Teach on Udemy

Turn what you know into an opportunity and reach millions around the world.

Learn More

Your cart is empty.

Keep shopping

BigQuery ML - Machine Learning in Google BigQuery using SQL

Name: BigQuery ML - Machine Learning in Google BigQuery using SQL
Rating: 4.4 (415 reviews)

Create Machine Learning models in Google Cloud Big Query using standard SQL. Big query ML course for ML, Data engineers

Created byJ Garg - Real Time Learning

Last updated 6/2025

English

What you'll learn

BigQuery ML - Learn Machine Learning in Google Cloud using BigQuery.
Learn to Train, Evaluate, Inference, Tune and Explain Machine leaning models using standard SQL with Big Query.
Theory + BigQuery ML implementation of many Machine learning algorithms.
Detailed theory for each of the ML algorithm with a Real-world example implementation in BigQuery ML.
Linear regression, Logistic regression, K-means clustering, Boosted Tree.
Deep neural networks, ARIMA+ Time series Forecasting, Matrix Factorization, PCA.
Hyperparameter tuning of models, Model Explainability functions, Feature pre-processing functions, model management operations in BigQuery ML.

Course content

18 sections • 125 lectures • 11h 3m total length

Introduction to Google Cloud Platform2:13
What is google cloud platform - An introduction to GCP
GCP vs AWS vs Azure - Why choose GCP6:03
Comparison between major Cloud providers - (Google cloud Platform) GCP , AWS and Azure. Why choose GCP
AI & ML services in Google Cloud8:55
In this lecture you will learn what all Artificial Intelligence and Machine learning services Google cloud platform (GCP) provides

What is BigQuery ML4:38
What is Bigquery ML - Bigquery ML lets you create and execute machine learning models in Google cloud Big query using standard SQL queries
Conventional ML challenges and How Big query is addressing them7:37
Earlier Data analysts could not take part in Machine learning initiatives in their organization because they don't have ML experience but with Big query ML, they can now train ML models with SQL only.
BigQuery ML Features6:36
Various features of Big Query machine learning (BQML)
Advantages of BigQuery ML4:02
Advantages and uses of having Big Query ML in your project's tool stack folio
Lifecycle/Workflow of a BigQuery ML Project4:56
This lecture explains How a basic workflow of Big query ML project looks like in real.
BQML supported models5:47
What all Machine learning models are supported by Google Bigquery

Announcement1:23
BigQuery crash course starts.
Setup a GCP account0:45
How to setup and login to Google cloud platform.
Important Note0:13
Create a Project4:25
Create first project in Google cloud Bigquery
BigQuery UI Tour12:41
This lecture will give you a very first look of What all options are present in Google cloud Bigquery's dashboard.
Create a Dataset10:04
Create first Dataset in Google cloud Bigquery
Create a Table8:00
Create first Table in Google cloud Bigquery
Assignment - Create Table

What is Linear regression - Part 15:53
What is linear regression, dependent variable, independent variable etc. This lecture explains the linear regression machine learning algorithm.
What is Linear regression - Part 24:00
What is linear regression, dependent variable, independent variable etc. This lecture explains the linear regression machine learning algorithm.
High-level view of Create Model query7:02
Bigquery's Create model statement in general. A high level view of Big query's create model statement with example.
Limitations of Create model query3:02
Limitations of a create model query in general for all the BigQuery ML supported algorithms.
Linear regression Example Use case5:03
Use case introduction to create a linear regression model using BigQuery ML
Basic Options in Create model query6:27
What options are available in Bigquery ML for linear regression machine learning algorithm.
Overfitting problem3:54
Apply L1 and L2 regularization to prevent overfitting by shrinking feature coefficients toward zero, improving generalization to unseen data beyond training.
L2/Ridge regularization5:41
Bigquery provides L2 regularization option to control model overfitting.
L1/Lasso regularization3:12
Bigquery provides L1 regularization option to control model overfitting.
Gradient Descent Optimize Strategy6:44
Optimize_strategy option in Big query Linear regression model to choose the strategy using which you would like to minimize the cost function.
Types of Gradient Descent2:52
Stochastic Gradient Descent
Batch Gradient Descent
Mini-batch Gradient Descent
Learn rate Option4:11
This is a generic option to set the step size hyperparameter in Bigquery's create model query.
Other Options in Create model query7:49
Other options in Bigquery ML for linear regression machine learning algorithm.
Model Training - Write Create model Query for Linear regression9:12
Implement the Linear regression model for our use case in Big query ML
Exploring Model details3:31
Explore the model created in BigQuery dashboard.
Model Evaluation Query (ML.EVALUATE)7:43
Run Bigquery's ML.EVALUATE function to get evaluation metrics for model.
Model Training - Optimize Create Model Query6:56
Induce regularization parameter in Big query linear regression model to control model overfitting.
ML.TRAINING_INFO Function0:28
ML.TRAINING_INFO function in Big query
Model Prediction (ML.PREDICT)6:12
BigQuery provides ML.PREDICT function for inferencing regression models.
Quiz 1
Assignment - Linear regression

