support & services / Education

Web Analytics & Web Intelligence Using SAS - BWAWI

As the Web has become more and more important for businesses, the need has emerged for sound measurement of the effectiveness of this channel and of the analytical tools to support continuous improvement of the customer experience. Online businesses gather an unprecedented amount of raw data about potential customers, but companies seek even more actionable insights (for example, by integrating their Web analytics data with data from offline sources, and applying advanced data mining techniques and predictive analytics to maintain deeper client relationships and enable one-to-one marketing).

This course provides an overview of state-of-the-art Web analytics, as well as of advanced data mining techniques and applications that are suitable to the context of the Web. It will provide a sound mix of theory and practice, illustrated by several real-life cases and hands-on exercises using SAS Web Analytics, SAS Enterprise Miner, and SAS/STAT software.

  Download course description as PDF     Register now  

Duration

2 Days - Classroom

Learn how to

  • gain a deep understanding of Web analytics and Web intelligence, and recognise how they can leverage Web site effectiveness and marketing measurement
  • identify and interpret key Web metrics and KPIs
  • understand the main data collection techniques, their impact on metrics, and their limitations
  • move from mere reporting of Web metrics to gaining actionable insights about how to optimise site design or online marketing efforts
  • explore the potential of data mining and predictive analytics in the context of the Web, and gain an understanding of the techniques involved and how to apply them.

Who should attend?

Web analysts who want to learn more about current best practices and trends, SAS solutions, and/or how to apply data mining techniques as part of their analyses; BI professionals, data analysts, or data miners, with experience in other areas of customer intelligence, who are in the process of incorporating Web channel data into their data warehouses or models, or developing custom BI solutions for Web analytics/mining; CRM/marketing analysts who want to improve their understanding of Web analytics/mining and its role within marketing

Prerequisites

Before attending this course, you should

  • have a basic understanding of the functioning of the Web and know how to use it for e-commerce and online advertising
  • have a basic background in descriptive statistics. You can review basic statistics by completing the Statistics I: Introduction to ANOVA, Regression, and Logistic Regression course.

Course Contents:

Introduction

  • definition, examples, and brief history
  • review of some basic WWW technologies and standards
  • clickstream analysis: core concepts
  • surveys: site-/page-level and post-visit surveys
  • usability research: expert review, lab/remote usability testing, and field research

Clickstream Data Collection Techniques

  • log analysis
  • page tagging
  • cookies (transient versus persistent, first- versus third-party)
  • Web bugs/beacons and packet sniffing
  • techniques compared: advantages and limitations; impact on the accuracy of metrics
  • vendors and tools; SAS Web Analytics Solution and services

Web Metrics and Key Performance Indicators

  • page views, visits (sessions), unique/new/return/repeat visitors
  • sessionisation
  • engagement: time on site/page, pages/visit, bounce rates, and so on
  • content: most popular pages, top entry/exit pages
  • event-driven metrics
  • measuring outcomes/actions: the conversion chain; conversion rates, drop-off (abandonment) rates, revenue, ROI, task completion rates, and so on

From Metrics to Actionable Insights: Monitoring and Analysis

  • monitoring; anomaly detection
  • trends analysis
  • benchmarking
  • dashboards
  • segmentation; OLAP, drill-down, slicing, and dicing
  • navigation analysis (path analysis funnel plots, site overlay)
  • experimentation: A/B or multivariate testing
  • Search Analytics and Search Engine Marketing (SEM) Measurement
  • internal site search analytics
  • search engine optimisation (SEO)
  • paid search or pay per click (PPC)

Descriptive Modeling for Web Intelligence

  • recap of hypothesis testing (comparing time on site, conversion rates)
  • Knowledge Discovery in Data (KDD) for Web analytics
  • data preprocessing
  • data miningpostprocessing
  • association rules for advanced Web usage mining
  • support/confidence/lift measures
  • sequence analysis for path detection
  • clustering (k-means)

Predictive Modeling for Web Intelligence

  • example applications (churn prediction, marketing response modeling, customer lifetime value modeling, and so on)
  • linear/logistic regression, decision trees, neural networks
  • performance measurement (confusion matrix, ROC analysis, lift, and so on)

Recommender Systems and Collaborative Filtering

  • examples (ebay, Netflix, and so on)
  • personalisation
  • content filtering (text mining)
  • collaborative filtering
  • user-user methods
  • item-item methods
  • vulnerabilities

Social Networks and Learning Using Networked Data

  • examples (Twitter, Facebook, and so on)
  • blog metrics
  • social network metrics (closeness, betweenness, and so on)
  • mining Web communities
  • social network inference
  • social network diffusion and viral marketing
  • components of a network learning system
  • relational classifiers (relational neighbor classifier, and so on)
  • collective inferencing (Gibbs sampling, iterative classification, and so on)
  • applications

Software Addressed

This course addresses SAS Enterprise Miner software.

Book Your Place Today