This project is using data on building damage in the region that is hit by Gorkha earthquake to predict damage grade caused by earthquakes to buildings in Nepal. The report involves discussing about the data pre-processing process, EDA, different models and brief discussion about WMD and fairness.
Things I liked:
I think the overall logic flow of this report is very clear, everything is well-connected and extremely intuitive to read through. I remembered hearing the news about Nepal’s earthquake that year so this report is also very much relatable and strongly connected to real-life
The models are well explained, why they are being used and how well they performed
I think the conclusion part is the strongest, very clearly summarized the report and how it can be applied to the real world as well as what future work can be
Areas of Improvement:
(There isn’t really much)
I think some of the graphs can be omitted as they are all already well explained with words (i.e. figure 1, figure 3). Especially for figure 1 it’s very hard to read from the graph so maybe only explanation can be better, and fit the graph in the appendix
Maybe add more hypothesis are questions in between, like when you discovered the plot doesn’t provide a clear picture of the relationship between the damage grades, why is that so? And after stating that there’s an association still, how you want to use models to check that are utilize that
Anyway you can prevent random forest model to overfit?
Overall really great job! I enjoyed reading your report alot !
This project is using data on building damage in the region that is hit by Gorkha earthquake to predict damage grade caused by earthquakes to buildings in Nepal. The report involves discussing about the data pre-processing process, EDA, different models and brief discussion about WMD and fairness.
Things I liked:
Areas of Improvement: (There isn’t really much)
Overall really great job! I enjoyed reading your report alot !