Retail Store en Google Cloud Platform

1

Lo que aprenderás sobre GCP para ecommerce

2

Etapas clave y MLOps

3

Arquitectura de alto nivel

4

Tour de la aplicación de retail

5

Backend as a Service y modelo de seguridad

6

Introducción al proyecto

7

Medición de interacciones

8

Setup de Google Tag Manager

9

Etiquetando con Google Tag Manager

10

Etiquetas relevantes para CLV

11

Integración con servicios

Exposición de servicios con Apigee

12

Servicios expuestos con APIs

13

¿Qué son las APIs?

14

Apigee

15

Creación de tu primer API Proxy en Apigee

16

Administración de APIs con Apigee

17

Creando un portal de desarrolladores

18

Interactuando con el portal de desarrolladores

19

Insights to Actions

Generación de modelos AI/ML

20

Machine Learning con datos estructurados

21

BigQuery para modelos de Forecasting y LTV

22

Bigquery ML - Manos a la Obra

23

Auto ML vs. Bigquery ML

24

Consideraciones para entrenar un modelo en BigQueryML

25

Entrenamiento del modelo en BigQuery ML

26

Cómo exportar modelos hechos en BQML

27

Exportando un modelo hecho con BQML

Consumo de servicios de AI/ML

28

Cómputo Serverless y Contenedores

29

¿Qué es Kubernetes?

30

Consumo de modelos ML mediante BigQuery API

31

Almacenamiento de predicciones

32

Ejecución de predicciones y persistencia

33

Despliegue continuo con Cloud Run

34

Ejecución de despliegue con Cloud Run

35

Escalamiento de servicios en Cloud Run

36

AuthN y AuthZ con Cloud Run

Google Marketing Platform

37

Análisis de las predicciones

38

Segmentamos nuestras Predicciones

39

Caso práctico para definir tu estrategia de activación

40

Generemos nuestros modelos en la plataforma

41

Segmentamos nuestras audiencias en BigQuery

42

Carga tus audiencias y conecta tu medio de activación

You don't have access to this class

Keep learning! Join and start boosting your career

Aprovecha el precio especial y haz tu profesión a prueba de IA

Antes: $249

Currency
$209
Suscríbete

Termina en:

0 Días
4 Hrs
36 Min
13 Seg

Cómo exportar modelos hechos en BQML

26/42
Resources

How is model export integrated with BigQuery ML?

Exporting a model created in BigQuery ML is crucial to maximize the leverage of the work invested in the development of machine learning models. This process not only ensures that the effort is useful, but also gives different areas of an organization, such as marketing or media, the ability to use the model to optimize resources such as advertising budgets.

Why is model exporting important?

Exporting models is essential because:

  • It allows developed solutions to be easily integrated into a company's daily operations.
  • It significantly improves business decisions by enabling optimized use of resources.
  • It gives access to areas such as marketing to improve the efficiency of your advertising budgets, increasing ROI and promoting a strategic focus on key customer segments.

What are the options for exporting models in BigQuery ML?

BigQuery ML offers several ways to export a model:

  1. Google Cloud Console: a visual and straightforward option for exporting models.
  2. bq extract command in the command line: Allows the export of the model in a simple and adaptable way.
  3. BigQuery API: Ideal for integration into an automated machine learning pipeline.

The choice of method will depend on specific needs, such as pipeline automation.

What considerations should be taken into account when exporting?

It is vital to take certain aspects into account when preparing your models for export:

  • Model Formats: each type of model may require a different export format. For example, a DNN (deep neural network) model will be exported in a TensorFlow format.
  • Data Structure: Make sure that the input data used during predictions have the same column structure as the data used during training. The use of new attributes that were not present at the start is not supported.
  • Model Size Limitations: There is a size limit of 1 GB for matrix factorization models. It is important to take this into account in order not to exceed the allowed size.
  • Models that do not support online prediction: Some models, such as AutoML Regressor and AutoML Classifier, are designed for batch processes, not supporting online implementation from the AI platform.

These aspects help optimize the process and ensure that the export runs smoothly and efficiently.

With these tips in mind, you will be ready to export your models and bring real added value to your organization! Keep learning and exploring the potential of BigQuery ML!

Contributions 0

Questions 0

Sort by:

Want to see more contributions, questions and answers from the community?