Accuracy is not always the best metric to evaluate unbalanced data.
– Especially in classification models such as Loan Prediction.
– Accuracy is basically the number of correct predictions out of the total number of predictions.
– In these cases, the use of accuracy is the same as using a telescope to examine microorganisms.

What do you think is the correct parameter?
– Precision and Recall are better metrics to evaluate both classes in classification models.
– Precision is of all the loans we labeled as 'Bad', how many were actually 'Bad'?
– Of all the 'bad loans' that actually exist, consider how many have you correctly labeled as 'bad'.

Sometimes the selection of accurate metrics to see how your model is working perfectly is extremely important!

Subscribe now to our channel: bit.ly/42tER5t

Free learning resources
– Data Science courses: https://www.youtube.com/playlist?listPLdKd-j64gDcDi1L1TUt_yGitDMsQ-UeYJ
– Data analysis courses: https://www.youtube.com/playlist?listPLdKd-j64gDcDbnQZeSBWumpT40nosLPDE
– Career in Data Technology: https://www.youtube.com/playlist?listPLdKd-j64gDcAJs7dBLQ_DPzjdDEFNZUjj
– AI Trends in Data Science: https://www.youtube.com/playlist?listPLdKd-j64gDcDt3WLLDPv7-v5u7ECibnXK

#evaluationmetric #accuracy #precision #recall #confusionmatrix #mlshorts #datashorts #ExplainedIn60

Please take the opportunity to connect and share this video with your friends and family if you find it helpful.