HCI in Business, Government and Organizations. Supporting Business

Disruptions caused by Web 2.0 and easily accessible technologies have had an impact on many thematic areas. In the economic sector these developments have resulted in the creation of a new business model: the sharing economy (SE). Despite its success in the last decade however, researchers are debating a clear definition without highlighting the key concept in terms of functions and processes that are fundamental to the SE model. Therefore, this paper focuses on functions of peers that are either consuming or providing, and elucidates the relation in accordance with business transactions in that both peers interact. Through a critical review of previous papers, we analyze the SE model by reflecting on prior definitions of sharing. We then compare motivations of peers to participate in the SE and, as a result, find discrepancies between providing and consuming peers in relation to their respective functions in the SE. Based on these findings, we introduce a theoretical framework that exemplifies the SE concept based on social interactions between peers and, thus, relates motivations of peers to transaction types and processes based on social interactions required.

Used car online trading is a new trend developed in the vehicle trading market recently. In this paper, we focus on user experience of car searching in a used-car website. The datasets of used vehicles are complicated and multidimensional. To find a satisfying car within the budget, the car buyer needs to compare many cars by exploring and comparing data include but not limit to car maker, type, mileage, price, and key features. Within most current e-commerce systems, to search and evaluate different cars, users often have to jump across detail pages to search pages repeatedly. Due to constraints set in the searching process, it may result in uncontrollable information overload or deficiency. With a user-centered design approach, we first analyzed the car searching behaviors through the user study, then designed a data visualization interface that helps a customer to (1) achieve an overall understanding of the used car market such as relations of car type to price, mileage/model-year to price, and features, and (2) search, filter, and compare cars of interest through simple interactions. The goal of this research is to help users to find out an ideal candidate car through an innovative interface and enhance user experience on used-car trading websites.

With the proliferation of e-commerce, online promotion strategy of limited quantity and limited-time is widely used by online retailers to entice consumers’ purchases. However, few research has investigated the exact effects of such a promotion strategy on consumers’ online impulsive purchase. Based on the environmental psychology view, this study focuses on the mediating role of arousal in explaining the influences of scarcity messages in aspects of limited-quantity and limited-time on impulsive purchase. By building an online shop for an actual offline milk tea shop at taobao.com, an experiment with 182 participants was conducted to test our research model. The results provide strong evidence that both the limited-quantity and the limited-time scarcity messages positively influence consumers’ perceived arousal, leading ultimately to impulsive purchases. Both theoretical and practical implications are discussed.

Relying on social connections, online recommendation engines and other enabling technologies, consumers have constantly been increasing expectations and seek experiential value in online shopping. Since customers have more places and ways to shop than ever before, retailers – in order to be successful – must find ways to make online shopping pleasant and enjoyable. They have begun to enhance the online customer experience by incorporating game elements into their business processes, making online shopping not just attractive with innovative products and low prices, but also fun. This concept is known as gamification – a trending topic in both academia and business – and generally defined as the use of game thinking and elements in non-game contexts. In our study, we used a state-of-the-art framework (Octalysis) to analyze a sample of retailers from different industries operating on the European market. Based on an octagonal shape, Octalysis comprises 8 core drives that seek to explain the influence of certain gamification techniques on consumer motivation. Our study focused on determining (a) each retailer’s position in the octagon and (b) whether retailers in the same sector target the same core drives. Further, we suggest guidelines for academics and practitioners seeking to convert results into more and better ideas for online shopping.

Banner advertising is usually placed on suitable, highly frequented websites. The extent to which the brand of a banner ad and the brand of the website influence each other, has not yet been sufficiently investigated. This article provides initial results based on a pilot study which reveals that a positively perceived website can shift a negative banner perception. Furthermore, it is shown that a congruence between banner ad and the website plays an important role. Congruent content supports each other and noncongruent content counteracts the intended advertising effect. Although the study cannot yet be considered as conclusive, the results have the potential to inform entrepreneurial practice on how and where ads should be placed.

With the prevalence of data online, consumers increasingly shop not only for the product that best fits their needs, but also for the best time to purchase the product in order to reduce its cost. In line with this behavior, ecommerce websites often not only offer products, but also provide analytics based statements and recommendations relating to the best time to purchase a perishable product (e.g., air travel). This study examines the effects of such purchase timing statements and recommendations on consumers’ trusting beliefs in the recommendation facility. Our theoretical background comes from Toulmin’s (1958) argumentation model and the literature related to the role of explanation facilities in enhancing consumers’ trust. Results from our pilot study show evidence for the different roles Toulmin elements have, serving as explanation facilities in the context of predictive analytics.

