Syllabus for DSI-601
Predictive Analytics 1: Python
In this online course, “Predictive Analytics 1—Machine Learning Tools—with Python,” you will be introduced to the basic concepts in predictive analytics, also called predictive modeling, which is the most prevalent form of data mining. This course covers the two core paradigms that account for most business applications of predictive modeling: classification and prediction. In both cases, predictive modeling takes data where a variable of interest (a target variable) is known and develops a model that relates this variable to a series of predictor variables, also called features. In classification, the target variable is categorical ("purchased something" vs. "has not purchased anything"). In prediction, the target variable is continuous ("dollars spent"). You will learn how to explore and visualize the data, to get a preliminary idea of what variables are important and how they relate to one another. Four machine learning techniques will be used: k-nearest neighbors, classification and regression trees (CART), and Bayesian classifiers. Then you will learn how to combine different models to obtain results that are better than any the individual models produce on their own. The course will also cover the use of partitioning to divide the data into training data (data used to build a model), validation data (data used to assess the performance of different models, or, in some cases, to fine tune the model), and test data (data used to predict the performance of the final model).
After completing this course, you should be able to:
CO 1 Visualize and explore data to better understand relationships among variables.
CO 2 Organize the predictive modeling task and data flow.
CO 3 Develop machine learning models with the KNN, Naive Bayes and CART algorithms using Python scikit-learn.
CO 4 Assess the performance of these models with holdout data.
CO 5 Apply predictive models to generate predictions for new data.
You will need the following materials to complete your coursework. Some course materials may be free, open source, or available from other providers. You can access free or open-source materials by clicking the links provided below or in the module details documents. To purchase course materials, please visit the University's textbook supplier.
Predictive Analytics 1: Python is a three-credit, online course consisting of six modules. Modules include an overview, topics, learning objectives, study materials, and activities. Module titles are listed below.
For your formal work in the course, you are required to participate in online discussion forums, complete written assignments, and complete a final project. See below for details.
Consult the Course Calendar for due dates.
One or more of your course activities may utilize a tool designed to promote original work and evaluate your submissions for plagiarism. More information about this tool is available in About SafeAssign.
In addition to an ungraded Introductions Forum, you are required to participate in four graded online class discussions.
Communication with your mentor and among fellow students is a critical component of online learning. Participation in online class discussions involves two distinct activities: an initial response to a discussion question and at least two subsequent comments on classmates' responses.
All of these responses must be substantial. Meaningful participation is relevant to the content, adds value, and advances the discussion. Comments such as "I agree" and "ditto" are not considered value-adding participation. Therefore, when you agree or disagree with a classmate or your mentor, state and support your position.
You will be evaluated on the quality and quantity of your participation, including your use of relevant course information to support your point of view, and your awareness of and responses to the postings of your classmates. Remember, these are discussions: responses and comments should be properly proofread and edited, mature, and respectful.
You are required to complete four assignments. The written assignments are on a variety of topics associated with the course modules.
You are required to complete a final project that incorporates concepts and skills from throughout the course. There will be several weeks leading up to the submission of the final project where you are expected to work on the project and receive feedback from your mentor.
Assemble the data needed to work on the project, formulate a strategy for completing the project, make sure you understand the questions, and address questions to your mentor. The last point is essential—even if you think you understand exactly how you are to proceed, you need to outline your strategy with your mentor.
Prepare an initial submission with your analysis that is substantially complete. You may raise additional questions with your mentor at this point to seek guidance. You must in any case share your work with your mentor.
Incorporate guidance and complete final submission. Taking the guidance from your mentor into account, prepare and submit your final submission.
Your grade in the course will be determined as follows:
All activities will receive a numerical grade of 0–100. You will receive a score of 0 for any work not submitted. Your final grade in the course will be a letter grade. Letter grade equivalents for numerical grades are as follows:
A | = | 93–100 | B | = | 83–87 | |
A– | = | 90–92 | C | = | 73–82 | |
B+ | = | 88–89 | F | = | Below 73 |
To receive credit for the course, you must earn a letter grade of C or higher on the weighted average of all assigned course work (e.g., assignments, discussion postings, projects). Graduate students must maintain a B average overall to remain in good academic standing.
To succeed in this course, take the following first steps:
Consider the following study tips for success:
To ensure success in all your academic endeavors and coursework at Thomas Edison State University, familiarize yourself with all administrative and academic policies including those related to academic integrity, course late submissions, course extensions, and grading policies.
For more, see:
Copyright © 2019 by Thomas Edison State University. All rights reserved.
