电子商界推荐系统手册：核心技术与应用解析

Recommender

Systems

需积分: 9 178 浏览量更新于2024-08-01 收藏 4.69MB PDF 举报

身份认证购VIP最低享 7 折!

领优惠券(最高得80元）

《推荐系统手册》第一部分深入探讨了随着电子商务和在线环境的爆炸式增长，如何应对信息搜索和选择的挑战。用户在海量选项面前感到压力山大，而推荐系统作为解决信息过载的有效工具，已成为电子商務中的强大武器。本书汇集了全球多学科专家的智慧，包括人工智能、人机交互、信息技术、数据挖掘、统计学、自适应用户界面、决策支持系统、市场营销以及消费者行为等领域，旨在提供一个连贯且全面的推荐系统框架。第1章介绍了推荐系统的基本概念和原理，作者弗朗西斯科·里奇、利奥尔·罗卡赫和布拉查·夏皮拉阐述了推荐系统的核心功能：为用户提供个性化物品建议，以辅助决策，如购物、音乐选择或在线阅读。这里的"物品"是一个通用术语，代表系统向用户推荐的具体内容。推荐系统通常专注于特定类型的商品（如CD、新闻等），设计、用户界面和核心推荐算法都根据这些类型进行定制，以提供有针对性且有效的建议。该部分的其余章节涵盖了推荐系统的多种基础技术，如基于内容的推荐、协同过滤、矩阵分解、深度学习方法、个性化推荐引擎以及混合推荐策略等。这些技术通过分析用户的兴趣偏好、行为模式和社交网络信息，生成个性化的推荐列表，帮助用户发现潜在的兴趣点，提升用户体验，同时也为企业创造了商业价值。此外，书中还包括大量实际应用案例和详细分析，展示推荐系统在亚马逊、谷歌、微软和AT&T等知名企业的应用场景。对于计算机科学的研究人员和高级学生来说，这是一本不可或缺的参考资料，它不仅提供了理论基础，还展示了推荐系统在现实世界中的实践和挑战，有助于读者理解和掌握这一领域的最新进展。《推荐系统手册》第一部分为读者提供了一个全面而深入的指南，旨在促进理论研究者和实际应用者之间的交流与合作，推动推荐系统技术的发展，并帮助用户更好地利用这项技术来支持决策过程，优化购物、娱乐和信息获取体验。

资源详情

资源推荐

1 Introduction to Recommender Systems Handbook 15

follow as in www.tweeter.com. Hence, the above list cannot cover all the applica-

tion domains that are now being addressed by RS techniques; it gives only an initial

description of the various types of application domains.

The developer of a RS for a certain application domain should understand the

speciﬁc facets of the domain, its requirements, application challenges and limita-

tions. Only after analyzing these factors one could be able to select the optimal

recommender algorithm and to design an effective human-computer interaction.

Chapter 11 of this handbook provides guidelines for matching the application

domain to the recommendation technique. Burke and Ramezani in their chapter

provide a new classiﬁcation of recommender systems. Unlike former classiﬁcations

of RSs (such as [25, 94, 3, 7]), Burke and Ramezani take an AI-centric approach, and

focus on the knowledge sources required for different recommendation approaches,

and the constraints related to them as a primer guideline to choosing the algorithm.

The chapter discusses the applicability of various recommendation techniques for

different types of problems and suggests decision-making guidelines in selecting

these techniques.

The chapter explicitly aims at system implementers as “recommenders” for the

right recommendation approach. The authors describe the knowledge sources that

are available to a recommender systems in different domains and identify what

knowledge sources are required for each recommendation technique. This implies

that the design of a recommender system should ﬁrst emphasize the analysis of the

available sources of knowledge, and then decide about the algorithm accordingly.

