In this quest you will learn how to use several BigQuery ML features to improve retail use cases. Predict the demand for bike rentals in NYC with demand forecasting, leverage regression to estimate the time it will take for a ticket to be solved with the help of an automated agent developed using Dialogflow, and see how to use BigQuery ML for a classification task that predicts the likelihood of a website visitor making a purchase.
Applying BigQuery ML's Classification, Regression, and Demand Forecasting for Retail Applications
Overview
Syllabus
- Introduction to SQL for BigQuery and Cloud SQL
- In this lab you will learn fundamental SQL clauses and will get hands on practice running structured queries on BigQuery and Cloud SQL.
- Integrating BigQuery ML with Dialogflow ES Chatbot
- In this lab you will train a simple machine learning model for predicting helpdesk response time using BigQuery Machine Learning.
- Building Demand Forecasting with BigQuery ML
- In this lab you will build a time series model to forcast demand of multiple products using BigQuery ML. This lab is based on a blog post and featured in an episode of Cloud OnAir.
- Predict Visitor Purchases with a Classification Model in BQML
- In this lab you will use a newly available ecommerce dataset to run some typical queries that businesses would want to know about their customers’ purchasing habits.
- Predict Taxi Fare with a BigQuery ML Forecasting Model
- In this lab you will explore millions of New York City yellow taxi cab trips available in a BigQuery Public Dataset, create a ML model inside of BigQuery to predict the fare, and evaluate the performance of your model to make predictions.
