Web Analytics by Dr. Robert J. Boncella Professor of Information ...

1

Web Analytics: A Brief Tutorialby

Dr. Robert J. BoncellaProfessor of Information Systems & Technology

School of BusinessWashburn University

Presented March 2008

ToSAIS 2008

2

Introduction• Web analytics is the study of the behavior of

website visitors. • In a commercial context, web analytics refers

to the use of data collected from a web site to determine which aspects of the website achieve the business objectives

• Tutorial Outline– Web Analytics: Context– Web Analytics: Technology & Terminology– Web Analytics: Tools and Case Studies

3

Context for Web Analytics• DSS – Decision Support System

– A conceptual framework for a process of supporting managerial decision- making, usually by modeling problems and employing quantitative models for solution analysis

• BI - Business Intelligence subset of DSS– An umbrella term that combines architectures, tools, databases,

applications, and methodologies

• BA - Business Analytics subset of BI– The application of models directly to business data– Assists in making strategic decisions

• WA - Web Analytics subset of BA– The application of business analytics activities to Web-based

processes, including e-commerce

4

Web Analytics - Details• Relevant Technology

– Internet & TCP/IP– Client / Server Computing– HTTP (HyperText Transfer Protocol)– Server Log Files & Cookies– Web Bugs

• Data Collection – The Clickstream

• Server Log Files• Page Tagging

• Data Analysis– Data Preparation– Pattern Discovery– Pattern Analysis

5

Client Server

This is a response

This is a request

Client/Server Computing

Internet & TCP/IP• The Internet

– The infrastructure that provides for the delivery of data between computer based processes

• TCP/IP– The protocols that provides for reliable

delivery of data on The Internet

6

7

HTTP Protocol• Client sends a request to a server• Server sends a response to client• Connectionless

– Client: • Opens connection to server• Sends request

– Server• Responds to request• Closes connection

• Stateless– Client/Server have no memory of prior

connections– Server cannot distinguish one client request from

another client

8

Cookies• Used to solve the “Statelessness” of the HTTP

Protocol• Used to store and retrieve user-specific

information on the web• When an HTTP server responds to a request it

may send additional information that is stored by the client - “state information”

• When client makes a request to this server the client will return the “cookie” that contains its state information

• State information may be a client ID that can be used as an index to a client data record on the server

9

ClientBrowser

My_Brwsr

Server BServer C

WBS Server A

Cookie: My_BrwsrPg A - Server APg B - Server BPg C - Server C

1. Render page2. Click on URL

Page B cnts- URLs & Img Src- WebBug Img@ WBS. TRKSTRM.COM

Page A cnts- URLs & Img Src- WebBug Img @ WBS. TRKSTRM.COM

Page C cnts- URLs & Img Src- WebBug Img@ WBS. TRKSTRM.COM

Req: Page_B.html

Req: Page_A.html

Res: Page_A.html

Req: WebBug IMG-Referer Header- Any cookie for TRKSTRM.com

Res: WebBug Img-Cookie to client Browser on 1st Req.

Res: Page_B.html

Res: Page_C.html

Req: Page_C.html

Web Bug Process

10

Common Clickstream Data Sources

• Server Log Files– Passive data collection– Normal part of web browser/ web server

transaction• Page Tagging

– Active data collection– Often requires a third party to implement – a

vendor

11

Server Log Files

• The name & IP address of the client computer• The time of the request• The URL that was requested• The time it took to send the resource• If HTTP authentication used; the username of

the user of the client will be recorded• Any errors that occurred• The referer link • The kind of web browser that was used

Each time a client requests a resource the server of that resource may record the following in its log files:

12

Server Log Files• Example

– 127.0.0.1 - frank [10/Oct/2000:13:55:36 -0700] "GET /apache_pb.gif HTTP/1.0" 200 2326

• 127.0.0.1 – Remote host• frank - user name• [10/Oct/2000:13:55:36 -0700] - date & time• "GET /apache_pb.gif HTTP/1.0" - request• 200 - status• 2326 - bytes

13

Server Log Files

• Technical issues for server log data– Data Preparation– Pageview Identification– User Identification– Session Identification

14

Page Tags as Data Source

• Provided by Third Party - Vendor– Vendor Supplies Page Tags– Vendor Collects the Data– Vendor Analyzes the Data– Business Accesses the Data

• Online or• Reports sent to Business

15

Web Data Abstractions

• Abstractions concerning Web usage, Content, and Structure

• Establishes precise semantics for the concepts – Web site– Users or Visitors– User Sessions– Server Sessions or Visits– Pageviews– Clickstreams

16

Data Abstractions• Web Site - collection of interlinked Web pages,

including a host page, residing at the same network location.

• User or Visitors - principal using a client to interactively retrieve and render resources or resource manifestations– an individual that is accessing files from a

Web server, using a browser. • User Session - a delimited set of user clicks

across one or more Web servers

17

Data Abstractions• Server Session or Visit - a collection of user

clicks to a single Web server during a user session

• Pageview - the visual rendering of a Web page in a specific environment at a specific point in time– a pageview consists of several items

• frames, text, graphics, and scripts that construct a single Web page

• Clickstream - a sequential series of pageview requests made from a single user

18

Web Data Abstractions (High Level)

• Abstractions concerning Visitors• Establishes precise semantics for the concepts

– Unique Visitor– Conversion Rate– Abandonment Rate– Attrition– Loyalty– Frequency– Recency

19

Data Abstractions

• Unique Visitor– A unique visitor is counted when a human being uses

a web browser to visit a web site.– A visitor may be “unique” for different periods of time.– The individual is defined by a cookie in the visitor’s

web browser

20

Data Abstractions

• Conversion Rate– A conversion rate is the number of “completers”

divided by the number of “starters” for any online activity that is more than one logical step in length

– Starting and finishing any activity• Purchase• Download a research article• Etc.

21

Data Abstractions

• Abandonment Rate– The abandonment rate for any step in a multi-step

process is one minus the number of units that make it to “step n+1” divided by those at “step n”

– The formula is (1 – ((n+1)/n)– Consider a 10 step process to acquire a resource

• How any quit after step 1 or 2 or 3 or 4 or …

– Consider a 5 step process to acquire a resource• How any quit after step 1 or 2 or 3 or 4 or …

22

Data Abstractions

• Attrition– Attrition is a measurement of people you have been

able to successfully convert but are unable to retain to convert again

– Consider e-bay web site vs. web site for technical information

23

Data Abstractions

• Loyalty– Loyalty is a measure of the number of visits any

visitor is likely to make over their lifetime as a visitor– Reported as number of visits per visitor

• 100 visitors made 3 visits each, 87 visitors made 4, etc.• Avoid double counting (i.e. do not count the 87 in with the

100)

24

Data Abstractions

• Frequency– Frequency is a measure of the activity a visitor

generates on a web site in terms of time between visits

– Measured in terms of “days between visits”

25

Data Abstractions

• Recency– Recency is the number of days since the last visit (or

purchase)– Reported as the number of visitors who returned after

“n” days.

26

Pyramid Model of Web Analytics Data

Hits

Page Views

Visits

Unique Visitors

Uniquely Identified Visitors

Volume of Available Data

Incr

easin

g Va

lue o

f Dat

a

27

Web Usage Mining

• Web usage mining is to apply statistical and data mining techniques to the processed server log data, in order to discover useful patterns

• Data mining methods and algorithms that have been adapted for the Web domain– Association rules– Sequential pattern discovery– Clustering– Classification

28

Web Usage Data Mining• After discovering patterns from usage data, a

further analysis has to be conducted. • Common ways of analyzing such patterns

– Using a query mechanism on a database where the results are stored

– Loading the results into a data cube and then performing OLAP operations

– Visualization techniques are used for an easier interpretation of the results

• Using these results in association with content and structure information concerning the Web site there can be extracted useful knowledge for modifying the site according to the correlation between user and content groups.

29

Web Analytics: Tools and Case Studies

• Tools– VisiStat - www.visistat.com

• Web Analytics Case Studies– Communications Provider - TuVox.com– Online Retailer - TicketsByInternet.com – Winery & Entertainment Venue - The Mountain Winery – Non-Profit Organization - SFBallet.org – Public Relations & Media Agency - BLASTmedia– Technology Provider for Real Estate Professionals - Pullan.com – Real Estate Agency - Intero Real Estate – Start-Up Online Business - GuruPrint.com