Consumers engage in mobile commerce via their smartphones. They are able to search for product information, compare prices and finalize their purchase without having to enter a physical store. With the choice of many apps, they are motivated by the convenience of shopping any place any time. The Unified Theory of Acceptance and Use of Technology (UTAUT2) is a well-tested theory that explains consumer adoption of a technology innovation. In this study, UTAUT2 is the foundational theory, but instead of specifying the antecedent ‘performance expectancy’ as reflective, it is specified as formative. In addition, perceived convenience is added and the resultant research model is empirically tested. Using PLS to analyze the data from a questionnaire sent to Canadian owners of smartphones, the results show that performance expectancy, hedonic motivation and perceived convenience are the main significant factors that influence consumers’ intention to use an app for mobile commerce.

Online retail business has become an emerging market for almost all business owners. Online recommender systems provide better service to consumers during their decision making processes. In this study, a controlled lab experiment was conducted to assess the effect of recommendation timing (early, mid, and late) and recommendation source (expert reviews vs. consumer reviews) on online consumers’ interest and attention. Eye-tracking data was extracted from the experiment and analyzed. The results suggest that consumers show more interest in recommendation based on consumer reviews than expert reviews. Earlier recommendations do not receive greater attention than later recommendations.

The impact of online coupons is well recognized, but few studies have attempted to model the optimal coupon face value. This research examines how the online coupon affects the payoff of a seller and analyzes the optimal coupon face value for online seller. We find that both the fixed costs and matching probability play critical roles in whether the seller chooses to offer coupons or not. We also find that, a seller can maximize his/her profit by providing the online coupon with an optimal face value which has been formulated. Finally, we conclude with managerial implications and directions for further studies.

Omnichannel retailing is an approach that enables customers to use multiple online and offline channels of retailers during a customer journey and combine them simultaneously. By embedding digital devices in brick-and-mortar retail stores, retailers are able to better observe customer behavior, to collect customer data, analyze their needs and provide personalized services. This personalization may provide additional value for customers but may also lead to privacy concerns. This paper examines the impact of personalization on privacy concerns and the intention of customers to adopt services in brick-and-mortar retail stores and online shops. The empirical study is based on an online survey that uses a within-subject design including four scenarios that covered the combinations of personalization and non-personalization with the retailing context online shop vs. brick-and-mortar retail store. The subjects had to assess their privacy concerns and their intention to adopt the omnichannel retailing services in these scenarios. 112 subjects participated within this study. Results show that personalized services cause significantly higher privacy concerns than non-personalized services for both contexts. Additionally, consumers expressed higher concerns regarding digital services in the retail store than in the online shop for both personalized and non-personalized services. The intention to adopt the digital services decreased in scenarios with personalized services, both online and offline. However, the intention to adopt personalized services is generally lower in retail stores (with digital elements of omnichannel retailing) than in the online shop. Privacy concerns appeared to have significant negative impact on the intention to adopt in three out of four omnichannel scenarios.

Due to the important role of product reviews in e-commerce, some systems have employed different approaches to present reviews on product detail page or comparison page. However, little work has investigated how to present reviews on screening interface for facilitating users to screen out interesting alternatives from a set of options. In this paper, we have developed a novel review-based screening interface in terms of users’ behaviors. Concretely, there are two innovations in the interface design: (1) it enables users to eliminate items by sentiment attributes (i.e., the attributes extracted from reviews), and (2) it emphasizes on visualizing the value distribution of each attribute and tradeoffs among attributes. The results of a user study show that our review-based screening interface achieves significantly more positive assessments than traditional screening interface, in terms of users’ perceived decision accuracy, cognitive effort, pleasantness and intention to use.

In line with the continuous growth rates in online retailing, the competitive situation for retailers has intensified. In order to strengthen their market position and exploit further potential, online retailers need to address the specific needs of their customers. In this context, a more detailed analysis of gender-specific preferences is expected to be worthwhile, as men and women might have different needs when shopping on the Internet. This study explores in-depth the extent to which the gender-specific design of online shops has an influence on the genders. The aim of this study is to answer the following question: Do women and men exhibit different information research and buying behavior when utilizing online shops designed to appeal to their respective genders? An eye-tracking method was chosen for this study with 80 participants.The findings illustrate that indeed there are differences between the behavior of men and women. It can be asserted that gender-specific online shop designs have a significant impact on women. Although not backed by strong statistical significance, men nevertheless also tend toward higher average values in the typically feminine shop compared to the masculine one, indicating that also online behavior of men is slightly impacted by gender-specific shop design.

