This project was about creating an online interactive dashboard combining ML models with a traditional dashboards. This app shows the key features of the Hollywood movies that were produced between 1930 to 2016 and provides an interactive ML modeling feature using which users can cluster movies and see the detail of their desired movie clusters.
Below are the brief descriptions of the data and the tabs in the dashboard:
Data used: The Dataset was collected from DataCamp. It contains data about Hollywood movies released from the 1930s to 2016.
Summary - shows the key indicators (e.g. most grossing movie & director, genre-wise profitability), an interactive plot showing over the year numbers of movies produced.
Bi variate relationship - Interactive scatter plot showing how two variables interact, detail data on any selected points on the plot (useful to check outliers) and summary statistics on the individual variable (mean, median, correlation coefficient).
Clustering model - Interactive data clustering modeler and model optimizer and detail data about the clustered movies.
Data - Full detail data with search capability to sort out search output.
Active shiny app link: https://curiousjoe.shinyapps.io/Finding_The_Most_Profitable_Movie/
Rstudio cloud project link: https://rstudio.cloud/project/249191