diff --git a/ml2/3_7_SVM.ipynb b/ml2/3_7_SVM.ipynb
index a24939e..b569717 100644
--- a/ml2/3_7_SVM.ipynb
+++ b/ml2/3_7_SVM.ipynb
@@ -276,7 +276,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "We can evaluate the accuracy if the model always predict the most frequent class, following this [refeference](http://blog.kaggle.com/2015/10/23/scikit-learn-video-9-better-evaluation-of-classification-models/)."
+    "We can evaluate the accuracy if the model always predict the most frequent class, following this [reference](https://medium.com/analytics-vidhya/model-validation-for-classification-5ff4a0373090)."
    ]
   },
   {