English | MP4 | AVC 1920×1080 | AAC 48KHz 2ch | 1h 12m | 237 MB
Analyze users behavior pattener on e-commerce site using Machine Learning
Learn to identify behaviour patterns based on the user actions on the web site using ML techniques
Nowadays web-sites needs to handle huge amount of traffic. We can leverage that fact and capture user interactions with the application. For further analysis.
Next, we can analyze users behavior and capture patterns on which we are able to react properly.
In applications that needs to deal with huge amount of traffic it is very hard to detect anomalies. We’ll learn how to apply clustering to find anomalies in web traffic. Next, we can analyze users behaviour and when they tend to do on our application using time series data. We will be using GMM clustering technique to achieve that.
On the e-commerce sites we want to predict when and what user wants to buy in the future. We can use the Hidden markov Model to find transitions between states and find the transition with highest probability.
What You Will Learn
- Understand K-Means Clustering to detect network traffic.
- Feature Normalization and Categorical Variables.
- Analyzing Time Series data using Clustering.
- Verifying and Validation of Model.
- Identifying Patterns using in time-series data using GMM.
- Explore explanation of Hidden Markov Model Explanation.
- Using HMM for defining transitions between states.
01 The Course Overview
02 Anomaly Detection
03 Analyzing and Loading Input Data in Spark
04 Implementing Clustering - Choosing Number of Clusters
05 Detecting Anomalies in Network Traffic
06 Analyzing Time Series Data Using Clustering
07 Implementing GMM in Apache Spark
08 Validation and Testing
09 Hidden Markov Model Explanation
10 Implementing HMM for Weather Forecast
11 Using HMM to Find State of a User
12 Graph Data for Anomaly Detection
13 Finding Anomalies in Social Network
14 Finding Suspicious Users in Social Network