Another example of the need to adjust the recommender approach to the domain

is described in Chapter 12, which deals with recommender systems for technology-

enhanced learning (TEL). TEL, which generally covers technologies that support

all forms of teaching and learning activities, aims at designing, developing and test-

ing new methods and technologies to enhance learning practices of both individuals

and organizations. TEL may beneﬁt greatly from integrating recommender systems

technology to personalize the learning process and adjust it to the user’s former

knowledge, abilities and preferences. The chapter presents the particular require-

ments of RSs for TEL; the user tasks that are supported in TEL settings; and how

these tasks compare to typical user tasks in other RSs. For example, one particu-

lar user task for TEL –“ﬁnd novel resources”– attempts to recommend only new

or novel items. Or, to cite another example, – “ﬁnd new pathways” – is concerned

with recommending alternative pathways through the learning resources. The chap-

ter presents an analysis of the ﬁltering approaches that could be useful for TEL along

with a survey of existing TEL systems illustrating the recommendation techniques

that have been deployed in these systems.

Chapter 10 discusses practical aspects of RS development and aims at providing

practical guidelines to the design, implementation and evaluation of personalized

systems. Besides the prediction algorithm, many other factors need to be considered

when designing a RS. Chapter 10 lists some of these elements: the type of target

users and their context; the devices that they would use; the role of the recommen-

dation within the application; the goal of the recommendation; and, as mentioned

previously, the data that is available.

16 Francesco Ricci, Lior Rokach and Bracha Shapira

The authors propose to build a model of the environment based on three dimen-

sions: system users; the characteristics of the data; and the overall application. The

recommender system design will be based on this model. The authors illustrate their

guidelines and the model on a news recommendation system that they have devel-

oped.

Another important issue related to the practical side of RS deployment is the

necessity of evaluating them. Evaluation is required at different stages of the systems

life cycle for various purposes [25, 1]. At design time, evaluation is required to

verify the selection of the appropriate recommender approach. In the design phase,

evaluation should be implemented off-line and the recommendation algorithms are

compared with user interactions. The off-line evaluation consists of running several

algorithms on the same datasets of user interactions (e.g., ratings) and comparing

their performance. This type of evaluation is usually conducted on existing public

benchmark data if appropriate data is available, or, otherwise, on collected data. The

design of the off-line experiments should follow known experiment design practices

[11] in order to ensure reliable results.

Evaluation is also required after the system has been launched. The algorithms

might be very accurate in solving the core recommendation problem, i.e., predicting

user ratings, but for some other reason the system may not be accepted by users, e.g.,

because the performance of the system is not as expected. At this stage it is usually

beneﬁcial to perform on-line evaluation with real users of the system and analyze

system logs in order to enhance system performance. In addition, most of the al-

gorithms include parameters, such as weights thresholds, the number of neighbors,

etc., requiring constant adjustment and calibration.

Another type of evaluation is a focused user study that can be conducted when

the on-line evaluation is not feasible or too risky. In this type of evaluation, a con-

trolled experiment is planned where a small group of users are asked to perform

different tasks with various versions of the system. It is then possible to analyze

the users performance and to distribute questionnaires so that users may report on

their experience. In such experiments it is possible to collect both quantitative and

qualitative information about the systems.

Evaluation is also discussed in Chapter 12 in the context of TEL systems. The

authors provide a detailed analysis of the evaluation methods and tools that can be

employed for evaluating TEL recommendation techniques against a set of criteria

that are proposed for each of the selected components (e.g., user model, domain

model, recommendation strategy and algorithm).

Chapter 8 details three types of experiments that can be conducted in order to

evaluate recommender systems. It presents their advantages and disadvantages, and

deﬁnes guidelines for choosing the methods for evaluation them. Unlike existing

discussions of evaluation in the literature that usually speaks about the accuracy of

an algorithms prediction [25] and related measures, this chapter is unique in its ap-

proach to the evaluation discussion since it focuses on property-directed evaluation.

It provides a large set of properties (other than accuracy) that are relevant to the

systems success. For each of the properties, the appropriate type of experiment and

1 Introduction to Recommender Systems Handbook 17

relevant measures are suggested. Among the list of properties are: coverage, cold

start, conﬁdence, trust, novelty, risk, and serendipity.

When discussing the practical aspects of RSs, it may be beneﬁcial to analyze

real system implementations. The idea is to test theoretically intuitive assumptions

in order to determine if they work in practice. The major problem that one must face

in this case comes from the fact that the owners of commercial RSs are generally

unwilling to reveal their practices and there are only relatively few opportunities for

such cooperation.

