Update binary-classification-customer-relationship-prediction.md

articles/samples/binary-classification-customer-relationship-prediction.md

@@ -36,7 +36,7 @@ First, some simple data processing.
 
 - Then use the Boosted Decision Tree binary classifier with the default parameters to build the prediction models. Build one model per task, that is, one model each to predict up-selling, appetency, and churn.
 
-- In the right part of the pipeline, we use **SMOTE** module to increase the percentage of positive examples. The SMOTE percentage is set to 100 to double the positive examples. Learn more on how SMOTE module works with [SMOTE module reference0](algorithm-module-reference/smote.md).
+- In the right part of the pipeline, we use **SMOTE** module to increase the percentage of positive examples. The SMOTE percentage is set to 100 to double the positive examples. Learn more on how SMOTE module works with [SMOTE module reference0](https://aka.ms/aml/smote).
 
 ## Results