These are the few questions we tackled in this project:
• How can we effectively predict the likelihood of a movie sequel?
• What is the probability of a sequel given the characteristics of a movie?
• Which movie property influences the prediction of a sequel the most?
Dataset Used
500K+ lines of data!
Data Cleaning
Original Data
Cleaned Data
Exploratory Analysis
Distributions of All Numeric Variables
Language Categorical Variable
Machine Learning Models
Feature Importance in the Random Forest Model
Feature Importance in the XGBoost Model
Conclusion
Drama genre is the best variable in predicting the outcome of a sequel. This is fascinating to know that any drama genres movie will have the most likely chance to have a sequel. I guess movie-goers love dramas...
