Fundamentals of Data Science: Transforming Data into Action

  • Data
  • Information
  • Knowledge
  • Intelligence
  • Action

Methodologies

  • Statistical analysis
  • Regression
  • Classification
  • Clustering
  • Time series analysis
  • Anomaly detection
  • NLP
  • Distributed ML
  • Graph analysis
  • Recommender systems
  • Neural networks / Deep learning

Data Science Pipeline

  1. Planning
  2. Acquisition
  3. Preparation
  4. Exploration
  5. Modeling
  6. Delivery
  7. Maintenance

Fundamentals of Data Science: History and Future of Data Science

History

Capability increased due to decreasing cost of data storage, cpu, and bandwidth.

Demand increased due to large amount of data being generated.

Future

  • Demand for talent
    • “The future is so bright, Ada would need shades” – Joseph Burton
  • Emerging subdisciplines
    • Machine Learning Engineer
    • Data Visualization Engineer
    • Data Journalist
    • Big Data Engineer
  • Continued reduction in technical learning curve
    • Automation around machine learning and data wrangling
  • Ethics
    • risk of discrimination in “Black Box” models
    • machine learning can be used for bad as well as for good