The regression model was built using the features Age
, Study_Hours
, Screen_Time
, Caffeine_Intake
, and Physical_Activity
to predict Sleep_Duration
.
Here are the evaluation results of the model:
- Mean Squared Error (MSE): 2.53
- R-squared (R²): -0.0485
The Mean Squared Error (MSE) indicates the average squared difference between the observed actual outcomes and the outcomes predicted by the model. A lower MSE is better, but in this case, it seems relatively high.
The R-squared (R²) value is negative, which suggests that the model does not fit the data well. An R² value of 1 indicates a perfect fit, while a value of 0 indicates that the model does not explain any of the variability in the response data around its mean. A negative R² suggests that the model is worse than a horizontal line (mean of the target variable).
This indicates that the linear regression model may not be suitable for this dataset, or that the selected features are not good predictors of Sleep_Duration
. You might want to consider feature engineering, trying different models, or checking for multicollinearity.
Would you like to try a different model or explore other features?