Meeting 2: Meeting with Professor Mehrotra

• Look at data more carefully

  • Conclusion is not clear → need to be clear

  • Possible conclusion: determine if 2 properties are similar or not

• Potential methodology to consider:

  • PCA

  • Correlation analysis

  • Convergent tree? → understand what this means

• Use correct terminology

  • Columns instead of ‘data points’ for attributes

• Since dataset is so large, should consider a sample-based mechanism

  • Try performing analysis on a small subset of dataset before expanding to the rest of it

• Add project proposal to timeline

  • Coming up soon so need to understand data well

• As a team, work jointly until understand project fully

  • 2 weeks from now (next meeting with Mehrotra), need to fully understand data

• Timeline of project

  • Presentations are last two weeks of Spring quarter so project should be complete by then