The study reported in this paper investigated the effects of online review message appeal and online review source type on review credibility perception, product attitude, and purchase intention across two types of products, namely technical and non-technical. A between-respondent 2 (message appeal: rational vs emotional) × 2 (online review source: experts vs consumers) experiment was implemented with 294 online consumers from Java, Indonesia. Results of analyses indicate that message appeal has a main effect on review credibility (for both technical and non-technical products) and product attitude (for a technical product). However, review source type has no significant effects on all dependent variables. Furthermore, the use of a rational appeal by expert reviewers resulted in higher review credibility perception than the use of a rational appeal by consumers as reviewers; while expert reviews with emotional appeals are regarded less credible than consumer-based reviews with emotional appeals. This interaction effect, however, is present in the non-technical product context only.

In recent years, the phenomenon of sharing economy has emerged in many industries worldwide and businesses leveraging the sharing economy have flourished. Sharing Economy denotes the “collaborative consumption made by the activities of sharing, exchanging, and rental of resources without owning the goods”. Value is a central concept in consumer behavior and it directly explains why consumers choose to buy or avoid particular products or services. Therefore, to establish the theoretical linkage between collaborative consumption and consumer value, our study propose a research model to explain why consumers participate in collaborative consumption from a value co-creation perspective. Based prior literature on collaborative consumption and literature on consumer value and value co-creation, we identify five factors as key determinants of attitude towards collaborative consumption, including economic value, social value, entertainment value, convenience value, and trust. A large scale survey was designed and implemented to test our research model. Data analysis results suggested that economic value, social value, entertainment value and trust significantly affect people’s attitude towards collaborative consumption. The practical and theoretical contributions of our study are discussed.

We view the prediction of Facebook likes as a content suggestion problem and show that likes can be much better predicted considered post content or user engagement. Experiments presented are based on a dataset of over 4 million likes collected from over seventy thousands of users in fan pages. The proposed model adopts the similarity metric to appraise how a user may like a document given his or her liked documents, as well as the Restricted Boltzmann Machine (RBM) to estimate whether a user would like a document given the like records of all users. The model achieves a precision of 5–10% and a recall of 2–55%. The commonly used label propagation model is implemented and tested as a baseline. Different models and settings are compared and results show superiority of the proposed model.

Trust is a necessary condition for many industries. However, trust may not be the most important factor driving participation in online fantasy sports gambling. In this research we examine how different classifications of gamblers (i.e., passive gamblers, problem gamblers, and pathological gamblers) perceive their participation in fantasy sports. We argue that trust is not commonly a primary consideration and that trust does not need to be present in these types of online transactions. To prove this relationship, a trust model is proposed to be tested in the context of online fantasy sports with a focus on the market leader in the industry: fanduel.com.

This is an extension of a previous study, which explored the relationship between happiness and Internet use [1]. An Internet Use Scale (IUS), developed in the previous study, was administered to college students along with the Flourishing Scale [2] and the Satisfaction with Life Scale [3]; and three new open-ended questions. We compared changes in the relationship between these measures, and their mean values, across the two samples, and carried out qualitative analyses of the open-ended questions. Results indicated that those who reported spending less time on the internet, less time expressing emotions, and more time checking facts, scored higher on measures of happiness. Further, participants found negative affective expression on the Internet particularly aversive. Finally, those with lower happiness scores were more likely to report playing on-line games; and those with higher happiness scores were more likely to identify Internet disinformation as aversive.

Applying gamification design to websites for promoting users’ experiences is a vital issue at present and in the future that in-depth discussions are necessary. This study intend to discuss experience from the aspects of human-computer interaction design, psychology, marketing, and communication to develop a “model applying gamification to networks for promoting marketing” with interdisciplinary knowledge and in-depth experiences and to treat it as the new possibility to effectively create users’ experiences. The objectives of this study contain 1. to enhance online marketing and users’ experiences with gamification design and 2. to construct a “model applying gamification to networks for promoting marketing”, which could enhance users’ experiences, by incorporating interdisciplinary theories.

