Return to Answer

By this definition: "Overfitting occurs when a statistical model describes random error or noise instead of the underlying relationship."(wikipedia), the solution is not overfitting.

But in this situation:

• Test data is a stream of items and not a fixed set of items.
  OR
  
• Prediction process should not contain learning phase (for example because of performance issues)
  
  the mentioned solution is overfitting. Because the accuracy of modeling is more than real situations.

By this definition: "Overfitting occurs when a statistical model describes random error or noise instead of the underlying relationship."(wikipedia), the solution is not overfitting.

But in this situation:

• Test data is a stream of items and not a fixed set of items.
  OR
  
• Prediction process should not contain learning phase (for example because of performance issues)
  
  The mentioned solution is overfitting. Because the accuracy of modeling is more than real situations.

By this definition: "Overfitting occurs when a statistical model describes random error or noise instead of the underlying relationship."(wikipedia), the solution is not overfitting.

But in this situation:

• Test data is a stream of items and not a fixed set of items OR
• Prediction process should not contain learning phase (for example because of performance issues) the mentioned solution is overfitting. Because the accuracy of modeling is more than real situations.

By this definition: "Overfitting occurs when a statistical model describes random error or noise instead of the underlying relationship."(wikipedia), the solution is not overfitting.

But in this situation: 

• Test data is a stream of items and not a fixed set of items.
  OR 
  
• Prediction process should not contain learning phase (for example because of performance issues) 
  
  the mentioned solution is overfitting. Because the accuracy of modeling is more than real situations.

By this definition: "Overfitting occurs when a statistical model describes random error or noise instead of the underlying relationship."(wikipedia), that's not overfitting. But if you think Overfitting is a condition that model can predict current data better than future data, I say Yes, that's overfitting. because if you want to reach that's accuracy with any other data you should do whole of learning part. Also that solution work just on a new sets of data and not a single case.

By this definition: "Overfitting occurs when a statistical model describes random error or noise instead of the underlying relationship."(wikipedia), the solution is not overfitting.

But in this situation:

• Test data is a stream of items and not a fixed set of items OR
• Prediction process should not contain learning phase (for example because of performance issues) the mentioned solution is overfitting. Because the accuracy of modeling is more than real situations.