From defb1ac082a3572fd57c1b81d26f3636bc1740d3 Mon Sep 17 00:00:00 2001
From: Anunay013 <58124584+Anunay013@users.noreply.github.com>
Date: Sun, 3 Jan 2021 14:32:03 -0500
Subject: [PATCH] Update predictive-modeling.md

For Q3, only L1 should be used as a regularization technique because it is robust to outliers where as L2 is not
---
 predictive-modeling.md | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/predictive-modeling.md b/predictive-modeling.md
index 73dc86f..b06094b 100644
--- a/predictive-modeling.md
+++ b/predictive-modeling.md
@@ -19,7 +19,7 @@
 - Solution to covariate shift
   - importance weighted cv
 #### 3. What are some ways I can make my model more robust to outliers?
-- We can have regularization such as L1 or L2 to reduce variance (increase bias).
+- We can have regularization such as L1 to reduce variance (increase bias).
 - Changes to the algorithm:
   - Use tree-based methods instead of regression methods as they are more resistant to outliers. For statistical tests, use non parametric tests instead of parametric ones.
   - Use robust error metrics such as MAE or Huber Loss instead of MSE.