Aim:
To predict the number of seating spaces based on various types of seating layout, number of corridors and dimensions of generative enclosed rectangular spaces such as an auditorium.
Data Structure:
Prediction Comparison between normal (linear) regression and XGB regression
Prediction Comparison between Kernel Ridge regression and XGB regression
Conclusion:
- The best method for this dataset is ANN regression.
- XGB regression is also good but has some minor outliers.
- Linear regression is not suitable for the dataset as it predicts some negative values that is not valid in real life scenarios for the number of people.
- ANN classification is more suitable for predicting seating layouts.