Skip to main content
added 424 characters in body
Source Link
mon
  • 1.6k
  • 11
  • 20

Using ROC can miss the low precision where FP > TP because ROC only look at TPR and FPR. I think what we need to ask is:

  1. Will FP > TP happen with your data and the model.
  2. Does FP > TP matter for your business problem.

If the answer is yes for both, then ROC only is not fit for use.

enter image description here

If the problem is identifying shoplifters and FP will alarm the police. Almost all the shop customers are honest, then catching more honest customers as shoplifters than real ones will cause angry customers and police. Then looking at only ROC will not be a good idea to measure the model.

If the problem is identifying potentially fatal food for toddlers, FP > TP may not be a big issue because there will be so many safe food (TN) as long as TPR is really high. Then ROC will be fit for use to measure the model.

FP: False Positive
TP: True Positive
FPR: False Positive Rate
TPR: True Positive Rate

Suppose I am running a risky loan business where manymajority of the customers can beare risky. If I evaluate the business performance with ROC only, I think the performance is good because TPR is high and FPR is low, although actually the business is losing money because of FP > TP. By looking at PR, it will tell the low precision and I will understand the business performance is bad as I am looking money.

enter image description here

Using ROC can miss the low precision where FP > TP because ROC only look at TPR and FPR. I think what we need to ask is:

  1. Will FP > TP happen with your data and the model.
  2. Does FP > TP matter for your business problem.

If the answer is yes for both, then ROC only is not fit for use.

enter image description here

If the problem is identifying shoplifters and FP will alarm the police. Almost all the shop customers are honest, then catching more honest customers as shoplifters than real ones will cause angry customers and police. Then looking at only ROC will not be a good idea to measure the model.

If the problem is identifying potentially fatal food for toddlers, FP > TP may not be a big issue because there will be so many safe food (TN) as long as TPR is really high. Then ROC will be fit for use to measure the model.

FP: False Positive
TP: True Positive
FPR: False Positive Rate
TPR: True Positive Rate

Suppose I am running a risky loan business where many customers can be risky. If I evaluate the business performance with ROC only, I think the performance is good because TPR is high and FPR is low, although actually the business is losing money because of FP > TP. By looking at PR, it will tell the low precision and I will understand the business performance is bad as I am looking money.

enter image description here

Using ROC can miss the low precision where FP > TP because ROC only look at TPR and FPR. I think what we need to ask is:

  1. Will FP > TP happen with your data and the model.
  2. Does FP > TP matter for your business problem.

If the answer is yes for both, then ROC only is not fit for use.

enter image description here

If the problem is identifying shoplifters and FP will alarm the police. Almost all the shop customers are honest, then catching more honest customers as shoplifters than real ones will cause angry customers and police. Then looking at only ROC will not be a good idea to measure the model.

If the problem is identifying potentially fatal food for toddlers, FP > TP may not be a big issue because there will be so many safe food (TN) as long as TPR is really high. Then ROC will be fit for use to measure the model.

FP: False Positive
TP: True Positive
FPR: False Positive Rate
TPR: True Positive Rate

Suppose I am running a risky loan business where majority of the customers are risky. If I evaluate the business performance with ROC only, I think the performance is good because TPR is high and FPR is low, although actually the business is losing money because of FP > TP. By looking at PR, it will tell the low precision and I will understand the business performance is bad as I am looking money.

enter image description here

added 424 characters in body
Source Link
mon
  • 1.6k
  • 11
  • 20

Using ROC can miss the low precision where FP > TP because ROC only look at TPR and FPR. I think what we need to ask is:

  1. Will FP > TP happen with your data and the model.
  2. Does FP > TP matter for your business problem.

If the answer is yes for both, then ROC only is not fit for use.

enter image description here

If the problem is identifying shoplifters and FP will alarm the police. Almost all the shop customers are honest, then catching more honest customers as shoplifters than real ones will cause angry customers and police. Then looking at only ROC will not be a good idea to measure the model.

If the problem is identifying potentially fatal food for toddlers, FP > TP may not be a big issue because there will be so many safe food (TN) as long as TPR is really high. Then ROC will be fit for use to measure the model.

