diff --git a/README.md b/README.md
index b2b05f5c..721c64c7 100644
--- a/README.md
+++ b/README.md
@@ -1,5 +1,5 @@
 # undp-data-challenge
-This repo contains the ml-code and front-end code for the weed-detection solution with UNDP data+
+This repo contains the ml-code and front-end code for the weed-detection solution with UNDP crop and weed seedlings dataset : https://www.kaggle.com/vbookshelf/v2-plant-seedlings-dataset
 
 * ml-code directory contains the scripts to process UNDP data and train the weed detection model. It also contains the azure ml model registration & deployment workflow
 * frontend-app directory contains the angular application which connects to the weed detection prediction API and retrieve results.