Mantieni tutto organizzato con le raccolte
Salva e classifica i contenuti in base alle tue preferenze.
Pattern di riferimento
Questa pagina fornisce link a casi d'uso aziendali, codice di esempio e guide di riferimento tecnico per i casi d'uso di BigQuery ML. Utilizza queste risorse per identificare le best practice e velocizzare lo sviluppo delle applicazioni.
Regressione logistica
Questo pattern mostra come utilizzare la regressione logistica per eseguire la definizione del modello di propensione per le applicazioni di gioco.
Scopri come utilizzare BigQuery ML per addestrare, valutare e ottenere
predizioni da diversi tipi di modelli di propensione.
I modelli di propensione possono aiutarti a determinare la probabilità che utenti specifici tornino nella tua app, in modo da poter utilizzare queste informazioni nelle decisioni di marketing.
Scopri come rendere operativo il machine learning con le tue attività
combinando
Connected Sheets con un
modello di previsione in BigQuery ML. Questo pattern illustra la procedura per creare un modello di previsione del traffico sul sito web utilizzando i dati di Google Analytics. Puoi estendere questo pattern per lavorare con altri tipi di dati e altri modelli di machine learning.
Questo pattern mostra come utilizzare il rilevamento di anomalie per trovare attività fraudolente con carte di credito in tempo reale.
Scopri come utilizzare le transazioni e i dati dei clienti per addestrare modelli di machine learning in BigQuery ML che possono essere utilizzati in una pipeline di dati in tempo reale per identificare, analizzare e attivare avvisi per potenziali attività fraudolente con carte di credito.
[[["Facile da capire","easyToUnderstand","thumb-up"],["Il problema è stato risolto","solvedMyProblem","thumb-up"],["Altra","otherUp","thumb-up"]],[["Difficile da capire","hardToUnderstand","thumb-down"],["Informazioni o codice di esempio errati","incorrectInformationOrSampleCode","thumb-down"],["Mancano le informazioni o gli esempi di cui ho bisogno","missingTheInformationSamplesINeed","thumb-down"],["Problema di traduzione","translationIssue","thumb-down"],["Altra","otherDown","thumb-down"]],["Ultimo aggiornamento 2025-09-04 UTC."],[[["\u003cp\u003eThis page provides resources such as business use cases, sample code, and technical guides for various BigQuery ML applications.\u003c/p\u003e\n"],["\u003cp\u003eLearn to create propensity models with logistic regression, which can determine the likelihood of user engagement, such as returning to your app.\u003c/p\u003e\n"],["\u003cp\u003eExplore time-series forecasting patterns to build models for predicting retail demand for products.\u003c/p\u003e\n"],["\u003cp\u003eDiscover how to combine Connected Sheets with a forecasting model in BigQuery ML to operationalize machine learning for business tasks, like forecasting website traffic.\u003c/p\u003e\n"],["\u003cp\u003eUtilize anomaly detection patterns to identify and analyze potential credit card fraud in real-time using machine learning models trained in BigQuery ML.\u003c/p\u003e\n"]]],[],null,["# Reference patterns\n==================\n\nThis page provides links to business use cases, sample code, and technical\nreference guides for BigQuery ML use cases. Use these resources to\nidentify best practices and speed up your application development.\n\nLogistic regression\n-------------------\n\nThis pattern shows how to use logistic regression to perform propensity\nmodeling for gaming applications.\n\nLearn how to use BigQuery ML to train, evaluate, and get\npredictions from several different types of propensity models.\nPropensity models can help you to determine the likelihood of specific\nusers returning to your app, so you can use that information in\nmarketing decisions.\n\n- Blog post: [Churn prediction for game developers using Google Analytics 4 and BigQuery ML](/blog/topics/developers-practitioners/churn-prediction-game-developers-using-google-analytics-4-ga4-and-bigquery-ml)\n- Notebook: [Churn prediction solution notebook](https://github.com/GoogleCloudPlatform/analytics-componentized-patterns/tree/master/gaming/propensity-model/bqml)\n\nTime-series forecasting\n-----------------------\n\nThese patterns show how to create time-series forecasting solutions.\n\n### Build a demand forecasting model\n\nLearn how to build a time series model that you can use to forecast retail\ndemand for multiple products.\n\n- Blog post: [How to build demand forecasting models with BigQuery ML](/blog/topics/developers-practitioners/how-build-demand-forecasting-models-bigquery-ml)\n- Notebook: [Demand forecasting solution notebook](https://github.com/GoogleCloudPlatform/analytics-componentized-patterns/blob/master/retail/time-series/bqml-demand-forecasting/bqml_retail_demand_forecasting.ipynb)\n\n### Forecast from Google Sheets using BigQuery ML\n\nLearn how to operationalize machine learning with your business\nprocesses by combining\n[Connected Sheets](/bigquery/docs/connected-sheets) with a forecasting\nmodel in BigQuery ML. This pattern walks you through\nthe process for building a forecasting model for website traffic using\nGoogle Analytics data. You can extend this pattern to work\nwith other data types and other machine learning models.\n\n- Blog post: [How to use a machine learning model from Google Sheets using BigQuery ML](/blog/topics/developers-practitioners/how-use-machine-learning-model-google-sheet-using-bigquery-ml)\n- Sample code: [BigQuery ML forecasting with Sheets](https://github.com/googleworkspace/ml-integration-samples/tree/master/apps-script/BQMLForecasting)\n- Template: [BigQuery ML forecasting with Sheets](https://docs.google.com/spreadsheets/d/1njedwGjBOkUbTS_HYD0wIPuQIDHgobp1D80qO-OsNH0/copy)\n\nAnomaly detection\n-----------------\n\nThis pattern shows how to use anomaly detection to find real-time credit\ncard fraud.\n\nLearn how to use transactions and customer data to train machine\nlearning models in BigQuery ML that can be used in a\nreal-time data pipeline to identify, analyze, and trigger alerts for\npotential credit card fraud.\n\n- Sample code: [Real-time credit card fraud detection](https://github.com/googlecloudplatform/fraudfinder)\n- Overview video: [Fraudfinder: A comprehensive solution for real data science problems](https://io.google/2022/program/9a759b60-9a9b-4744-bd22-6e21a4a864cd/)"]]
