Part I
· How many units have been transacted over the COVID period i.e., 2019 to 2021?
· What are the characteristics of the transacted unit?
· What are the demographics that was observed?
Part II
· Under the Field name – Flat Type, what do you think is the appropriate Data Type?
o Substantiate with relevant research paper or.
o Justify with the appropriate statistical test i.e., significance p-value test.
· Which field name do you think is less meaningful?
o Justify with either Data techniques that you have learned in previous courses such as either Dimensionality Reduction / Feature Selection / Statistical Techniques and Test / Multivariate analysis
Part III
· Conduct Data Blending and add additional fields or variables where you can scrape
o You may extract geospatial data from geospatial provider i.e., OneMap API
§ You may consider testing for confounding variables or variables with effects on housing price i.e., proximity to train / good schools / eateries and substantiate why you would choose it?
Part IV
· Create a dashboard to highlight the following:
o The demographics of certain seller
o The obvious trends and patterns
o A suitable predictive modelling with the appropriate charts i.e., Visual Analytics
The report should document information
· Evolution of your mini project (planning, development, MVP) (200 words in total)
· Analysis of the data provided using data visualization and predictive modelling (500 words in total)
