Limited time · 90% off Premium Membership - claim $199 deal →
Mammoth Club All levels 16 sections 65 lectures

Build Recommendation Algorithms - Machine Learning to Trigger Clicks in Python

Learn how to create your own movie recommender systems using real-world datasets, user behavior, and advanced machine learning techniques. This hands-on course walks you through the complete process—from data preprocessing to user similarity modeling, KNN classifiers, and neural network architectures.

01
Skill level
All levels
02
Sections
16
03
Lectures
65
04
Instructor
Alex Kropf
What's inside

This course includes.

16
Sections
4
Quizzes
Certificate of completion
Included
Mobile and desktop access
Included
AI learning assistance
Included
Unlock all courses with our Subscription Bundle! Get unlimited access to entire course library, books and assets. Learn more and subscribe today!
Course content

Curriculum & lectures.

16 sections · 65 lectures
+ Welcome! 1 lecture
Submit a Question/Feedback Locked
+ 00a Recommender System Types & Performance Metrics 3 lectures
Types of recommender systems: content-based, collaborative, hybrid Locked
Metrics of success: click-through rate (CTR), conversion rate, dwell time Locked
Deep Learning Techniques for Recommendations Locked
+ 00b Data Structures & Feedback Loops 3 lectures
Implicit vs explicit feedback (clicks, ratings, watch time) Locked
Cold start problem and strategies for new users and items Locked
Data collection pipelines, user interaction logs, feature stores Locked
+ 01 Introduction to Recommender Systems 5 lectures
01 Introduction To Recommender Systems Locked
02 How To Evaluate Recommender Systems Locked
03 Content Based Recommendations Locked
04 Neighborhood Based Collaborative Filtering Locked
Full Course Source Files Locked
+ 02 Build a Basic Movie Recommender System 5 lectures
01 Project Preview Locked
02 Load Data As Pandas Dataframes Locked
03 Merge Movies And Ratings Dataframes Locked
04 Build A Correlation Matrix Locked
05 Test The Recommender Locked
+ 03 Build a Simple Movie Recommender with Machine Learning 1 lecture
01 Project Preview Locked
+ 04 Introduction to User Similarity 5 lectures
01 Load Data Into Dataframes Locked
02 Find A Recommendation Based On Different Movie Features Locked
03 Calculate Distance Between Users Locked
04 Find Similar Users With Euclidean Distance Locked
Source Files 1-4 Locked
+ 05 Recommend a Movie Based on User Similarity 4 lectures
01 Define Similarity Between Users Locked
02 Find Top Similar Users Locked
03 Recommend A Movie Based On User Similarity Locked
Source Files Locked
+ 06 Recommend a Movie with a K Nearest Neighbors Classifier 5 lectures
01 What Is K Nearest Neighbours Locked
02 Recommend A Movie With A K Nearest Neighbors Classifier Locked
03 Create A Sample User For Testing Locked
04 Recommend Movies To Sample User Locked
Source Files Locked
+ 07 Machine Learning User Recommendations with Profiles and Items 1 lecture
01 Project Preview Locked
+ 08 Data Processing Profiles and Items 4 lectures
01 Load Data For Machine Learning Locked
02 Process Data For Machine Learning Locked
03 Build Categories Locked
Source Files Locked
+ 09 Build Models for User Recommendations 9 lectures
01 Regression Introduction Locked
02 What Is Regression Locked
03 Build A Ridge Regression Model Locked
04 Evaluate Model Error Locked
05 Visualize Top Features Affecting Rating Locked
06 Build A Lasso Regression Model Locked
07 Visualize Top Features From Lasso Regression Locked
08 Determine Which Model Is Best Locked
Source Files Locked
+ 10 Build a Model to Predict Ratings 4 lectures
01 Load Data For A Neural Network Locked
02 Build A Singular Value Decomposition Algorithm Locked
03 Calculate Model Error Locked
Source FIles Locked
+ 11 Build a Dense Neural Network to Recommend Movies 3 lectures
01 What Is Deep Learning Locked
02 What Is A Neural Network Locked
03 What Is Unsupervised Learning Locked
+ 12 Build a Neural Network to Predict Ratings 3 lectures
01 Build A Neural Network Locked
02 Train The Neural Network Locked
Source Files Locked
+ 13 Data Analysis with Pandas, Numpy and Sci-kit Learn 9 lectures
01 Project Preview Locked
02 Load Data Into Dataframes Locked
03 Explore Data In Our Dataset Locked
04 Build A Rating Pivot Table Locked
05 Calculate Average Rating Of A Movie Locked
06 Find Ratings For A Movie In Every Slice Locked
07 Find Rating Averages For Every Movie In The Slice Locked
08 Build An Average Ratings Column Locked
Source Files Locked
Description

About this course.

✅ Understand how recommender systems work and their real-world applications

✅ Build a basic content-based recommender system with Python

✅ Apply machine learning to create personalized user-based recommendations

✅ Use K-Nearest Neighbors to predict user preferences based on behavior and similarity

✅ Process and analyze data using Pandas, NumPy, and Scikit-learn

✅ Create profile-based recommendation models by connecting users to items

✅ Build, train, and evaluate dense neural networks for scalable movie suggestions

✅ Work with user-item matrices and collaborative filtering strategies


🎮 Follow step-by-step projects that build your skills from simple logic to machine learning-powered predictions.


🎁 Includes source code, sample datasets, and lifetime access with free updates.


If you're ready to master the technology behind Netflix and Spotify’s recommendation engines—this course will show you how. Enroll now and start building intelligent recommender systems today. 

Instructors

Taught by people who ship.

Alex Kropf

Alex Kropf

Mammoth Club's CLO, public speaker, consultant, IT author and Senior Software Developer. Alex has produced best-selling courses, books and workshops for Mammoth Club, Course Pro and our clients since 2016.

Ready to start building?

Learn how to create your own movie recommender systems using real-world datasets, user behavior, and advanced machine learning techniques. This hands-on course walks you through the complete process—from data preprocessing to user similarity modeling, KNN classifiers, and neural network architectures.

Buy lifetime access →