IS517: Methods for Data Science

Course Overview

A dramatic increase in computing power has enabled new areas of data science to develop in statistical modeling and analysis. These areas cover predictive and descriptive learning and bridge between ideas and theory in statistics, computer science, and artificial intelligence. We will cover methods including predictive learning: estimating models from data to predict future outcomes. Regression topics include linear regression with recent advances using large numbers of variables, smoothing techniques, additive models, and local regression. Classification topics include linear regression, regularization, logistics regression, discriminant analysis, splines, support vector machines, generalized additive models, naive Bayes, mixture models and nearest neighbor methods as time permits. We situate the course components in the "data science lifecycle" as part of the larger set of practices in the discovery and communication of scientific findings.

The course moves quickly and includes hands-on computing exercises using Python and other relevant languages.

Regression Classification Regularization SVMs Unsupervised Learning Deep Learning LLMs

Learning Objectives

Gain broad exposure to core data science methods through lectures and discussion.
Develop working proficiency through hands-on exercises and computational practice.
Identify opportunities to apply course concepts in new settings through independent exploration and a course project.

Schedule

Week	Topic	Readings
1	Syllabus + Data Science Intro	—
2	Classification	ISL Ch. 4, PML Ch. 3
3	Linear Regression	ISL Ch. 3, PML Ch. 10
4	Resampling	ISL Ch. 5, PML Chs. 4 and 6
5	Tree-Based Methods	ISL Ch. 8, PML Ch. 3
6	Support Vector Machines	ISL Ch. 9, PML Ch. 3
7	Non-Linear Models for Regression	ISL Ch. 7, PML Ch. 10
8	Project Proposal + Slides Due / Proposal Presentations	—
9	Unsupervised Learning 1	ISL Ch. 10, PML Chs. 4 and 5
10	Unsupervised Learning 2	ISL Ch. 10, PML Ch. 5
11	Deep Learning and LLMs	PML Chs. 12 and 13
12	Final Presentation Slides Due / Final Project Presentations	—
13	Final Project Presentations	—
14	Final Project Report Due	—

Instructor Information

Instructor

Yaoyao Liu

Office

Room 5125, 614 E. Daniel St.

lyy@illinois.edu

Office Hours

By appointment

Prerequisites

LIS542 Data, Stat, Info, or equivalent (such as STAT100, CS361, or ECON202)
LIS490IDS / CS398ID / STAT490 or CS101 or equivalent; or instructor consent
Linear algebra recommended at the level of MATH125
Calculus recommended at the level of MATH220

Textbooks

Introduction to Statistical Learning: with Applications in Python (ISL), by Gareth James, Daniela Witten, Trevor Hastie, Robert Tibshirani, and Jonathan Taylor
Python Machine Learning: Machine Learning and Deep Learning with Python, scikit-learn, and TensorFlow 2 (PML), by Sebastian Raschka and Vahid Mirjalili

Assessment

Component	Weight
Home assignments	40%
Class participation	10%
Project proposal	5%
Project proposal presentation	5%
Final project report	30%
Final project presentation	10%

Quiz policy: There will be nine in-class quizzes scheduled across the semester. The overall quiz grade is based on the best 5 out of 9.

Policies at a Glance

Late Work

Assignments may be accepted late for up to 80% of points until the end of Week 15. In-class quizzes, exams, and the project are not accepted late without prior approval.

Project

Group project with ideally one or two students per group, including a proposal, a presentation, and a final report.

Homework Platform

Homework and practices are mainly based on PrairieLearn.