Machine Learning Capstone

Go to Course: https://www.coursera.org/learn/machine-learning-capstone

Introduction

## Course Review: Machine Learning Capstone on Coursera ### Overview The *Machine Learning Capstone* course on Coursera offers an innovative opportunity for learners to apply their knowledge in real-world scenarios. Designed for those who have completed prior courses in machine learning and data science, this capstone is an ideal platform to consolidate your understanding and showcase your skills. Utilizing Python-based libraries such as Pandas, scikit-learn, and TensorFlow/Keras, the course focuses on building a course recommender system along with analyzing related datasets. This hands-on project not only enhances your technical competencies but also empowers you to create actionable insights in a practical context. ### What You'll Learn Throughout the course, participants will engage with various concepts and techniques central to machine learning, including: - Building a course recommender system. - Performing exploratory data analysis and feature engineering. - Calculating cosine similarity and creating similarity matrices. - Applying KNN, PCA, and collaborative filtering techniques. - Leveraging deep learning for rating predictions. Each module is carefully curated to ensure a comprehensive learning experience that transitions from basic to advanced techniques in machine learning. ### Syllabus Breakdown #### Capstone Overview The introductory module sets the tone for the course, providing a clear understanding of recommender systems and an overview of the capstone project. Participants receive an IBM Cloud feature code, which is essential for setting up an IBM Watson Studio account, an invaluable tool for data science projects. #### Exploratory Data Analysis and Feature Engineering The second module dives into exploratory data analysis (EDA) where you will analyze course-related datasets. The hands-on labs empower you to extract a “bag of words” from course titles and descriptions, which is foundational for understanding textual data. The module culminates with the application of cosine similarity measurements to assess course similarities. #### Unsupervised-Learning Based Recommender System In the third module, learners will construct three different recommendation systems employing various methods. From generating interest scores based on user profiles to implementing clustering algorithms using K-means and PCA, this section solidifies your understanding of unsupervised learning. Additionally, collaborative filtering techniques are introduced to predict user preferences based on similar users' interactions. #### Supervised-Learning Based Recommender Systems The fourth module transitions into supervised learning where you will utilize neural networks to predict course ratings. This section is particularly insightful as it combines regression analysis with classification models, allowing students to explore different methodologies in predicting user interactions with courses. #### Share and Present Your Recommender Systems What's unique about this course is the inclusion of a module dedicated to presenting your findings and recommendations. By utilizing Streamlit, you’ll create a web application that showcases your recommender systems, enhancing your ability to communicate complex data-driven insights. #### Final Submission In the final module, students complete the course by submitting their lab screenshots and peer reviewing a colleague's work. This critique process encourages collaborative learning and further enhances your analytical skills by assessing others' approaches. ### Recommendation The *Machine Learning Capstone* course is highly recommended for those looking to transition from theoretical knowledge to practical applications in data science and machine learning. It is particularly well-suited for: 1. **Advanced Learners**: If you have a background in machine learning concepts, this capstone will help you refine your skills. 2. **Job Seekers**: The hands-on projects provide a portfolio piece that can be critical when showcasing your abilities to potential employers. 3. **Data Enthusiasts**: If you're passionate about data and enjoy solving real-world problems, this course allows you to apply your creativity with machine learning techniques. In conclusion, the *Machine Learning Capstone* course on Coursera is a comprehensive and engaging program that encourages learners to apply theoretical knowledge in a practical, collaborative environment. Whether you're looking to enhance your resume, pivot into a new career, or solidify your understanding of machine learning, this course offers the resources and mentorship needed to succeed. Get ready to dive into the exciting world of recommender systems and make your mark in the field of data science!

Syllabus

Capstone Overview

In this module, you will be introduced to the idea of recommender systems in the first video. All labs in subsequent modules are based on this concept. You will also be provided with an overview of the capstone project. In the last two exercises, you will obtain an IBM Cloud feature code and use that code to create an IBM Watson Studio account.

In module 2, you will perform exploratory data analysis to find preliminary insights such as data patterns. You will also use it to check assumptions with the help of summary statistics and graphical representations of online course-related data sets such as course titles, course genres, and course enrollments. Next, you will extract a word-count vector called a “bag of words” (BoW) from course titles and descriptions. The BoW feature is probably the simplest but most effective feature characterizing textual data. It is widely used in many textual machine learning tasks. Finally, you will apply the cosine similarity measurement to calculate the course similarity using the extracted BoW feature vectors.

In module 3, you will create three course recommendation systems using different methods. In lab 1, you will create a course recommendation system based on user profile and course genre matrices by computing an interest score for each course and recommend the courses with the highest interest scores. In the second lab, you will generate a course similarity matrix to create the recommendation system. In the third lab, you will implement a clustering-based recommender system algorithm using K-means clustering and principal component analysis based on group members’ course enrollment history. In labs four and five you will use collaborative filtering to make predictions about a user’s interest based on a collection of other users’ similar preferences. In lab 4, you will perform KNN-based collaborative filtering and in lab 5, you will use non-negative matrix factorization.

In this module, you will predict course ratings using neural networks. In the first lab, you will train neural networks to predict course ratings while simultaneously extracting users' and items' latent features. In lab 2, you will be given course interaction feature vectors as input data. Using regression analysis, you will calculate numerical rating scores that predict whether a student will audit or complete a course. Lab 3 is similar to lab 2 but instead of using regression you will use a classification model. You will extract user and item embedding feature vectors from a neural network. With those embedding feature vectors, you will create an interaction feature vector and use that to build a classification model. The model maps the interaction feature vector to a rating mode that predicts whether a learner will audit or complete a course.

In this module, you will be introduced to Streamlit and have the opportunity to build a Streamlit app to showcase your work in previous modules. You will review guidelines and best practices for creating successful reports. As well you may wish to review instructions on creating PowerPoint presentations and how to save a PowerPoint as a PDF.

In this final module you will complete your submission of screenshots from the hands-on labs for your peers to review. Once you have completed your submission you will then review the submission of one of your peers and grade their submission.