Capstone Project-R Shiny App
Factors Influencing the Sales Prices of Miami’s Single-Family Homes
Miami's real estate market has expanded and changed significantly (Wijburg, 2021).
Single-family homes are among the best real estate options for investors and homebuyers because they offer a consistent value over the long term as well as the short term.
To make well-informed decisions, real estate agents, buyers, and sellers must develop a thorough understanding of the underlying factors that affect the sale prices of single-family homes.
Data-driven decisions, for instance, can assist sellers in accurately valuing their real estate properties to draw buyers while maximizing their investment returns.
This capstone project used a dataset of 13,932 observations related to single-family homes sold in Miami.
The dataset contained a number of attributes such as sale price, land area, floor area, value of special features, distance to amenities (rail line, ocean, business center, nearest subcenter, highway), age of the structure, airplane noise, quality of the structure and sales month.
The dataset was considered sufficiently complex and interesting enough to justify its use in the developed shiny app.
It contained both continuous and categorical variables, allowing for a diverse range of visualizations.
The visualizations created by the shiny app allowed users to gain insights into various aspects of the dataset. The histogram visualization for continuous variables provided a clear understanding of their distribution, allowing users to observe trends and variations in data. The bar chart and frequency table for categorical variables enabled users to explore the distribution and prevalence of different categories. The scatter plots with color encoding offered multivariate insights, allowing users to identify relationships and patterns between three continuous variables and a third categorical variable.
Principles
The presentation demonstrated adherence to visualization principles, such as choosing appropriate visualizations based on the variable type (histograms for continuous, bar charts for categorical, scatter plots for multivariate analysis).
Color encoding in scatter plots was used effectively to represent a third variable, enhancing the visual understanding without cluttering the plots.
The presentation encouraged interactive exploration through the shiny app, enabling users to choose their variables of interest and gain personalized insights.
