nerdexam
Amazon

MLS-C01 · Question #277

A manufacturing company has a production line with sensors that collect hundreds of quality metrics. The company has stored sensor data and manual inspection results in a data lake for several…

The correct answer is B. Amazon SageMaker XGBoost algorithm. The task is to classify product quality into multiple categories (good, replacement, scrap) based on sensor data and inspection results, requiring the most accurate modeling approach.

Modeling

Question

A manufacturing company has a production line with sensors that collect hundreds of quality metrics. The company has stored sensor data and manual inspection results in a data lake for several months. To automate quality control, the machine learning team must build an automated mechanism that determines whether the produced goods are good quality, replacement market quality, or scrap quality based on the manual inspection results. Which modeling approach will deliver the MOST accurate prediction of product quality?

Options

  • AAmazon SageMaker DeepAR forecasting algorithm
  • BAmazon SageMaker XGBoost algorithm
  • CAmazon SageMaker Latent Dirichlet Allocation (LDA) algorithm
  • DA convolutional neural network (CNN) and ResNet

How the community answered

(44 responses)
  • A
    7% (3)
  • B
    77% (34)
  • C
    2% (1)
  • D
    14% (6)

Why each option

The task is to classify product quality into multiple categories (good, replacement, scrap) based on sensor data and inspection results, requiring the most accurate modeling approach.

AAmazon SageMaker DeepAR forecasting algorithm

Amazon SageMaker DeepAR is a forecasting algorithm designed for predicting future values in time series data, not for multi-class classification of product quality based on static or snapshot sensor data.

BAmazon SageMaker XGBoost algorithmCorrect

Amazon SageMaker XGBoost algorithm is a highly effective and widely used gradient boosting algorithm that excels in classification tasks involving tabular data, such as sensor metrics and inspection results. Its robust performance, speed, and ability to handle complex relationships make it an excellent choice for achieving high accuracy in predicting categorical product quality.

CAmazon SageMaker Latent Dirichlet Allocation (LDA) algorithm

Amazon SageMaker Latent Dirichlet Allocation (LDA) is an unsupervised algorithm used for topic modeling in text documents, which is entirely unsuitable for classifying product quality from structured sensor data.

DA convolutional neural network (CNN) and ResNet

Convolutional Neural Networks (CNNs) and ResNet architectures are primarily designed for image and video data analysis, not for direct application to tabular sensor data for multi-class classification without complex data transformation.

Concept tested: Machine learning algorithm selection for tabular classification

Source: https://docs.aws.amazon.com/sagemaker/latest/dg/xgboost.html

Topics

#Classification#XGBoost#Algorithm Selection#Supervised Learning

Community Discussion

No community discussion yet for this question.

Full MLS-C01 Practice