Blueprint: ECP-451 Ericsson Certified Associate - Data Science

Download as pdf or txt
Download as pdf or txt
You are on page 1of 1

Blueprint:

ECP-451 Ericsson Certified Associate – Data Science

Sections Section/Objective Title


Section 1 Data Science Fundamentals 19%
Objective 1.1 Identify the problem in data science terms
Objective 1.2 Identify what is statistical significance
Objective 1.3 Describe why AI/ML might be more appropriate than traditional algorithms
Objective 1.4 Identify how to interpret a new large unlabeled data set
Section 2 Data Science Tools 10%
Objective 2.1 Identify data science tools
Section 3 Data Exploration and Processing 26%
Objective 3.1 Describe the impact of feature importance based upon domain expertise
Objective 3.2 Identify the main telecom data sources
Objective 3.3 Identify the dataset using data science terminology
Objective 3.4 Identify the main steps in Exploratory Data Analysis (EDA)
Objective 3.5 Describe the types of feature engineering (selection/extraction) required
Objective 3.6 Describe the methods of data interpolation
Section 4 Modeling and Algorithms 21%
Objective 4.1 Describe how to assess an ML model's performance
Objective 4.2 Describe when to use ML for problem solving
Objective 4.3 Identify potential ML models
Objective 4.4 Describe how to apply statistical analysis concepts
Section 5 Model Lifecycle 11%
Objective 5.1 Describe the aspects of model management
Section 6 Visualization 13%
Objective 6.1 Identify the main types of data visualization

You might also like