Chapter 9 reports on such an opportunity and describes the operation of a real

RS, illustrating the practical aspects that apply to the implementation stage of the

RS development and its evaluation. This description focuses on the integration of

a RS into the production environment of Fastweb, one of the largest European IP

Television (IPTV) providers. The chapter describes the requirements and consider-

ations, including scaling and accuracy, that led to the choice of the recommender

algorithms. It also describes the off-line and on-line evaluations that took place and

illustrates how the system is adjusted accordingly.

1.6 Recommender Systems and Human Computer Interaction

As we have illustrated in previous sections, researchers have chieﬂy been concerned

with designing a range of technical solutions, leveraging various sources of knowl-

edge to achieve better predictions about what is liked and how much by the target

user. The underlying assumption behind this research activity is that just presenting

these correct recommendations, i.e., the best options, should be enough. In other

words, the recommendations should speak for themselves, and the user should def-

initely accept the recommendations if they are correct. This is clearly an overly

simpliﬁed account of the recommendation problem and it is not so easy to deliver

recommendations.

In practice, users need recommendations because they do not have enough

knowledge to make an autonomous decision. Consequently, it may not be easy for

them to evaluate the proposed recommendation. Hence, various researchers have

tried to understand the factors that lead to the acceptance of a recommendation by a

given user [105, 30, 24, 97, 33].

[105] was among the ﬁrst to point out that the effectiveness of a RS is depen-

dent on factors that go beyond the quality of the prediction algorithm. In fact, the

recommender must also convince users to try (or read, buy, listen, watch) the rec-

ommended items. This, of course, depends on the individual characteristics of the

selected items and therefore on the recommendation algorithm. The process also

depends, however, on the particular human/computer interaction supported by the

system when the items are presented, compared, and explained. [105] found that

from a users perspective, an effective recommender system must inspire trust in

the system; it must have a system logic that is at least somewhat transparent; it

should point users towards new, not-yet-experienced items; it should provide details

18 Francesco Ricci, Lior Rokach and Bracha Shapira

about recommended items, including pictures and community ratings; and ﬁnally, it

should present ways to reﬁne recommendations.

[105] and other similarly oriented researchers do not diminish the importance of

the recommendation algorithm, but claim that its effectiveness should not be evalu-

ated only in terms of the accuracy of the prediction, i.e., with standard and popular

IR metrics, such as MAE (Mean Absolute Error), precision, or NDCG (Normalized

Discounted Cumulative Gain) (see also Chapters 8 5, 9). Other dimensions should

be measured that relate to the acceptance of the recommender system and its recom-

mendations. These ideas have been remarkably well presented and discussed also by

[33]. In that work the authors propose user-centric directions for evaluating recom-

mender systems, including: the similarity of recommendation lists, recommendation

serendipity, and the importance of user needs and expectations in a recommender.

Following the remarks made in [105], let us introduce some important points

raised by HCI research that are further discussed in this handbook.

1.6.1 Trust, Explanations and Persuasiveness

First of all let us focus on trust. There are two different notions of trust that are

discussed in this handbook: trust about the other users of the recommender and trust

about a system’s recommendations.

Chapter 20 focuses on the ﬁrst notion and considers a class of recommender

systems termed “social recommender systems”. These systems attempt to generate

more useful recommendations derived from information about user proﬁles and re-

lationships between users that nowadays can be found virtually everywhere; e.g.

in social networking sites such as Facebook, LinkedIn and MySpace. Since trust-

based recommender systems mainly exploit the trust relationships found in these

social networking sites to build new recommendation algorithms (e.g., [34]), they

still operate on the core rating prediction problem but use trust relationships. The

main claimed advantage is that users will be aware of the nature of the recommen-

dations, i.e., how they have been identiﬁed, and will tend to place greater trust in

these recommendations. In other words, the mutual trust of users can be exploited

also for increasing the trust in the system.

