Market data
Download and clean ten years of stock prices in Python and compute returns and correlations.
Developers or data scientists moving into finance.
Python, portfolio construction and machine learning for asset management, then supervised and reinforcement learning in finance.
Skill labels as listed on Coursera.
Stated prerequisites: No prerequisites; designed as an on-ramp to programming
| Course | Level | Length | Rating (reviews) |
|---|---|---|---|
| Programming for Everybody (Getting Started with Python) | Beginner | 17 h | 4.8 (233,775) |
| Python Data Structures | Beginner | 20 h | 4.9 (97,365) |
| Using Python to Access Web Data | Beginner | 19 h | 4.8 (44,591) |
| Using Databases with Python | Beginner | 14 h | 4.8 (21,659) |
| Capstone: Retrieving, Processing, and Visualizing Data with Python | Beginner | 9 h | 4.7 (14,483) |
Stated prerequisites: No prior experience required
| Course | Level | Length | Rating (reviews) |
|---|---|---|---|
| Introduction to Portfolio Construction and Analysis with Python | — | 25 h | 4.8 (1,477) |
| Advanced Portfolio Construction and Analysis with Python | Intermediate | 12 h | 4.7 (514) |
| Python and Machine Learning for Asset Management | Intermediate | 16 h | 3.1 (333) |
| Python and Machine-Learning for Asset Management with Alternative Data Sets | Intermediate | 21 h | 4.4 (238) |
Stated prerequisites: Basic math, probability and statistics, Python
| Course | Level | Length | Rating (reviews) |
|---|---|---|---|
| Guided Tour of Machine Learning in Finance | Intermediate | 24 h | 3.8 (684) |
| Fundamentals of Machine Learning in Finance | Intermediate | 18 h | 3.7 (345) |
| Reinforcement Learning in Finance | Advanced | 17 h | 3.6 (134) |
| Overview of Advanced Methods of Reinforcement Learning in Finance | Advanced | 13 h | 3.8 (86) |
This path takes 225 hours, about 5 months at 10 hours a week. A Coursera Plus subscription gives access to most of its courses during that time.
Download and clean ten years of stock prices in Python and compute returns and correlations.
Build a sentiment indicator from news headlines and test its link with returns.
Train a reinforcement learning agent on a simulated market and compare it with a simple strategy.