menu
arrow_back
戻る

Building Demand Forecasting with BigQuery ML

—/100

Checkpoints

arrow_forward

Explore the NYC Citi Bike Trips dataset

Cleaned training data

Training a Model

Evaluate the time series model

Make Predictions using the model

Building Demand Forecasting with BigQuery ML

1時間 クレジット: 5

GSP852

Google Cloud Self-Paced Labs

Overview

BigQuery is Google's fully managed, NoOps, low cost analytics database. With BigQuery you can query terabytes and terabytes of data without having any infrastructure to manage, or needing a database administrator.

BigQuery Machine Learning (BQML) is a feature in BigQuery where data analysts can create, train, evaluate, and predict with machine learning models with minimal coding. Watch this video to learn more about BigQuery ML.

In this lab, you will learn how to build a time series model to forecast the demand of multiple products using BigQuery ML. Using the NYC Citi Bike Trips public dataset, learn how to use historical data to forecast demand in the next 30 days. Imagine the bikes are retail items for sale, and the bike stations are stores.

Watch this video to understand some example use cases for demand forecasting.

Objectives

In this lab, you will learn to perform the following tasks:

  • Use BigQuery to find public datasets.

  • Query and explore the public NYC Citi Bike Trips dataset.

  • Create a training and evaluation dataset to be used for batch prediction.

  • Create a forecasting (time series) model in BQML.

  • Evaluate the performance of your machine learning model.

Qwiklabs に参加してこのラボの残りの部分や他のラボを確認しましょう。

  • Google Cloud Console への一時的なアクセス権を取得します。
  • 初心者レベルから上級者レベルまで 200 を超えるラボが用意されています。
  • ご自分のペースで学習できるように詳細に分割されています。
参加してこのラボを開始