From 7e196a8a650f623c221f39e70cdfbe2806c222ab Mon Sep 17 00:00:00 2001
From: Valentin Leonard Tabacaru <42213638+vltabacaru@users.noreply.github.com>
Date: Thu, 17 Aug 2023 11:57:12 +0200
Subject: [PATCH] Quarterly QA LWMS ID 6601

---
 .../initialize-environment-novnc.md                       | 2 +-
 oml4py/introduction/introduction.md                       | 2 +-
 use-case/use-case.md                                      | 8 ++++----
 3 files changed, 6 insertions(+), 6 deletions(-)

diff --git a/oml4py/initialize-environment-novnc/initialize-environment-novnc.md b/oml4py/initialize-environment-novnc/initialize-environment-novnc.md
index bd2d79f0..348b45eb 100644
--- a/oml4py/initialize-environment-novnc/initialize-environment-novnc.md
+++ b/oml4py/initialize-environment-novnc/initialize-environment-novnc.md
@@ -7,7 +7,7 @@ This lab will show you how launch Jupyter Notebooks in your NoVNC instance.
 
 Watch the video below for a quick walk through of the lab.
 
-[](youtube:HI9iczwKwJ4)
+[OML4Py Workshop Walk-through](youtube:HI9iczwKwJ4)
 
 ### Objectives
 * Get familiar with the lab Instance
diff --git a/oml4py/introduction/introduction.md b/oml4py/introduction/introduction.md
index 8e93f6a4..bfe77ad3 100644
--- a/oml4py/introduction/introduction.md
+++ b/oml4py/introduction/introduction.md
@@ -14,7 +14,7 @@ Oracle Machine Learning for Python (OML4Py) is a component of Oracle Database, t
 
 Watch the video below on introduction to Oracle Machine Learning for Python.
 
-[] (youtube:P861m__PEMQ)
+[Oracle Machine Learning for Python](youtube:P861m__PEMQ)
 
 ### Objectives
 
diff --git a/use-case/use-case.md b/use-case/use-case.md
index 013de90a..3f55cafb 100644
--- a/use-case/use-case.md
+++ b/use-case/use-case.md
@@ -26,21 +26,21 @@ In this lab, you will:
 ## Task 1: Review the Customer Insurance Data
 
 1. Review the historical customer data.  Note the Buy Insurance column.  
-  ![customer-data-1](./images/customer-data-1.png)
+  ![historical customer data](./images/customer-data-1.png)
 
 2. Note the LTV and LTV\_BIN columns. LTV gives us a numerical score of the life time value of the customer, and LTV\_BIN is just a readable category derived from the score with VERY HIGH, HIGH, MEDIUM, and LOW business value.
 
-  ![customer-data-2](./images/customer-data-2.png)
+  ![LTV and LTV_BIN columns](./images/customer-data-2.png)
 
 Since the data already has the buy insurance and LTV information and the other data, we can use all this information in machine learning to "train" and build a model that can predict new customer outcomes for buy insurance and LTV.
 
 3. Consider the following new customer records with the buy insurance column empty.
 
-  ![customer-data-3](./images/customer-data-3.png)
+  ![new customer records](./images/customer-data-3.png)
 
 4. And with the LTV and LTV_BIN columns empty.
 
-  ![customer-data-4](./images/customer-data-4.png)
+  ![LTV and LTV_BIN columns empty](./images/customer-data-4.png)
 
 5. In this workshop, you will pass new records to machine learning models to predict whether the customer will buy the insurance and automatically determine the LTV without humans.  Have fun.