Machine Learning for Financial Modeling

Machine learning has been a major catalyst for financial decision making with big data. From credit scoring in the financial services industry, to investment models for portfolio and wealth management, to algorithmic trading and risk management. It is well known that machine learning is often used to make basic decisions, such as loan approvals, but the field has advanced substantially in the last few years to deliver a much broader set of capabilities. The goal of this short-course is to equip finance professions with a better understanding of which specific techniques in machine learning are shaping the finance industry.  In particular, we address common questions such as “Why has machine learning replaced statistical modeling?” and “how is machine learning used for portfolio selection?”.  The overall format of the course will be oriented towards finance professionals who are key decision makers in their organizations. Real world applications of machine learning using big data shall be demonstrated in areas such as trading, investment, and risk management.  A key value proposition of this workshop will be providing frameworks to understand how to most effectively apply machine learning to financial workflows across a broad range of business functions and roles, from data capture through to modeling, risk management and reporting.

Who is the course for? What will you learn?

• Financial analysts responsible for areas such as risk management, trading, investment management, retail and commercial banking, loan and payment services
• Financial managers seeking to improve their ability to evaluate the opportunity and competitive advantages of Machine Learning in finance
• Entrepreneurs and technical founders who are developing new technologies at the intersection of machine learning and finance

Instructors:

Igor Cialenco

Dr. Cialenco is a Full Professor in the Department of Applied Mathematics at Illinois Institute of Technology. He currently serves as Associate Chair and the Director of Graduate Studies supervising the graduate programs in the Department of Applied Mathematics at Illinois Tech.

His current research interests span across several areas of applied probability and statistics, including Mathematical Finance, Statistical Inference for Stochastic Processes, and Stochastic Control.

Dr. Cialenco is serving as Chair for SIAM Activity Group on Financial Mathematics and Engineering for the period 01/2022-12/2022, and previously served as Program Director. He is also a Managing Editor for the International Journal of Theoretical and Applied Finance (IJTAF), and on Editorial Boards of Applied Mathematical Finance, SIAM Journal on Financial Mathematics (SIFIN), Statistical Inference for Stochastic Processes (SISP), and International Journal of Financial Engineering (JFE).

During his academic career, he has taught and developed courses in Financial Engineering, Stochastic Analysis and Statistics at both graduate and undergraduate levels.

Dr. Cialenco holds a Ph.D. in Applied Mathematics, University of Southern California.

His awards include: College of Science Dean’s Excellence Award for Teaching, Illinois Tech, Fall 2015; College of Science and Letters Dean’s Excellence Award for Research and Scholarship, Illinois Tech 2011; Dissertation Fellowship from College of Letters, Arts and Sciences, USC; The First Prize of the Presidium of the Academy of Sciences of Moldova, 2000.

Matthew Dixon, Ph.D, FRM

Dr. Dixon began his career in structured credit trading at Lehman Brothers. He has consulted for numerous investment management, trading and financial technology firms in machine learning and risk analytics. He is the co-author of the 2020 textbook "Machine Learning in Finance: From Theory to Practice" and has written over 20 peer reviewed papers on machine learning and quantitative finance, is the recipient of an Illinois Tech innovation award and the College of Computing's Dean Award for Excellence in Research (Junior level), and his research has been funded by Intel, Dell, and the NSF in addition to being quoted in the Financial Times and Bloomberg Markets.

Dr. Dixon has recently co-authored the CFA course material on machine learning, serves on the CFA advisory committee for quantitative trading, and is deputy editor of the Journal of Machine Learning in Finance. He holds a PhD in Applied Math from Imperial College and has held visiting academic appointments at Stanford and UC Davis. His research focuses on applying concepts in computational and applied mathematics to financial modeling, especially in the area of investment management, algorithmic trading, and derivatives.

Course structure

This course will be comprised of 6 – 2 hour evening classes. Classes will be live, but online (supported by our LMS and Zoom). There will be about 1 hour of outside work in-between each class. The classes will be held once a week for six straight weeks.

Each of the classes will follow this format:

• 10 minutes: review work from previous week (except first week when we will do introductions)
• 1hr 15 minutes: lecture covering main concepts
• 30 minutes: guided lab sessions using Google Colab in which participants will work in small groups to complete an exercise in ML applied to financial data
• 5 minutes: Instructions for completing the next homework assignment

Participants are encouraged to review background materials in the starter package which include a Python primer.  Note that Python programming is not essential for successful completion of the course, but is encouraged. Laptops are recommended but not required. No special software or functionality is required.  Further materials and tools will be provided for use during and after the course.

Topics covered

• Understand the main theoretical concepts in machine learning particularly those relevant in financial modeling
• Formulate and formalize your business unit modeling problems into standard machine learning problems
• Understand how machine learning for finance can more broadly add value to your workflow, from data capture through to reporting
• Gain familiarity with the role of data scientists and how machine learning is implemented and operationalized
• Identify the risks and limitations of machine learning for various financial modeling applications
• Gain insight into the future of machine learning in the context of financial regulation, cybersecurity, and emerging financial technologies.

Unique elements of the class

• Hands-on financial data labs
• Simple and illuminating exercises on financial modeling with machine learning
• Thematic group-thinks around planning and troubleshooting for one or more applications of machine learning in your organization
• One-on-one consultations with the instructor.

Digital credential

Certificate of completion: Machine Learning and Finance, provided and endorsed by Illinois Tech

Timeline:

April 6, 2022 to April 21, 2022: Tuesdays and Thursdays 5:30-7:30 pm CT.

Fee:  $3,000 per person 

Discount is available for Illinois Tech alumni. Please email the Illinois Tech Office of Professional and Continuing Education at opce@iit.edu to get the promotion code.