FP: False Positive
TP: True Positive
FPR: False Positive Rate
TPR: True Positive Rate

Suppose I am running a risky loan business where many customers can be risky. If I evaluate the business performance with ROC only, I think the performance is good because TPR is high and FPR is low, although actually the business is losing money because of FP > TP. By looking at PR, it will tell the low precision and I will understand the business performance is bad as I am looking money.

enter image description here

Using ROC can miss the low precision where FP > TP because ROC only look at TPR and FPR. I think what we need to ask is:

  1. Will FP > TP happen with your data and the model.
  2. Does FP > TP matter for your business problem.

If the answer is yes for both, then ROC only is not fit for use.

enter image description here

If the problem is identifying shoplifters and FP will alarm the police. Almost all the shop customers are honest, then catching more honest customers as shoplifters than real ones will cause angry customers and police. Then looking at only ROC will not be a good idea to measure the model.

If the problem is identifying potentially fatal food for toddlers, FP > TP may not be a big issue because there will be so many safe food (TN) as long as TPR is really high. Then ROC will be fit for use to measure the model.

FP: False Positive
TP: True Positive
FPR: False Positive Rate
TPR: True Positive Rate

Using ROC can miss the low precision where FP > TP because ROC only look at TPR and FPR. I think what we need to ask is:

  1. Will FP > TP happen with your data and the model.
  2. Does FP > TP matter for your business problem.

If the answer is yes for both, then ROC only is not fit for use.

enter image description here

If the problem is identifying shoplifters and FP will alarm the police. Almost all the shop customers are honest, then catching more honest customers as shoplifters than real ones will cause angry customers and police. Then looking at only ROC will not be a good idea to measure the model.

If the problem is identifying potentially fatal food for toddlers, FP > TP may not be a big issue because there will be so many safe food (TN) as long as TPR is really high. Then ROC will be fit for use to measure the model.

FP: False Positive
TP: True Positive
FPR: False Positive Rate
TPR: True Positive Rate

Suppose I am running a risky loan business where many customers can be risky. If I evaluate the business performance with ROC only, I think the performance is good because TPR is high and FPR is low, although actually the business is losing money because of FP > TP. By looking at PR, it will tell the low precision and I will understand the business performance is bad as I am looking money.

enter image description here

edited body
Source Link
mon
  • 1.6k
  • 11
  • 20

Using ROC can miss the low precision where FP > TP because ROC only look at TPR and FPR. I think what we need to ask is:

  1. Will FP > TP happen with your data and the model.
  2. Does FP > TP matter for your business problem.

If the answer is yes for both, then ROC only is not fit for use.

enter image description hereenter image description here

If the problem is identifying shoplifters and FP will alarm the police. Almost all the shop customers are honest, then catching more honest customers as shoplifters than real ones will cause angry customers and police. Then looking at only ROC will not be a good idea to measure the model.

If the problem is identifying potentially fatal food for toddlers, FP > TP may not be a big issue because there will be so many safe food (TN) as long as TPR is really high. Then ROC will be fit for use to measure the model.

FP: False Positive
TP: True Positive
FPR: False Positive Rate
TPR: True Positive Rate

Using ROC can miss the low precision where FP > TP because ROC only look at TPR and FPR. I think what we need to ask is:

  1. Will FP > TP happen with your data and the model.
  2. Does FP > TP matter for your business problem.

If the answer is yes for both, then ROC only is not fit for use.

enter image description here

If the problem is identifying shoplifters and FP will alarm the police. Almost all the shop customers are honest, then catching more honest customers as shoplifters than real ones will cause angry customers and police. Then looking at only ROC will not be a good idea to measure the model.

If the problem is identifying potentially fatal food for toddlers, FP > TP may not be a big issue because there will be so many safe food (TN) as long as TPR is really high. Then ROC will be fit for use to measure the model.

FP: False Positive
TP: True Positive
FPR: False Positive Rate
TPR: True Positive Rate

Using ROC can miss the low precision where FP > TP because ROC only look at TPR and FPR. I think what we need to ask is:

  1. Will FP > TP happen with your data and the model.
  2. Does FP > TP matter for your business problem.

If the answer is yes for both, then ROC only is not fit for use.

enter image description here

If the problem is identifying shoplifters and FP will alarm the police. Almost all the shop customers are honest, then catching more honest customers as shoplifters than real ones will cause angry customers and police. Then looking at only ROC will not be a good idea to measure the model.

If the problem is identifying potentially fatal food for toddlers, FP > TP may not be a big issue because there will be so many safe food (TN) as long as TPR is really high. Then ROC will be fit for use to measure the model.

FP: False Positive
TP: True Positive
FPR: False Positive Rate
TPR: True Positive Rate
added 235 characters in body
Source Link
mon
  • 1.6k
  • 11
  • 20
Loading
Source Link
mon
  • 1.6k
  • 11
  • 20
Loading