CME 240: Statistical and Machine Learning Approaches to Problems in Investment Management (MS&E 445)
This course will approach a variety of problems in investment management, using statistical and machine learning tools to model forecasting problems in the evolution of security prices. Through a combination of lectures and projects, we will investigate pricing and risk models ranging from individual securities up through asset classes. Occasional guest lecturers will present problems they currently face in their day to day work. Prerequisites: Basic background in Probability (e.g.:
CME 106) and Mathematical Finance (e.g.:
MATH 238), and some facility programming in R and/or Python.
Terms: Spr

Units: 3

Grading: Letter or Credit/No Credit
Instructors:
Evnine, J. (PI)
CME 241: Reinforcement Learning for Stochastic Control Problems in Finance (MS&E 346)
This course will explore a few problems in Mathematical Finance through the lens of Stochastic Control such as Portfolio Management, Optimal Exercise of Derivatives, Order Execution, Personal Finance. For each of these problems, we formulate a suitable Markov Decision Process (MDP), develop Dynamic Programming (DP) solutions, and explore Reinforcement Learning (RL) algorithms. The course emphasizes the theory of DP/RL as well as modeling the practical nuances of these finance problems, and strengthening the understanding through plenty of coding exercises of the methods. Prerequisites: basic background in Probability (eg:
CME 106) and Mathematical Finance (eg:
MATH 238), and some experience coding in Python; Dynamic Programming or Reinforcement Learning experience not required.
Terms: Win

Units: 3

Grading: Letter or Credit/No Credit
Instructors:
Rao, A. (PI)
;
Gu, J. (TA)
MATH 238: Mathematical Finance (STATS 250)
Stochastic models of financial markets. Forward and futures contracts. European options and equivalent martingale measures. Hedging strategies and management of risk. Term structure models and interest rate derivatives. Optimal stopping and American options. Corequisites:
MATH 236 and 227 or equivalent.
Terms: Win

Units: 3

Grading: Letter or Credit/No Credit
Instructors:
Papanicolaou, G. (PI)
MS&E 346: Reinforcement Learning for Stochastic Control Problems in Finance (CME 241)
This course will explore a few problems in Mathematical Finance through the lens of Stochastic Control such as Portfolio Management, Optimal Exercise of Derivatives, Order Execution, Personal Finance. For each of these problems, we formulate a suitable Markov Decision Process (MDP), develop Dynamic Programming (DP) solutions, and explore Reinforcement Learning (RL) algorithms. The course emphasizes the theory of DP/RL as well as modeling the practical nuances of these finance problems, and strengthening the understanding through plenty of coding exercises of the methods. Prerequisites: basic background in Probability (eg:
CME 106) and Mathematical Finance (eg:
MATH 238), and some experience coding in Python; Dynamic Programming or Reinforcement Learning experience not required.
Terms: Win

Units: 3

Grading: Letter or Credit/No Credit
Instructors:
Rao, A. (PI)
;
Gu, J. (TA)
MS&E 445: Statistical and Machine Learning Approaches to Problems in Investment Management (CME 240)
This course will approach a variety of problems in investment management, using statistical and machine learning tools to model forecasting problems in the evolution of security prices. Through a combination of lectures and projects, we will investigate pricing and risk models ranging from individual securities up through asset classes. Occasional guest lecturers will present problems they currently face in their day to day work. Prerequisites: Basic background in Probability (e.g.:
CME 106) and Mathematical Finance (e.g.:
MATH 238), and some facility programming in R and/or Python.
Terms: Spr

Units: 3

Grading: Letter or Credit/No Credit
Instructors:
Evnine, J. (PI)
Filter Results: