diff --git a/.obsidian/plugins/harper/data.json b/.obsidian/plugins/harper/data.json
index 2b69b77..296bd5c 100644
--- a/.obsidian/plugins/harper/data.json
+++ b/.obsidian/plugins/harper/data.json
@@ -1,5 +1,5 @@
 {
-  "ignoredLints": "{\"context_hashes\":[15865895689566000533,6119222255552956109,11253296314840191199,16721049695819994954,8216002975862858808,214610641060740680,9548152354067699590]}",
+  "ignoredLints": "{\"context_hashes\":[214610641060740680,11253296314840191199,9548152354067699590,16721049695819994954,6119222255552956109,15865895689566000533,8216002975862858808]}",
   "useWebWorker": true,
   "lintSettings": {
     "ACoupleMore": null,
@@ -430,6 +430,7 @@
   },
   "userDictionary": [
     "Mariama",
+    "Undersampling",
     "csb320",
     "frc",
     "hea150",
diff --git a/Wiki/Machine Learning/Imbalanced Data.md b/Wiki/Machine Learning/Imbalanced Data.md
new file mode 100644
index 0000000..1dd6c58
--- /dev/null
+++ b/Wiki/Machine Learning/Imbalanced Data.md	
@@ -0,0 +1,7 @@
+#machine_learning 
+- - -
+
+## Methods
+### Undersampling
+Undersampling is one of the easiest ways to deal with imbalanced data. The idea is that you remove samples from the majority class at random until the two classes have an equal number of instances. This approach is simple and comes with the advantage that no synthetic data ne
+### Oversampling