Data Analytics Overview
- Data: Raw facts and figures.
- Information: Processed data that provides context and meaning.
- Knowledge: Insights gained from analyzing information.
Importance of Understanding Relationship
- Mistakes in confusing data with information can lead to significant errors.
- Organizations rely on accurate information to make informed decisions.
Data-Driven Decision Making
- Definition: Making decisions based on data analysis instead of intuition.
- Data Analytics Process: Structured approach to analyze raw data and derive insights.
Levels of Data Analytics
- Descriptive Analytics:
- Analyzes historical data to understand past events (e.g., trends in website traffic).
- Diagnostic Analytics:
- Explains why something happened by examining various data sources (e.g., impact of marketing campaigns).
- Predictive Analytics:
- Uses statistical models and past data to forecast future outcomes (e.g., predicting weather-related sales).
- Prescriptive Analytics:
- Recommends specific actions based on analysis (e.g., adjusting production based on forecasts).
CRISP-DM Framework
- Business Understanding: Aligns project objectives with business needs.
- Data Understanding: Collects and explores relevant data, checking for quality issues.
- Data Preparation: Prepares data for analysis, which may involve cleaning and transforming data.
- Modeling: Applies various analytical techniques to derive insights, also may require adjustments to data preparation.
- Evaluation: Assesses model performance against business objectives.
- Deployment: Implements insights, which can be in various forms from reports to automated systems.
- Focus on phases: Data Understanding and Data Preparation, including tasks like content engagement analysis.
- Insights from models can guide scheduling and content strategies to maximize engagement.