《电子商务 E-business》阅读文献：Intelligent Database Systems Laboratory

Personalization Technologies: A Process-Oriented Perspective Communications of the ACM(October 2005) Presented by Gediminas Adomavicius Alexander tuzhilin Information and Decision Sciences, Carlson School of Management, University of Minnesota Information, Operation and Management Sciences, Stern School of Business, New York University Summerized By Jaeseok Myung

Personalization Technologies: A Process-Oriented Perspective Communications of the ACM (October 2005) Presented By Gediminas Adomavicius, Alexander Tuzhilin Information and Decision Sciences, Carlson School of Management, University of Minnesota Information, Operation and Management Sciences, Stern School of Business, New York University Summerized By Jaeseok Myung

Outline 口 Introduction Definitions Personalization engine a Personalization process Understand-Deliver-Measure Cycle ■ Data collection Build Customer profile ■ Matchmaking Delivery presentation Measuring personalization Impact Adjusting Personalization Strategy a Future Work on personalization process CEBT Center for E-Business Technology Copyright o 2008 by CEBT

Copyright © 2008 by CEBT Outline  Introduction ◼ Definitions ◼ Personalization Engine  Personalization Process ◼ Understand-Deliver-Measure Cycle ◼ Data Collection ◼ Build Customer Profile ◼ Matchmaking ◼ Delivery & Presentation ◼ Measuring Personalization Impact ◼ Adjusting Personalization Strategy  Future Work on Personalization Process Center for E-Business Technology

Definitions a Personalization is the ability to provide content and services that are tailored to individuals based on knowledge about their preferences and behavior [Smart Personalization", Forrester Report, 1999 a Personalization is the combined use of technology and customer information to tailor electronic commerce interactions between a business and each individual customer. Using information either previously obtained or provided in real-time bout the customer and other customers the exchange between the parties is altered to fit that customer's stated needs so that the transaction requires less timeanddeliversaproductbestsuitedtothatcustomer[www.personalzation.com] a Personalization is the capability to customize communication based on knowledge preferences and behaviors at the time of interaction [CRM Handbook, 2002 u These definitions state collectively that Tailors certain offerings By providers to the consumers Based on knowledge about them with certain goal in mind CEBT Center for E-Business Technology Copyright o 2008 by CEBT

Copyright © 2008 by CEBT Definitions  Personalization is the ability to provide content and services that are tailored to individuals based on knowledge about their preferences and behavior [“Smart Personalization”, Forrester Report, 1999]  Personalization is the combined use of technology and customer information to tailor electronic commerce interactions between a business and each individual customer. Using information either previously obtained or provided in real-time about the customer and other customers, the exchange between the parties is altered to fit that customer’s stated needs so that the transaction requires less time and delivers a product best suited to that customer [www.personalization.com]  Personalization is the capability to customize communication based on knowledge preferences and behaviors at the time of interaction [CRM Handbook, 2002]  These definitions state collectively that ◼ Tailors certain offerings ◼ By providers to the consumers ◼ Based on knowledge about them with certain goal in mind Center for E-Business Technology

Personalization engine a Personalized offers can be delivered from providers to consumers by personalization engines in three ways Consumers ovide Consu Providers (a) Provider-centric (b)Consumer-centric (c) Market-centric Figure 1. Classification of Personalization Approaches CEBT Center for E-Business Technology Copyright o 2008 by CEBT

Copyright © 2008 by CEBT Personalization Engine  Personalized offers can be delivered from providers to consumers by personalization engines in three ways Center for E-Business Technology

Personalization Process-(1) a Personalization constitutes an iterative process that can be defined by the Understand-De/lver-Measure cycle Understand consumers by collecting comprehensive information about them and converting it into actionable knowledge stored in consumer profiles Deliver personalized offering based on the knowledge about each consumer, as stored in the consumer profile Measure personalization impact by determining how much the consumer is satisfied with the delivered personalized offering Measure the personalization Impact Understand the visitors f Deliver personalized content CEBT Center for E-Business Technology Copyright o 2008 by CEBT

Copyright © 2008 by CEBT Personalization Process - (1)  Personalization constitutes an iterative process that can be defined by the Understand-Deliver-Measure cycle ◼ Understand consumers by collecting comprehensive information about them and converting it into actionable knowledge stored in consumer profiles ◼ Deliver personalized offering based on the knowledge about each consumer, as stored in the consumer profile ◼ Measure personalization impact by determining how much the consumer is satisfied with the delivered personalized offering Center for E-Business Technology Understand the visitors Deliver personalized content Measure the personalization impact

Personalization Process-(2) a the technical implementation of the Understand-Deliver-Measure cycle consists of the six stages Adjusting Personalization Strategy Measuring Personalization Impact Personalization Feedback a Delivery and Presentation Deliver LOOP Personalized Matchmaking Offerings key issues Building Consumer Profiles Understand the Consumer Data Collection CEBT Center for E-Business Technology Copyright o 2008 by CEBT

Copyright © 2008 by CEBT Personalization Process – (2)  The technical implementation of the Understand-Deliver-Measure cycle consists of the six stages Center for E-Business Technology key issues

Personalization Process-3) 1. Data Collection The objective is to obtain the most comprehensive picture of a consumer Various and heterogeneous data sources(Web phone, mail ,) Can be solicited explicitly or tracked implicitly 4. Delivery and presentation Delivery Method Push: Reaches a consumer who is not currently interacting with the system Pull Notify consumers that personalized information is available but display this information only when the consumer explicitly requests it Passive: displays personalized information as a by-product of other activities of the consumer Presentation Ordered by relevance unordered list of alternatives, or various types of visualization CEBT Center for E-Business Technology Copyright o 2008 by CEBT

Copyright © 2008 by CEBT Personalization Process – (3) 1. Data Collection ◼ The objective is to obtain the most comprehensive ‘picture’ of a consumer ◼ Various and heterogeneous data sources (Web, phone, mail, ..) ◼ Can be solicited explicitly or tracked implicitly 4. Delivery and Presentation ◼ Delivery Method – Push : Reaches a consumer who is not currently interacting with the system – Pull : Notify consumers that personalized information is available but display this information only when the consumer explicitly requests it – Passive : displays personalized information as a by-product of other activities of the consumer ◼ Presentation – Ordered by relevance, unordered list of alternatives, or various types of visualization Center for E-Business Technology

Personalization Process-( 4) 5. Measuring Personalization Impact Various accuracy metrics can be used to evaluate the personalization Consumer lifetime value loyalty value purchasing and consumption experience The quality of recommendations depends on the previous stages 6. Adjusting Personalization Strategy Feedback can be used to identify a part that needs improvements a The quality of interaction should grow over time One of the main challenges of personalization is the ability to achieve the virtuous cycle of personalization and not to fall into the de-personalization trap CEBT Center for E-Business Technology Copyright o 2008 by CEBT

Copyright © 2008 by CEBT Personalization Process – (4) 5. Measuring Personalization Impact ◼ Various accuracy metrics can be used to evaluate the personalization – Consumer lifetime value, loyalty value, purchasing and consumption experience ◼ The quality of recommendations depends on the previous stages 6. Adjusting Personalization Strategy ◼ Feedback can be used to identify a part that needs improvements ◼ The quality of interaction should grow over time ◼ One of the main challenges of personalization is the ability to achieve the virtuous cycle of personalization and not to fall into the de-personalization trap Center for E-Business Technology

Building consumer profiles a Traditionally, consumer profiles consist of simple factual information Name, gender, date of birth The largest purchase value made at a Web site a Advanced behavioral information can be expressed by Conjunctive Rules John Doe prefers to see action movies on weekends Name= John doe"& movietype = action"->TimeofWeek="weekend Sequences XYZ: StartPage->Home& Gardening ->Gardening->Exit Signatures The data structure that are used to capture the evolving behavior learned from large data streams of simple transactions Top 5 most frequently browsed product categories over the last 30 days typedef struct i int product _id[5];s profile CEBT Center for E-Business Technology Copyright o 2008 by CEBT

Copyright © 2008 by CEBT Building Consumer Profiles  Traditionally, consumer profiles consist of simple factual information ◼ Name, gender, date of birth, .. ◼ The largest purchase value made at a Web site  Advanced behavioral information can be expressed by ◼ Conjunctive Rules – John Doe prefers to see action movies on weekends – Name = “John Doe” & Movietype = “action” -> TimeOfWeek=“weekend” ◼ Sequences – XYZ: StartPage -> Home&Gardening -> Gardening -> Exit ◼ Signatures – The data structure that are used to capture the evolving behavior learned from large data streams of simple transactions – Top 5 most frequently browsed product categories over the last 30 days – typedef struct { int product_id[5]; } profile; Center for E-Business Technology

Matchmaking Technologies -(1) a Classification based on the recommendation approach Content-based recommendations Analyze the commonalities among the items the consumer has rated highly in the past. Then, only the items that have high similarity with the consumer's past preferences would get recommended Collaborative Recommendations Find the closest peers for each consumer, i. e. the ones with the most similar tastes and preferences. Then, only the items that are most liked by the peers would get recommended ■ Hybrid Approaches Combine collaborative and content -based methods This combination can be done in many different ways CEBT Center for E-Business Technology Copyright o 2008 by CEBT

Copyright © 2008 by CEBT Matchmaking Technologies – (1)  Classification based on the recommendation approach ◼ Content-based Recommendations – Analyze the commonalities among the items the consumer has rated highly in the past. Then, only the items that have high similarity with the consumer’s past preferences would get recommended ◼ Collaborative Recommendations – Find the closest peers for each consumer, i.e., the ones with the most similar tastes and preferences. Then, only the items that are most liked by the peers would get recommended ◼ Hybrid Approaches – Combine collaborative and content-based methods – This combination can be done in many different ways Center for E-Business Technology