What is Hyperparameter Tuning ?2:39
What is Hyperparameter Tuning in general and what kind of Hyperparameter Tuning does Big query supports.
Hyperparameter Tuning Options in BigQuery8:31
This lecture explains What all exclusive options are provided by BigQuery to induce hyperparameter tuning in create model statement.
Tune the Linear regression model6:01
Include BigQuery hyperparameter tuning in the Linear regression model we just created in the previous section.
ML.TRIAL_INFO Function0:35
ML.TRIAL_INFO Function for Hyperparameter tuned models of Big query.

Why Model Explainability is important ?3:40
Model explainability has become very important in highly regulated industries where companies have to align with the ethnic requirements or legal regulations.
Model Explainability Functions in BigQuery6:24
What all functions are provided by Bigquery ML for model explainability.
ML.WEIGHTS Function2:33
How to implement ML.WEIGHTS Function in Bigquery for ML regression models.
List of functions supported by all models0:08
List of functions supported by all models in BigQuery

What is Logistic regression ?3:09
What is logistic regression algorithm and How it is different from Linear regression machine learning algorithm.
Sigmoid Function3:42
Difference between linear regression and logistic regression algorithm.
Logistic regression Example Use case4:44
Use case to implement Logistic regression model in Big query ML. Also covers some basic EDA to do.
Model Training - Write Create model Query for Logistic regression3:04
Implement Logistic regression example in BigQuery. Write the bigquery's create model statement for the problem.
Evaluation metrics Fundamentals explained6:55
This lecture explains model evaluation metrics like ROC_CURVE, CONFUSION_MATRIX etc of logistic regression model.
Precision, Recall, Accuracy, F1 score7:38
Explained - Precision, Recall, Accuracy, F1 score metrics of the BigQuery Logistic regression model created. How to choose the threshold value for a use case.
Evaluation Functions in BigQuery5:15
This lecture explains various Evaluation Functions provided to us by BigQuery for Logistic regression models.
Prediction Function (ML.PREDICT)4:12
Big Query provides ML.PREDICT function for inferencing regression models.
Applications of Logistic regression2:16
Applications of logistic regression machine learning model.
Quiz 2
Assignment - Logistic regression

Automatic Feature Pre-processing9:32
BigQuery applies Standardization and one-hot encoding techniques to preprocess the data automatically before training a Machine learning model.
Manual Feature Pre-processing - Part 110:25
This lecture explains many BigQuery functions for manual feature pre-processing of data.
Manual Feature Pre-processing - Part 23:06
This lecture explains many BigQuery functions for manual feature pre-processing of data.
FEATURE_INFO Function0:38
FEATURE_INFO Function in Big query

What is Clustering4:00
What is clustering in machine learning world.
K-means algorithm working4:10
Explanation of k-means clustering machine learning algorithm.
Advantages & Disadvantages of K-means3:27
Advantages & Disadvantages of K-means clustering machine learning algorithm.
Applications of K-means algorithm3:01
Applications of K-means clustering machine learning algorithm.
Options in Create model query6:43
What are various create model query options provided to us by big query for k-means clustering machine learning algorithm.
K-means Example in BigQuery - Create model7:54
Implement k-means clustering machine learning algorithm in Bigquery ML part 1
K-means Example in BigQuery - Evaluation6:02
Implement k-means clustering machine learning algorithm in Bigquery ML part 2
K-means Example in BigQuery - Prediction4:08
Implement k-means clustering machine learning algorithm in Bigquery ML part 3
K-means Example in BigQuery - Anomaly detection5:43
Quiz 3
Assignment - Kmeans Clustering

