Data Science 11 Quiz 1

How is curiosity a skill for a data scientist?

• It allows to work independently without any team collaboration

• It drives to explore deeper questions and uncover more meaningful insights from the data

• It lets them skip data cleaning and move straight to data modeling

• It replaces the need for statistical knowledge

Which of the following best describes the role of data scientist in an organization

• They write complex algorithms without any business understanding

• They help in decision-making by deriving insights from data

• They only handle the technical deployment of models

• They primarily collect and store large datasets

In what way is storytelling important in Emma's role as a data scientist

• It helps her avoid visualizations

• It enables her to present technical finding in a way that stakeholders can understand and act upon

• It helps her create more complex algorithms

• It allows her to skip the data acquisition phase

Why is intellectual curiosity important for a data scientist like Emma

• It helps gather more data

• It ensures the use if the best algorithms

• It drives deeper exploration and questioning

• It makes client meetings shorter

Lorraine is working with a new dataset containing customer purchase data. The dataset has missing values and inconsistent data types. What should Lorraine's first course of action be to prepare the dataset for modeling

• Start building the model

• Perform data cleaning to handle missing and inconsistent data

• Run the machine learning algorithms directly

• Visualize the data without any preprocessing

Gwyneth has completed data acquisition and notices that the data collected from one API is inconsistent with the data from another source. What should she do next?

• Ignore the inconsistencies and proceed

• Conduct a thorough investigation and resolve inconsistencies in the data

• Select the data that looks more accurate

• Remove the data from both sources

In a data science project, Darrel has built several models using different algorithms, but all the models show high error rates. What should be his next step?

• Select any model and move forward

• Revisit the data cleaning, feature selection, and possibly the quality of the data

• Increase the complexity of the model without reviewing data

• Deploy the model immediately without any changes

Which of the following scenarios would require Emma to conduct data cleaning?

• The data already contains well-defined features

• There are missing or duplicated values in the data set

• The business problem is not clearly defined

• The client is familiar with all technical terms

Why might companies prefer data scientists with versatile skills?

• Because versatile data scientists can work in different departments

• Versatile data scientist can balance domain expertise, technical proficiency, and communication

• They are usually better at visualizing data using more tools

• They can write better algorithms without needing any business input

What is the key reason for Emma using multiple machine learning techniques like KNN and Naiv

• To make sure she uses the easiest technique

• To find the model that best fits the business requirement

• To avoid cleaning the data

• To gather more data from multiple sources