The aim of this study is to extract a customer’s needs from their reviews of an electronic commerce (EC) site using transfer learning. Transfer learning involves retaining and applying the knowledge learned from one or more tasks to efficiently develop an effective hypothesis for a new task. Recently, with the spread of EC sites, customer reviews have become a beneficial information source, as they include customers’ opinions or product reputations, and can attract attention. However, this information is too huge to browse conveniently. Moreover, to develop new products with a competitive advantage, it is necessary to incorporate customers’ opinions. Therefore, it is necessary to extract the customers’ opinions from the enormous amount of customer reviews.In this research, we focus on markets where multiple products compete. With the spread of smartphones, multiple products, e.g., cameras, compete in the same market. We want to understand customers’ needs efficiently by extracting com-mon requests by consumers from the information about these multiple products. Hence, we propose a method of extracting customers’ needs using transfer learning to comprehensively handle multiple products’ information for this market.

Consumers are increasingly relying on online consumer reviews (OCRs) to facilitate their decision making process as a credible source of information. This study seeks to explicate why consumers deem OCRs as helpful and how they make use of OCRs in their decision making process. By drawing on Simon’s decision making model, this study posits that the two forms of OCRs (i.e., numerical ratings and opinionated reviews) facilitate consumers’ decisional processes in terms of the effectiveness of constructing consideration sets and the efficiency of arriving at a final decision. Consumers’ performance in decisional process in turn determines the justifiability of and the confidence in their decisional outcomes. To empirically test all the hypotheses proposed in this study, a field survey was conducted on users of a custom-developed online restaurant review website equipped with OCR curation features and populated with real restaurant review data. Except for two unexpected findings, all hypotheses were supported by the data analysis results. It is worth noting that, numerical rating exerts stronger positive influence on decisional process efficiency comparing to opinionated review. Furthermore, decisional outcome justifiability mediates the positive effects of both decisional process effectiveness and decisional process efficiency on decisional outcome confidence. This study contributes to both research and practice by offering a more in depth explanation to consumers’ reliance on OCRs through the lens of bounded rationality and providing excitable guidelines for enhancing the benefits of OCRs via curation features.

Self-service technologies within retail enable customers to scan, bag and pay for their items independent from staff involvement. The use of self-service, due to its nature of reducing social interaction between customers and staff, has been implicated in creating opportunities for thefts to occur. However, the perception of social presence, such as induced by surveillance, induces customers to show more prosocial behavior. As security personnel are at the forefront to deal with dishonest customers, we conducted semi-structured interviews with security guards in two major supermarkets in the UK to assess factors surrounding theft, with a view to identify operational or technological opportunities to address theft. Our findings show that the perceived motivational and situational factors contributing to theft are complex. We conclude that surveillance in its current form does not appear to provide a sufficient social presence to prevent potential theft at self-service checkouts (SCOs). Future research could focus on additional surveillance measures to induce social presence, such as technological implementations in the SCO itself.

This study investigates the duality of envy in online social information consumption. By drawing on the Social Comparison Theory, this study identifies three key aspects of social information consumption, namely social exhibition, network attention strength, and network attention valence, to be important determinants of positive and negative envy emotions induced by such consumption. More importantly, this research elucidates better understanding of individuals’ response strategies pertinent to the online social networking environment. To do so, this research investigates the multiplex perspective of online social network usage to determine the behavioral responses of online social network users in regards to online social information consumption. Subsequently, this research empirically examines the impacts of social information consumption have on users’ envy emotions and motivations specific to usage of social networking platforms. The research model was tested using an experiment. Contributions are discussed.

The ‘‘Service Dominant Logic’’ (SDL) approach suggests that value for the consumer is generated only while using a product (value in use). Extending this perspective, the concept “value in context” considers the impact of the specific usage situation. We shall develop a classification of context dimensions with respect to their relevance in influencing the value for the customer.While technology today provides innumerous systems to measure context factors, it is highly important to develop suitable algorithms to transform data into knowledge allowing real time reactions as there are presentation of information, automated execution of functions and services and tagging of customer data for future use. While presentation of information is already used in smart online marketing we see a lot of potential for innovations in context-sensitive online services and will provide some ideas in this paper.We will focus on two key challenges for digital brand management: brand integration and customer integration into the context of the usage situation. To this end we introduce the term “brand viscosity” describing the capability of the brand to adjust to a specific context situation. E.g. it should be possible to select and combine context-relevant brand attributes out a set of predefined brand-specific symbols, language styles and stories and digitally display those that promise the highest value in context. In such way, the brand substance, the brand image and its relationship with the customer, who is considered as “value (co) creator”, are designed so that they can adapt to the specific context conditions without losing its basic identity.This paper is addressed to marketers by giving guidelines for the design of a context-sensitive digital marketing approach as well as to researchers by providing a framework to link the theoretical concepts of SDL, digital brand management and the concept of context-sensitivity.

