Big Data Management, Analysis, and Presentation

The School hosted Dr. Andrea Brunello for a total of 10 hours of interactive lectures in the Digital Resources and Document Management course from October 9 to 23, 2024.

9/10 [3h]: LLMs and Prompt Engineering for Data Analysis

  • Overall presentation of the course
  • Fundamental concepts of data mining (supervised vs. unsupervised, training and test split), which are needed to understand the hands-on part
  • LLMs and prompt engineering
  • Hands-on with ChatGPT for data analysis (Titanic dataset on Kaggle)

16/10 [3h]: Data visualization, theory, and practice with Power BI

  • Storytelling with data
  • Hands-on with Power BI (UFO dataset on Kaggle)

23/10 [4h]: Data provenance and storage

  • Databases intro and motivation
  • Relational databases and SQL (brief look at Postgres)
  • Big Data and NoSQL databases (brief look at Neo4j graph database)
  • Data warehousing (with a case study)