added new overview

anshuhan · Nov 12, 2020 · 0a2d15d · 0a2d15d
1 parent 6a3d1a3
commit 0a2d15d
Show file tree

Hide file tree

Showing 2 changed files with 29 additions and 18 deletions.
diff --git a/11_stream/00_Overview.ipynb b/11_stream/00_Overview.ipynb
@@ -4,9 +4,35 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Continuous Machine Learning over Streaming Data\n",
+    "# Continuous Analytics and Machine Learning over Streaming Data\n",
     "\n",
-    "Streaming technology provides you with the tools to ingest data as it is generated, process the data on-the-fly, and run real-time analytics on the data which can trigger actions. AWS offers a range of streaming tools as part of the [Amazon Kinesis](https://aws.amazon.com/kinesis/) family of services. "
+    "Streaming technologies provide you with the tools to collect, process, and analyze data streams in real time. AWS offers a wide range of streaming technology options including Amazon Managed Streaming for Apache Kafka (Amazon MSK), and the [Amazon Kinesis](https://aws.amazon.com/kinesis/) family of services. \n",
+    "\n",
+    "With Kinesis Data Firehose, you can prepare and load the data continuously to a destination of your choice. With Kinesis Data Analytics, you can process and analyze the data as it arrives. And with Kinesis Data Streams, you can manage the ingest of data streams for custom applications. \n",
+    "\n",
+    "In this section, we move from our customer reviews training dataset into a real-world scenario. Customer feedback about products appear in all of a company's social media channels, on partner websites, in customer support messages etc. We need to capture this valuable customer sentiment about our products as quickly as possible to spot trends and react fast.\n",
+    "\n",
+    "We will focus on analyzing a continuous stream of product review messages that we collect from all available online channels. "
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "<img src=\"img/online_reviews_architecture.png\" width=\"100%\" align=\"left\">"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "In a first step, we analyze the sentiment of the customer, so we can identify which customers  might need high-priority attention. \n",
+    "\n",
+    "Next, we run continuous streaming analytics over the incoming review messages to capture the average sentiment per product category. We visualize the continuous average sentiment in a metrics dashboard for the line of business owners. The line of business owners can now detect sentiment trends quickly,  and take action. \n",
+    "\n",
+    "We also calculate an anomaly score of the incoming messages to detect anomalies in the data schema or data values. In case of a rising anomaly score, we can alert the application developers in charge to investigate the root cause. \n",
+    "\n",
+    "As a last metric, we also calculate a continuous approximate count of the received messages. This number of online messages could be used by the digital marketing team to measure effectiveness of social media campaigns."
    ]
   },
   {
@@ -30,20 +56,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "## In the following noteboooks, we will show you how you can start implementing continuous machine learning using the Kinesis streaming services. \n",
-    "\n",
-    "* Create a **Kinesis Data Firehose** delivery stream to receive live customer review data, and write the streaming data to S3.\n",
-    "* Invoke a **SageMaker Endpoint** to predict the `star_rating` on streaming data (incoming reviews)\n",
-    "* Analyze Streaming Data with **Kinesis Data Analytics** (calculate average star rating, approximate count, and detect anomalies)\n",
-    "* Use **Kinesis Data Streams** to deliver streaming data to custom consumer applications"
-   ]
-  },
-  {
-   "cell_type": "markdown",
-   "metadata": {},
-   "source": [
-    "# Use Case 1: \n",
-    "# Invoke a SageMaker Endpoint from Kinesis to receive a `star_rating` prediction "
+    "# Ingest Streaming Data Using Kinesis Data Firehose"
    ]
   },
   {
@@ -78,7 +91,6 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Use Case 2: \n",
     "# Analyze Streaming Data with Kinesis Data Analytics\n",
     "\n",
     "## _Calculating AVG Star Rating_"
@@ -123,7 +135,6 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "# Use Case 3: \n",
     "# Implement Incremental Model Training with Streaming Data using Multi-Armed Bandit models"
    ]
   },

diff --git a/11_stream/img/online_reviews_architecture.png b/11_stream/img/online_reviews_architecture.png