SVM regression model to predict a movie's box office collection.

The notebook implements Regression model under Support Vector Machine (SVM) to predict the box-office collection of movies in the test set.

• Preprocessing techniques used
  • Missing Value Imputation
  • Dummy variables
  • Normalization using Standard Scaler
• SVM kernel used : Linear Kernel
• Accuracy Measurement
  • r2_score: R-squared measures the strength of the relationship between the model and the dependent variable on a convenient 0 – 100% scale.
• Running the model
  1. Download the jupyter notebook and the csv file with this repo.
  2. Replace the 'Source File Location' with the location of the downloaded csv file.
  3. Make sure all the dependencies and libraries are installed (e.g. python, pandas, sklearn, numpy, etc.)
  4. Run all the blocks gradually.