Microsoft Power BI
Power BI has components in one of the following categories:
- Data visualization
- Data preparation
- Data modeling
We will look into AI in all of these three categories:
AI in Data visualization:
This AI visual tells what the factors are due to which a particular metric changed.
Example: If you want to know what factors increase the happiness of students, it would let you know.
Using this visual, end-users can ask questions when using the report.
Example: Total number of students enrolled.
It explains why there is an increase/decrease between two points in the data. It also finds where the distribution is different in data. Example: In April there may be more enrollments than Feb. Insights will show which factor contributed to this happening.
AI in Data Preparation:
Automated Machine Learning:
AutoML lets users create and train machine learning models. It currently supports development of Binary classification, Regression and General Classification models. Forecasting and other models may be added later.
Example: Using the survey data it will determine the relation between different factors such as curriculum, residence and happiness etc.
They mainly include:
- Image Tagging
- Extracting Key Phrases
- Detecting Language
- Score Sentiment
Example: This service will determine the language in which the survey is filled, it will extract the key phrases and detect the sentiments using those phrases.
AI in Data Modeling:
Data models in PowerBI allows you to build reports on top of it. A well-built model allows you to use features such as Q&A and Quick Insights. Quick Insights uses your model to find various trends in your data whereas Q&A allows users to ask natural language questions w.r.t data model.
The Key Influencers feature in PowerBI will recommend you the factors to work on to reach your goal.
Created with the Personal Edition of HelpNDoc: Full-featured multi-format Help generator