AWS Certified Big Data - Specialty: Efficiently Solving Customer Identification Problem | Allianz Financial Services

Improve Customer Identification for Allianz Financial Services

Question

Allianz Financial Services (AFS) is a banking group offering end-to-end banking and financial solutions in South East Asia through its consumer banking, business banking, Islamic banking, investment finance and stock broking businesses as well as unit trust and asset administration, having served the financial community over the past five decades. AFS being one the largest banks in the region is planning to improve its segment business by launching a campaign to identify potential customers for their product(s) based on their past behavior? AFS is looking for services that address batch and real-time predictive analytics and also the relevant model to solve customer problem.

Which of the following options in combination help us in efficiently solve the problem.

Select 2 options.

Answers

Explanations

Click on the arrows to vote for the correct answer

A. B. C. D. E.

Answer : B and E.

Option A is incorrect.

Machine Learning web service offers 2 types of predictions.

Batch Predictions asynchronously generate predictions for multiple input data observations.

Real-time Predictions synchronously generate predictions for individual data observations.

https://docs.aws.amazon.com/machine-learning/latest/dg/amazon-machine-learning-key-concepts.html

Option B is correct.

Problem being a binary classification whether the customer will subscribe to new product or not ML models for binary classification predict a binary outcome.

To train binary classification models, Amazon ML uses the industry-standard learning algorithm known as logistic regression.

Amazon ML provides an industry-standard accuracy metric for binary classification models called Area Under the (Receiver Operating Characteristic) Curve (AUC)

https://docs.aws.amazon.com/machine-learning/latest/dg/binary-model-insights.html

Option C is incorrect.

ML models for multiclass classification problems allow you to generate predictions for multiple classes.

In Amazon ML, the macro-average F1 score is used to evaluate the predictive accuracy of a multiclass metric.

https://docs.aws.amazon.com/machine-learning/latest/dg/multiclass-model-insights.html

Option D is incorrect.

ML models for regression problems predict a numeric value.

Amazon ML uses the industry standard root mean square error (RMSE) metric.

https://docs.aws.amazon.com/machine-learning/latest/dg/regression-model-insights.html

Option E is correct.

Machine Learning offers 2 types of predictions.

Batch Predictions asynchronously generate predictions for multiple input data observations.

Real-time Predictions synchronously generate predictions for individual data observations.

https://docs.aws.amazon.com/machine-learning/latest/dg/amazon-machine-learning-key-concepts.html

To efficiently solve AFS's problem of identifying potential customers for their product(s) based on their past behavior, we need services that address batch and real-time predictive analytics and relevant models.

Option A: Amazon ML for batch analytics and SPARK on EMR for real-time analytics Amazon Machine Learning (Amazon ML) is a cloud-based service for creating machine learning models. It provides both batch and real-time prediction services. The SPARK on EMR (Elastic MapReduce) is a managed Hadoop framework that can be used for real-time analytics. Therefore, this option addresses both batch and real-time predictive analytics needs. However, the option does not specify the relevant model for solving the customer problem.

Option B: Binary classification model Binary classification is a supervised learning model where the goal is to classify data into two categories. This model can be used to predict whether a customer is likely to buy a product or not. However, this option does not address the batch and real-time predictive analytics needs of AFS.

Option C: Multiclass classification model Multiclass classification is a supervised learning model where the goal is to classify data into more than two categories. This model can be used to predict which product a customer is likely to buy. However, this option does not address the batch and real-time predictive analytics needs of AFS.

Option D: Regression Model Regression is a supervised learning model where the goal is to predict a continuous variable. This model can be used to predict the expected revenue from a customer. However, this option does not address the batch and real-time predictive analytics needs of AFS.

Option E: Amazon ML for both batch and real-time analytics. Amazon Machine Learning (Amazon ML) provides both batch and real-time prediction services. This option addresses both batch and real-time predictive analytics needs. However, it does not specify the relevant model for solving the customer problem.

In summary, the two options that help efficiently solve AFS's problem are Option A (Amazon ML for batch analytics and SPARK on EMR for real-time analytics) and Option E (Amazon ML for both batch and real-time analytics). However, none of the options specify the relevant model for solving the customer problem. The relevant model will depend on the specific customer problem AFS is trying to solve.