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 has built their entire infrastructure on AWS which includes web applications built on EC2, Files and logs on S3, databases on Amazon RDS, DynamoDB and DWH on Redshift.
AFS built the data sources and now working on understanding the ML capabilities and establishing the guidelines for building the Amazon ML model insights.
Please advice.
Select 4 options.
Click on the arrows to vote for the correct answer
A. B. C. D. E. F.Answer :
B.
C, D,E.
Option A is incorrect -Different types of logistic regression is implemented as Binary classification, and multiclass classification respectively and linear regression is implemented as regression model.
https://docs.aws.amazon.com/machine-learning/latest/dg/types-of-ml-models.htmlOption B is correct -A prediction accuracy metric to report on the overall success of the model.
https://docs.aws.amazon.com/machine-learning/latest/dg/ml-model-insights.htmlOption C is correct -Different types of logistic regression is implemented as Binary classification, and multiclass classification respectively and linear regression is implemented as regression model.
https://docs.aws.amazon.com/machine-learning/latest/dg/types-of-ml-models.htmlOption D is correct - Prevent overfitting which will make lose generalization.
https://docs.aws.amazon.com/machine-learning/latest/dg/evaluating_models.html#overfittingOption E is correct -Visualizations to help explore the accuracy of your model beyond the prediction accuracy metric.
https://docs.aws.amazon.com/machine-learning/latest/dg/ml-model-insights.htmlOption F is incorrect - Prevent overfitting which will make lose generalization.
https://docs.aws.amazon.com/machine-learning/latest/dg/evaluating_models.html#overfittingAs AFS is exploring the ML capabilities, they need to establish guidelines for building Amazon ML model insights. Here are the explanations for the given options:
A. Different types of linear regression is implemented as Binary classification, and multiclass classification respectively and logistic regression is implemented as regression model. This option is incorrect. Linear regression is used for regression problems while logistic regression is used for binary classification problems. Multiclass classification is usually implemented using algorithms like Decision Trees, Random Forests, or Neural Networks.
B. Prediction accuracy metric defines the overall success of the model. This option is partially correct. While prediction accuracy is an important metric to evaluate the performance of the model, it is not the only metric that defines the overall success of the model. Other important metrics include precision, recall, and F1 score.
C. Different types of logistic regression is implemented as Binary classification, and multiclass classification respectively and linear regression is implemented as regression model. This option is incorrect. As mentioned earlier, logistic regression is used for binary classification problems and not for multiclass classification problems. Linear regression is used for regression problems.
D. Prevent overfitting the models by using cross-validation techniques. This option is correct. Overfitting is a common problem in machine learning, and it occurs when the model is too complex and fits the training data too closely. Cross-validation techniques, such as k-fold cross-validation, can help prevent overfitting by evaluating the model's performance on multiple subsets of the data.
E. Visualizations explore the accuracy of your model beyond the prediction accuracy metric. This option is correct. Visualizations can help in understanding the performance of the model beyond just the prediction accuracy metric. Visualizations can be used to understand the distribution of the data, identify outliers, and explore relationships between variables.
F. Overfitting (through hyperparameters) identifies the right model which can be generalized later. This option is incorrect. Overfitting is not desirable, and it is important to identify the right model that can be generalized to new data. Hyperparameters can be tuned to prevent overfitting, but the goal is not to overfit the model. Instead, the goal is to find the right balance between underfitting and overfitting.