ISYE 6402: Time Series Analysis

Overview

In the 6402 Time Series course, learners will learn standard time series analysis topics such as modeling time series using regression analysis, univariate ARMA/ARIMA modelling, (G)ARCH modeling, Vector Autoregressive model along with forecasting, model identification, and diagnostics. Building on these fundamental time series modeling concepts, the last module of the course will also present the methodology and implementation of well-established machine learning (ML) forecasting systems including Meta’s Prophet , Linkedin’s Silverkite, and Uber’s Orbit, complemented by a brief introduction on Deep Learning approaches inspired by commonly used tools such as neural networks. The course material will be accompanied by a GitHub repository including all data examples and implementations used to illustrate the fundamentals of time series learned in the course.

Course Goals

By the end of this class, students will:

• Learn the widely used time series models such as univariate ARMA/ARIMA modelling, (G)ARCH modeling, and VAR model.
• Be given fundamental grounding in the use of some widely used tools, but much of the energy of the course is focus on individual investigation and learning.

This class is more about the opportunity for individual discovery than it is about mastering a fixed set of techniques.

This course is not foundational and does not count toward any specializations at present, but it can be counted as a free elective.