Digital Lifestyle, Sleep & Stress Health

Muralidhar_Gunde

Which dataset used?

I used a dataset related to mental fatigue, lifestyle, and digital usage patterns.

How did you analyze or prepare the data?

The dataset (sourced from Kaggle) was analyzed through a structured data preparation and transformation process to ensure accuracy and meaningful insights.

Data Cleaning

• Removed null or inconsistent values in key fields like mental_fatigue_score, gender, and occupation
• Standardized categorical values (e.g., gender labels, occupation names)
• Checked for duplicate records and eliminated them

Data Transformation

• Converted numerical fields into appropriate formats for analysis
• Created decile buckets for mental_fatigue_score to analyze distribution (Low → High)
• Aggregated metrics such as:
  • Total mental fatigue score
  • Average fatigue score by occupation
  • Notifications received per day

Data Modeling

• Established relationships between key dimensions:
  • Gender ↔ Occupation
  • Occupation ↔ Mental fatigue score
• Structured the data to support slicing and filtering across multiple dimensions

Visualization & Analysis

• Used different charts to represent insights effectively:
  • Bar charts → Comparison across occupations
  • Histogram → Distribution of fatigue scores
  • Stacked visuals → Gender and occupation split
  • Decile analysis → Trend from low to high fatigue

Did you use Oracle Analytics AI features?

Yes, I utilized Oracle Analytics AI capabilities, including:

Explain, to identify key drivers of attrition
Auto Insights and AI Assistant for generating insights, which were further refined and customized.