What is Boosting and Why it is needed6:09
What is Boosting in Machine learning and Why it is needed
Boosted Tree working explained4:40
This lecture explains the working of boosted tree machine learning model.
Types of Boosting5:22
This lecture explain about various types of boosting techniques available in boosted tree machine learning.
Options in Create model query - Part 18:15
What are various create model query options provided to us by big query for Boosted Tree machine learning algorithm - part 1
Options in Create model query - Part 28:50
What are various create model query options provided to us by big query for Boosted Tree machine learning algorithm - part 2
Boosted Tree Example - Use Case Intro & EDA5:55
This lecture demonstrates an example to implement Boosted tree machine learning algorithm in BigQuery ML.
Boosted Tree Example - Feature Engineering Part 12:32
Feature engineering step while implementing Boosted tree machine learning algorithm in BigQuery ML part 1
Boosted Tree Example - Feature Engineering Part 210:49
Feature engineering step while implementing Boosted tree machine learning algorithm in BigQuery ML.
Boosted Tree Example - Create model8:50
Write the create model query to train the model for implementing Boosted tree machine learning algorithm in BigQuery ML.
Boosted Tree Example - Hyperparameter Tuning5:28
After evaluating the model 1 results, tune the create model query by adding hyperparameters provided by BigQuery ML for boosted tree machine learning algorithm.
Boosted Tree Example - Evaluation4:38
Evaluation of Hyperparameter tuned bigquery model.
Quiz 4
Boosted Tree - Assignment

Requirements

Basic knowledge of SQL.

Description

"BigQuery ML lets you create and execute machine learning models in BigQuery using standard SQL queries."

Big Query ML is a blessing for engineers who want to work in Machine Learning domain but lack programming language like Python, R. With Big Query ML, they can use their existing SQL knowledge to build operational production-grade Machine learning models.

What's included in the course ?

Brief introduction to various Machine Learning services of Google Cloud.
Fundamentals of BigQuery ML and challenges which it solves.
All of the Machine Learning algorithms are explained in 2 Steps :
Step 1 : Theoretical explanation of working of an ML algorithm.
Step 2 : Practical implementation of the ML algorithm in BigQuery ML.
Each and every Machine learning algorithm is explained with HANDS-ON examples.
Hyperparameter tuning of models, Model Explainability functions, Feature pre-processing functions.
Model management operations using bq commands.
BigQuery ML pricing (Flat rate & On-demand pricing models).
Assignment for each Machine learning algorithm for self Hands-On in Big Query ML.
Learn Best practices and Optimization techniques for BigQuery ML.

Machine Learning algorithms explained:

Linear regression
Logistic regression
K-means clustering
Boosted Tree
Deep neural networks
ARIMA+ Time series Forecasting
Product Component Analysis (PCA)
Matrix Factorization

After completing this course, you can confidently start creating production-grade Machine Learning models in Real-world corporate projects using BigQuery ML.

Add-Ons

Questions and Queries will be answered very quickly.
Queries, datasets and references used in lectures are attached in the course for your convenience.
I am going to update it frequently, every time adding new components of Bigquery ML.

Who this course is for:

Machine Learning Engineers
Data analysts
Data scientists
Data Engineers

BigQuery ML - Machine Learning in Google BigQuery using SQL

What you'll learn

Explore related topics

Course content

Introduction to GCP3 lectures • 17min

BigQuery ML (BQML) introduction6 lectures • 34min

BigQuery Basics - Crash course7 lectures • 38min

Linear Regression19 lectures • 1hr 40min

Hyperparameter Tuning in BigQuery4 lectures • 18min

Model Explainability Functions4 lectures • 13min

Logistic regression9 lectures • 41min

Feature Pre-processing4 lectures • 24min

K-means Clustering9 lectures • 45min

Boosted Trees11 lectures • 1hr 11min

Requirements

Description

Who this course is for: