35.txt

This complete matlab for neural network

发信人: helloboy (hello), 信区: DataMining
标  题: personalization on the web
发信站: 南京大学小百合站 (Sat Mar 23 10:27:55 2002), 站内信件

http://www7b.boulder.ibm.com/wsdd/library/techarticles/hvws/personalize.html

Web site personalization
IBM High-Volume Web site team
January 2000

This paper introduces current and future techniques for personalizing your W
eb site. Techniques for maximizing the performance of personalized Web sites
, such as content caching, are also discussed.
A successful e-business Web site gives special treatment to its repeat visit
ors who buy. Does yours? If it doesn't, you know it needs to. If it already 
does, you know it can do better. And even if it's pretty good, it could be f
aster. Providing special treatment in the form of information and applicatio
ns matched to a visitor's interests, roles, and needs is known as personaliz
ation. A personalized e-business site is more likely to attract and retain v
isitors and to build sales. Personalized sites for employees improve their p
roductivity by simplifying access to information and applications. Overall c
ustomer satisfaction is increased when less time is required to locate accou
nt information, and service is personalized to the customer's needs. Two com
mon reasons for personalizing a site are to make the site easier to use and 
to increase sales.
Personalization is a process of gathering and storing information about site
 visitors, analyzing the information, and, based on the analysis, delivering
 the right information to each visitor at the right time. A number of person
alization techniques, with more on the way, can enable your site to target a
dvertising, promote products, personalize news feeds, recommend documents, m
ake appropriate advice, and target e-mail.
Providing personalization for real-time applications affects the system perf
ormance. How personalization is deployed is thus important and needs to be i
ntegrated into the overall system design. This is especially true for high-v
olume Web sites. As described in "Design for scalability" (see Resource 1), 
your selection of personalization techniques should be directed by your Web 
site type. In our work with high-volume Web sites, IBM determined there are 
generally five types of sites, distinguished by workload pattern: publish/su
bscribe, online shopping, customer self-service, trading, and business-to-bu
siness. Regardless of type, Web sites look increasingly to the use of person
alization to increase repeat business.
This paper introduces personalization and describes some current techniques.
 It also explains how personalization affects the system performance and int
roduces techniques such as content caching, also called intelligent content 
distribution, for implementing appropriate, effective personalization while 
still meeting the performance requirements of high-volume e-business sites. 
Finally, the paper suggests what we believe to be the most effective persona
lization techniques for each type of Web site.
The information contained in this document has not been submitted to any for
mal IBM test and is distributed as is. The use of this information or the im
plementation of any of these techniques is a customer responsibility and dep
ends on the customer's ability to evaluate and integrate the techniques into
 the customer's operational environment. While each item may have been revie
wed by IBM for accuracy in a specific situation, there is no guarantee that 
the same or similar results will be obtained elsewhere. Customers attempting
 to adapt these techniques to their own environments do so at their own risk
.
Introducing personalization
Personalization is a process of gathering and storing information about site
 visitors, analyzing the information, and, based on the analysis, delivering
 the right information to each visitor at the right time. It is a key techno
logy needed in various e-business applications, such as:
Managing customer relationships
Targeting advertisements and promoting products
Managing marketing campaigns
Managing Web site content
Managing knowledge
Managing personalized portals and channels
Although each application area may need tailoring, especially in the areas o
f user interface and data collection, the core techniques for personalizatio
n, depicted in Figure 1, are quite similar.
Figure 1. Elements of a personalization system
Personalization has gone through different phases. Initially, personalizatio
n was used to keep the visitor on the site, exploring more of the site, whic
h provided opportunities to advertise and promote products. The next phase a
ttempted to increase how much money a visitor spent at each visit by offerin
g more expensive or related products. Today, personalization is increasingly
 used as a means to expedite the delivery of information to a visitor, makin
g the site useful and attractive to return to.
In July 1999, Forrester Research published a report, "Smart Personalization"
 (see Resource 2), describing their research to-date on why and how companie
s implement personalization. e-businesses want personalization to accomplish
 goals that range from making their sites easier to use to increasing sales.
 The overarching goal is to increase repeat business. Companies use differen
t methods to personalize their e-business sites. The most common are tailore
d e-mail alerts, customized content, and account access.
True measurements of the results of installing personalization features are 
not available. Companies implement personalization simply because they think
 it's worth the investment. Depending on size and complexity of effort, some
 believe that an investment in personalization can be returned in less than 
12 months. Successful sites, such as Amazon.com and Garden.com, use rich pro
file information as the basis for providing valuable services. These sites a
re considered models for those who want to personalize their sites.
Custom pricing, customized content, targeted marketing, and advertising are 
more advanced personalization methods that require sophisticated data mining
. These methods rely on personalized Web pages and deliver business value by
 enabling site owners to determine how and when to change site content. Howe
ver, dynamically building such pages requires additional resources and may a
ffect overall system performance. Minimizing the impact of these pages requi
res a personalization engine that is scalable to handle a large number of re
quests, a large and complex content space, and the collection of customer in
formation.
Personalization techniques
This section introduces current techniques for collecting and analyzing info
rmation. Figure 2 is an overview of personalization techniques. The major st
eps -- collecting visitor information, filtering, and developing recommendat
ions -- may or may not be performed dynamically; part or all of some steps m
ay be performed offline, in batch mode, or even manually.
Collecting visitor information
The objective of collecting visitor information is to develop a profile that
 describes a site visitor's interests, role in an organization, entitlements
, purchases, or some other set of descriptors important to the site owner. T
he most common techniques are explicit profiling, implicit profiling, and us
ing legacy data:
Explicit profiling asks each visitor to fill out information or questionnair
es. This method has the advantage of letting customers tell the site directl
y what they want to see. An example is MyYahoo, where the visitor is asked t
o specify profile information, including, for example, what stocks to track 
and what news categories to report. MyYahoo dynamically constructs a persona
lized Web page accordingly.
Implicit profiling tracks the visitor's behavior. This technique is generall
y transparent to the visitor. Browsing and buying patterns are the behaviors
 most often assessed. The browsing pattern is usually tracked by saving spec
ific visitor identification and behavior information in what is called a coo
kie that is kept at the browser and updated at each visit. The buying patter
n is generally available in the customer purchase database. For example, Ama
zon.com logs each customer's buying history and, based on that history, reco
mmends specific purchases.
Using legacy data accesses legacy data for valuable profile information, suc
h as credit applications and previous purchases. For existing customers and 
known visitors, legacy data often provides the richest source of profile inf
ormation.
Figure 2. Overview of personalization techniques
The techniques can be combined to produce comprehensive profiles. Access to 
legacy data can be an important component of explicit or implicit profiling.
 Profile and legacy data become the metadata processed by the filtering tech
niques.
Analyzing visitor profiles
When the profile is available, the next step is to analyze the profile infor
mation in order to present or recommend documents, purchases, or actions spe
cific to the visitor. Making such recommendations is the most challenging st
ep. Many techniques for presenting content and making recommendations are in
 use or under development. Rule-based and filtering techniques are the best 
known.
Rule-based techniques
Rule-based techniques provide a visual editing environment for the business 
administrator to specify business rules to drive personalization. This requi
res the administrator, most likely with the help of a consultant, to figure 
out the appropriate rules. The rule-based approach provides a flexible mecha
nism to specify rules for business applications or marketing campaigns. IBM 
WebSphere provides a set of tools and services that enable an e-business dev
elopment team to easily create personalized Web sites.
Cross-selling is an e-business example of the rule-based technique. For exam
ple, a rule could be specified to offer product X to a customer who has just
 bought product Y; for example, a customer of a book might be interested in 
current or previous books by the same author or in books on the same subject
.
Rule-based techniques can be used with filtering techniques, either before o
r after the filtering process, to develop the best recommendation.
Filtering techniques
Filtering techniques employ algorithms to analyze meta data and drive presen
tation and recommendations. The three most common filtering techniques -- si
mple filtering, content-based filtering, and collaborative filtering -- are 
introduced below. These techniques are described in more detail in Appendix 
A: More on filtering techniques.
Simple filtering relies on predefined groups, or classes, of visitors to det
ermine what content is displayed or what service is provided. An example of 
simple filtering is managing access to corporate information. For example, e
mployees identified with the Human Resources department would have personali
zed Web sites that give them access to information and applications specific
 to their job. Online brokerages often classify their accounts by asset valu
e or age groups. Their sites could use simple filtering to provide preferent
ial treatment to customers based on whether they are in the silver, gold, or
 platinum account class. Or, referring to the age group, the site could reco
mmend savings accounts for college tuition or retirement.
Content-based filtering works by analyzing the content of the objects to for
m a representation of the visitor's interests. Generally, the analysis needs
 to identify a set of key attributes for each object and then fill in the at
tribute values. One example is a document filtering system that analyzes doc
uments based on keywords. Recommending video movie purchases is another exam
ple of content-based filtering. Content-based filtering is most suitable whe
n the objects are easily analyzed by computer and the visitor's decision abo
ut object suitability is not subjective.
Collaborative filtering collects visitors' opinions on a set of objects, usi
ng either explicit or implicit ratings, to form like-minded peer groups and 
then learns from the peer groups to predict a particular visitor's interest 
in an item. Instead of finding objects similar to those a visitor liked in t
he past, as in content-based filtering, collaborative filtering develops rec
ommendations by finding visitors with similar tastes. Recommendations produc
ed by collaborative filtering are based on the peer group's response and are
 not restricted to a simple profile matching. For product recommendations, c
ollaborative filtering is most suitable for homogeneous, simple products, su
ch as books, CDs, or videos.
The numbers of Web site types, personalization goals, and personalization me
thods suggest that none of the current techniques can satisfy all needs (see
 Resources 5 and 6). Generally speaking, different personalization technique
s are most suitable for different variables, such as type of Web site, Web s
ite component, or product/services. Consider the case of product recommendat
ions. Selling books or CDs requires techniques different from those required
 to sell groceries, computers, or apparel. A technique that improves on the 
best of the current techniques and offers additional options could satisfy a
 wider set of needs (see Resource 4). With a flexible architecture that allo
ws for multiple recommendation engines, each engine would use specific perso
nalization techniques to make its recommendations (see Resource 3). Such an 
architecture makes it easy to accommodate new techniques as technology evolv
es and new requirements develop.
Use content caching to maximize performance
Providing personalization for real-time applications, such as dynamically co
nstructing Web pages based on the visitor's profile, affects system performa
nce. How personalization is deployed is thus important and needs to be integ
rated into the overall system design. This is especially true for high-volum
e Web sites.
Caching techniques have long been used to improve the system performance. Wi
th content caching, frequently accessed pages do not need to be retrieved re
motely or materialized at the server for each access. This can significantly
 reduce the latency for obtaining Web pages, as well as reduce the load on t
he server and network. In the Web environment, frequently accessed Web pages
 can be cached at the client browser, proxy servers, and server caches.
For caching to be effective, data needs to be reused frequently. With person
alization, each Web page may be specific to each visitor. Personalization id
entifies the visitor using a cookie or session logon, and dynamically genera
tes a page specific to the visitor. Dynamic pages are not cached at proxy se
rvers and most server caches. Even if the page were cached at the server or 
proxy, the likelihood of reusing a personalized page is low. Doing so would 
significantly impact cache hit rates. Note also that the CPU overhead at the
 Web server for creating personalized pages can be significantly higher than
 serving static pages. There can thus be a performance penalty for introduci