This dataset is linear or no?
What is the best dimensionality reduction? PCA or T-SNE?
Are there empty or null values?
Linear models: Linear regression, Lasso, Ridge, ElasticNet, BayesianRidge
Non-linear models: SVR
Neural network: Hidden layers with Tensorflow and Keras
To the codeSee the results for each model:
Model | R2 score | MSE score |
---|---|---|
Neural network | 88.92% | 5.40 |
SVR | 79.81% | 9.85 |
BayesianRidge | 45.68% | 26.52 |
LinearRegression | 45.68% | 26.53 |
Ridge | 45.68% | 26.52 |
ElasticNet | 45.55% | 26.59 |
Lasso | 45.55% | 26.59 |