开源软件名称（OpenSource Name）：

开源软件地址(OpenSource Url)：

开源编程语言(OpenSource Language)：

开源软件介绍(OpenSource Introduction)：

Introduction to Machine Learning for Good

How can we use data for social impact?

Data is powerful. We believe that anyone can harness that power for change.

In this introductory course, students will learn the foundational theory and the necessary coding skills to translate data into actionable insights. Students will learn the latest machine learning tools and algorithms.

Data science is a highly interdisciplinary practice: demanding critical thinking, understanding of statistics, and technical coding ability. Irresponsible application of powerful algorithms or an inadequate exploration of underlying assumptions can lead to spurious results. In this course, we emphasize the fundamentals of proper data science and expose students to what is possible using sophisticated machine learning methods.

Each of the modules is hands-on, project-based, using real world data from KIVA, a non-profit that connects people through lending to alleviate poverty.

Who We Are

Delta Analytics is a 501(c)3 San Francisco Bay Area non-profit dedicated to bringing rigorous data science to problem-solving, effecting change in nonprofits and the public sector, and making data science an accessible and democratic resource for anyone with the same mission.

Overview

Topics covered in this course include: data cleaning, supervised machine learning, and unsupervised machine learning.

The slides that cover the theory of the topic are available here. We present theory alongside real-life data science examples will open doors to novices and professionals alike to harness the power of data for good.

Weebly (our website host) has blocked traffic to certain countries. We have submitted numerous complaints, and apologize to students for the inconvenience caused. Until then, you can access pdf of all course slides below.

Module 1 - Introduction to Machine Learning

Module 2 - Machine learning deep dive

Module 3 - Linear Regression

Module 4 - Model Selection and Evaluation

Module 5 - Decision Trees

Module 6 - Ensemble Algorithms

Module 7 - Unsupervised Algorithms

Module 8 - Natural Language Processing Pt. 1

Module 9 - Natural Language Processing Pt. 2

Course outcomes

By the end of the course, students will be able to:

1. Explain the fundamental statistical and machine learning algorithms that underlying common data science methods.
2. Write code to clean, process, analyze, and visualize real-world data.
3. Be able to communicate with other data scientists using technical terms.

Our students

The course is intended for any and all individuals interested in harnessing data towards solving problems in their communities. Minimal prior coding or mathematical/statistical experience is expected. Computer proficiency is necessary.

Our teachers

Delta Teaching Fellows are all data professionals working in the San Francisco Bay Area. All of our time is donated for free to build out a curriculum that makes machine learning tools and knowledge more accessible to communities around the world. You can learn more about our team here.