Learning Objectives

The Enterprise Big Data Analyst (EBDA®) qualification shows that candidates possess the skill to analyze Big Data and are able to understand key data analysis concepts and techniques. Moreover, an Enterprise Big Data Analyst is able to interpret data and draw conclusions correctly. The Enterprise Big Data Analyst qualification builds upon the first level of the Big Data Framework qualification scheme (EBDP), in which fundamental knowledge and elementary concepts related to Big Data were covered. The Enterprise Big Data Professional certificate is therefore a pre-requisite to this certification.

A certified Enterprise Big Data Analyst has proficiency in key models and concepts that are required to analyze data on a day-to-day basis. (S)He understands the theoretical difference between different statistical and machine learning approaches and is able to explain the difference between models and select and apply the appropriate model when confronted with a particular business problem.

Certified candidates should be able to deduce value out of Big Data sets but may not be sufficiently skilled to do this autonomously for all types of problems. Their Big Data experience, the complexity of the problem, and the support provided in their work environment would all be factors that impact what the certified candidate can achieve.

Specifically, (s)he should be able to demonstrate this understanding by being able to:

• Understand and explain the data analysis process, including all relevant steps included in enterprise big data analysis.
• Understand the difference and structure of common data sources (local, online, and database connections) and the way these sources should be imported in order to perform data analysis.
• Apply and utilize fundamental data cleaning operations and the differences between different data cleaning techniques.
• Apply and utilize fundamental data wrangling operations and the differences between different data wrangling techniques.
• Understand and apply exploratory data analysis techniques that are required for model building, model validation, and initial visualizations.
• Understand and apply the core concepts of statistical inference, including techniques required for hypothesis testing.
• Formulate and interpret predictive models based on statistical correlation and regression functions, including simple linear regression.
• Formulate and interpret machine learning models for classification, including K-Nearest Neighbour, Naïve Bayes, Logistic Regression, and Classification Trees.
• Formulate and interpret machine learning models for clustering, including the Hierarchical clustering and K-means clustering techniques.
• Formulate and interpret outlier detection models, including Grubbs Outlier detection and K-NN Outlier Detection.
• Understand and apply the core data presentation techniques including codebooks and visualizations to present the findings of their analysis.