diff --git a/0_2_Dataset_construction.py b/0_2_Dataset_construction.py
index 26e3ad3..917dee9 100644
--- a/0_2_Dataset_construction.py
+++ b/0_2_Dataset_construction.py
@@ -122,7 +122,10 @@ def dataset_construction(min_date, end_features_date, max_date, directory_path):
     dataset = pd.merge(df_customer_product, y, on = ['customer_id'], how = 'left')
 
     # 0 if there is no purchase
-    dataset[['y_has_purchased']].fillna(0)    
+    dataset[['y_has_purchased']].fillna(0)
+
+    # add id_company prefix to customer_id
+    dataset['customer_id'] = directory_path + '_' + dataset['customer_id'].astype('str')
     
     return dataset