Trust in system recommendations is discussed in Chapter 15. In this chapter the

main scope is actually the role of explanations in RSs and trust emerges as one out of

seven roles that can be played by explanations in RSs. These roles are: transparency

- explaining how the system works; scrutability - allowing users to tell the system

it is wrong [50]; trust - increasing user conﬁdence in the system; effectiveness -

helping users make good decisions; persuasiveness - convincing users to try or buy;

efﬁciency - helping users make decisions faster; and satisfaction - increasing the

ease of use or enjoyment.

This chapter also illustrates a range of approaches for building explanations. In

the collaborative ﬁltering style, i.e., the explanation is of the form “Other users sim-

ilar to you liked this item”. In content-based style explanations, the item’s attributes

1 Introduction to Recommender Systems Handbook 19

which most affected the item to be recommended to the user are illustrated. For ex-

ample, in a movie recommendation, an explanation may be of the form “This movie

was recommended because it stars Bruce Wills who you seem to like”, or “Item X

was recommended because of features A and B which are shared by items Y and

Z, which you rated highly”. In case-based style explanations, the system refers to

items that are similar to the recommended one, for example, “The item was recom-

mended because you said you own item X” or “These items are recommended based

on your most recently viewed items”. And ﬁnally, in knowledge-based style expla-

nations, the system explains the differences between the recommended item and

another item and how it serves the user’s goal: “This room has an ocean view and is

larger than the previous recommended room, which will make it more romantic as

you requested”.

Moving back to trust, we see that it serves as a means of obtaining the main goal

of the recommender, i.e., to convince the user to accept the recommendations and

try out one of the recommended items. This issue is ultimately related to the per-

suasiveness of the full RS, i.e., how the various elements of the RS, including what

and how an item is recommended, actually operate during the human/computer in-

teraction. This topic is discussed in the Chapter 14. Here the authors stress that a

recommendation is seen as credible advice and is actually taken into account not

only because of the user’s perceptions of the recommendation but also due to the

fundamental role of the system which is perceived as an advice-giver. Indeed, the

literature about persuasion suggests that people are likely to accept recommenda-

tions from credible sources and we therefore conclude that the credibility of the RS

is vital to increasing the likelihood of recommendation acceptance. Hence, the au-

thors discuss how the credibility of RSs can be enhanced, providing a synopsis of

credibility-related research.

1.6.2 Conversational Systems

Another severe limitation of many algorithmic approaches to RSs is due to the fact

that these algorithms have been designed to collect all the input data only once.

They then terminate their job by returning their recommendations. In many cases,

this model is not effective since users may not be fully aware of their preferences

until they have interacted to a certain extent with the system and roughly understand

the range of alternatives. Or they may want to browse several alternative options

before being convinced that some of the recommendations may suit them. There is

also the possibility that the system may be initially wrong in its suggestions and the

user may be willing to provide additional information that can ﬁx these problems,

and eventually obtain some better recommendations.

These aspects have been stressed and tackled by researchers engaged in following

a line of research that is commonly known as “conversational RSs” [27, 110, 67, 60].

Conversational RSs use a diverse range of techniques for rating prediction or rank-

ing. However, they all try to support an interactive process where both the user and

剩余247页未读，继续阅读

xiaot23

粉丝: 1
资源: 2

电子商界推荐系统手册：核心技术与应用解析

Recommender Systems Handbook

给我推荐20个比较流行的推荐算法模型

graph neural networks in recommender systems: a survey

a survey on knowledge graph-based recommender systems

recommender systems

引用文献介绍基于内容的推荐算法

有什么关于机器学习推荐的好书

帮我讲解总结一下Self-Supervised Learning for Recommender Systems: A Survey这篇论文

协同过滤算法参考文献

PBL项目人们个性化健康推荐系统的参考来源

CARS python

我想了解基于keras的推荐系统项目

top1% recall

node-recommender怎么使用

DDPG结合GCN做预测的GitHub代码

图神经网络和推荐系统

F_know’s Binary Matrix

有哪几种推荐算法，他们的英文名字是什么

Calibration 不是Collaborative Filtering，我要的是Calibration相关的推荐系统

错误: 找不到或无法加载主类 com.aliyun.recommender.DataLoader

最新资源