of any portfolio. - The
**statistical model**starts from a full covariance matrix. This has often been calculated with returns filtered by a “winsorization” process. A principal component analysis (PCA) identifies the main dimensions of the covariance matrix by ranking them by their importance but without identifying the factors to which they refer. The risk factors are inferred empirically.

Until now GPTD has built risk models according to these two types of modeling. Statistical models (which use less information) work well, especially when stock markets are less volatile but are less adequate when market volatility increases sharply. So far, little consensus exists on the optimal way to combine the fundamental model or the statistical model or on the possibility of constructing a third one. TDAM is looking at what would be the best way to forecast the risk of a portfolio that uses historical returns on stocks in a certain universe and the fundamentals of those stocks?

- Devise an algorithm to better predict risk using sophisticated quantitative methods.
- Find a better way to build a portfolio (long only and without leverage) with minimal volatility.

TD Asset Management will provide an anonymized dataset to generate the two types of risk models described above.

- 30 characteristics + stock returns
- 120 months x 3,000 shares

### TEAM

**René Garcia**

Full Professor, *Department of Economics*, Université de Montréal.

**Ruslan Goyenko**

Associate Professor of Finance – *Desautels Faculty of Management*, McGill University.

**Manuel Morales**

Associate Professor & Fin-ML Program director – *Départment of Mathematics & Statistics*, Université de Montréal.

**Jean Masson**

Managing Director, TD Asset Management.

**Jean-François Fortin **

Vice President, TD Asset Management.

**Rheia Khalaf**

Director, Collaborative Research & Partnerships, Fin-ML/IVADO.

**Avinash Srikanta Prasad**

Fin-ML CREATE program Postdoctoral Fellow, University of Waterloo.

**Yaroslav Babich**

UG in Engineering Science – Aerospace, University of Toronto.

**Kiran Deol**

UG in Computing Science, University of Alberta.

**Mohamed Gueye**MSc. in Statistics, Université de Montréal.

**Qi Guo**PhD. in Mathematics, University of Calgary.

**Thierry Jean**MSc. in Computational Medecine, Université de Montréal.

**Ehsan Rezaei**PhD. in Applied Mathematics, Polytechnique de Montréal.

**Javad Roustaei**MSc. in Financial Mathematics, Concordia University.

**Myles Sjogren**MSc. in Financial Mathematics, University of Calgary.

**Ernest Tafolong**MSc. in Data Science, HEC Montréal.

**Shiva Zokaee**MSc. in Mathematics & Industrial Engineering, Polytechnique de Montréal.