Upcoming Seminar

Machine Learning and Credit Risk Analytics with MATLAB

Location:
Toronto, ON
Venue:
Toronto Marriott Downtown Eaton Centre Hotel
Date:
April 12, 2017
Time:
9:00 a.m. - 12:00 p.m.

Overview

Financial risk management is all about assessing, quantifying, and making decisions upon the potential for financial loss. As such, risk is an expansive field that often includes tasks that span calibration, simulation, pricing/valuation, sensitivity analysis, forecasting, model validation and transparency, and regulatory enforcement. Production systems and dashboards then aggregate results to generate on-demand customized reports or issues alerts in real-time. Additionally, scaling risk infrastructure can be challenging due to the need to work with big data and integrate rapidly with existing systems, all while meeting stringent performance criteria.

At the heart of many risk applications are machine learning techniques used for risk classification, credit scoring, time series forecasting, estimating default probabilities, and data mining. In order to meet the demands of a modern risk infrastructure, MATLAB provides you with a complete platform that takes you from initial prototype all the way to business critical production system.

You will learn how products such as the Risk Management Toolbox, Statistics and Machine Learning Toolbox, and MATLAB Production Server are ideal tools for building and scaling enterprise risk management systems. We will leverage advanced analytics, machine learning techniques, built-in methods to measure/forecast risk, and development tools in MATLAB to build applications quickly. Then we will explore how to take an agile risk management infrastructure and rapidly deploy it into enterprise system architectures.

Whether you specialize in risk management or are simply interested in building and deploying machine learning models, this seminar is ideal for you.

Highlights

  • Data management and integration with databases, live market data, and big data environments
  • Predictive modeling and using supervised machine learning techniques to build a credit rating engine
  • Computing credit migration and probabilities of default
  • Building custom credit scorecards for consumer risk using multivariate regression techniques
  • Using copula-based Monte-Carlo simulations to analyze credit portfolio risk
  • Powerful tools to take prototypes into production, creating scalable performant enterprise web services

Who Should Attend

  • Risk Analysts
  • Risk and Portfolio Managers
  • Quantitative Analysts
  • Analytical Researchers
  • Data Scientists, Engineers, and Architects
  • Business Intelligence Analysts

About the Presenter

Ian McKenna joined MathWorks in 2011 as an application engineer supporting the financial services industry. His focus is in computational finance with applications including risk management, portfolio optimization and asset allocation, time series forecasting, and instrument pricing. Prior to joining MathWorks he worked at the University of British Columbia developing simulation code used in industry for heat treatment of steel alloys. Ian holds a Ph.D. from Northwestern University and a B.S. from the University of Florida in materials science and engineering with a minor in business administration.