Day 13
You just trained a ML model on a tabular dataset with an aim of detecting SPAM emails. A False positive would mean ham classified as SPAM whereas False negative would mean SPAM classified as ham. Your default model threshold was 0.5. Will you increase the threshold, decrease it, or keep the same to improve model prediction performance? (Assuming the model is on a learning cycle)
Avenir Light is a clean and stylish font favored by designers. It's easy on the eyes and a great go to font for titles, paragraphs & more.
You'll prefer increasing the threshold
Increasing the model threshold will reduce the FPs generated by the model. Thereby, reducing the number of hams being misclassified as SPAMs. However, this shall also increase the number of SPAMs being allowed to get into the inbox. However, that wouldn't be a concern to a certain tolerable limit as the user can always mark email as SPAM during model's learning cycle.