Mobile technologies may facilitate collaborative consumption among strangers that can help merchants “attract customers through customers” beyond close relational boundary. To leverage on this opportunity, it is important to understand what may motivate consumers to participate in such collaborative consumptions when they do not know each other, given that embarrassment of interacting with strangers may inhibit one from doing so. In this study, we propose that the use of a gamification strategy can increase consumer response to a mobile collaborative consumption offer. Through conducting a field experiment, we show that when asked to invite a nearby stranger to enjoy a group discount together, a gamification design whereby the group discount is randomly split between participants can promote the consumer likelihood to do so, compared to the typical design of equal splitting of the discount (pure economic gains). Similarly, the acceptance rate of invitation from a stranger was also enhanced with a gamification design.

In the past, poorly designed alarm systems and inadequate alarm management contributed to the emergence of critical events with partially serious consequences. Based on the experience gained from these incidents, guidelines were created with recommendations for the design of alarm systems and alarm management. A comprehensive checklist has been developed to analyze the current design quality of alarm systems and alarm management and has been used in various control rooms across different branches of industry in Germany. Using the checklist, design deficiencies can be identified and action needs can be derived. So far, the results also show systematic differences in the application of the checklist between individual assessors and between groups of assessors.

Supply Chains and production networks are complex sociotechnical cyber-physical systems whose performance is determined by system, interface, and human factors. While the influence of system factors (e.g., variances in delivery times and amount, queuing strategies) is well understood, the influence of interface and human factors on supply chain performance is currently insufficiently explored. In this article, we analyze how performance is determined by the correctness of Decision Support Systems and specifically, how correct and defect systems influence subjective and objective performance, subjective and objective compliance with the system, as well as trust in the system. We present a behavioral study with 50 participants and a business simulation game with a market driven supply chain. Results show that performance (−21%), compliance (−35%), and trust (−25%) is shaped by the correctness of the system. However, this effect is only substantial in later stages of the game and occluded at the beginning. Also, people’s subjective evaluations and the objective measures from the simulation are in congruence. The article concludes with open research questions regarding trust and compliance in Decision Support Systems as well as actionable knowledge on how Decision Support Systems can mitigate supply chain disruptions.

The last few years have seen more and more employees using their personal mobile devices for work-related tasks. This phenomenon is part of a broader trend known as IT consumerization. Enterprises and employees have recognized that they might profit from these developments and implemented “Bring Your Own Device” (BYOD) policies, but they also have to face new challenges. This study investigates which types of employees adopt BYOD and how they benefit from it. To address these questions, the authors conducted a survey with 219 participants. Participants were classified into adopter types based on the Diffusion of Innovation Theory. The results indicate that early adopters and the early majority use their personal smartphones more often for work-related tasks than laggards, and that innovators and early adopters more often receive work-related email on their personal smartphones than other adopter types. It is concluded that DOI can successfully be applied to explain BYOD adoption behavior. Differentiated management strategies have to be applied in order to address the whole workforce.

Games are captivating from a human-computer interaction point of view. They can induce an intensely involving and engaging experience termed flow, which refers to the optimal state of experience when one is fully immersed in an activity. This paper provides a review of the neural and psychophysiological correlates of flow as well as some directions for future research.

This paper will look at what types of information graphics and visualizations can support supervised Machine Learning tasks: in essence, how to support the problem of model validation and model overfitting. In particular, I look, graphically, at model performance as a function of model complexity. With an appropriate information graphic, we can visualize at what point the model becomes too complex and starts to deteriorate in performance because of model overfitting. I will look at two actual case studies—the first, a regression task using polynomial regression and the second, a classification problem using neural networks. I create information graphics, in particular fitting graphs, to support the end-user in visualizing which model is the best choice.

In recent years, serious quality accidents and quality troubles such as recalls have occurred frequently, and Total Quality Management (TQM) is important as effective management to prevent quality troubles beforehand. There is also a Quality Management Level Research [6] (TQM research) that is jointly implemented by the Union of Japanese Scientists and Engineers and the Nikkei. In the TQM survey, the rankings on the six criteria of quality management and comprehensive rankings have been announced. However, concrete TQM activities have not been announced. Meanwhile, Corporate Social Responsibility (CSR) report has published abundant descriptions about the role of customers, employees, society and management who are stakeholders of companies. In this research, we aim to evaluate and extract the characteristics of the company’s quality management activities according to the six criteria of the TQM survey using corporate CSR reports.

Our aim is to develop general heuristics for the visualization of contracts, which may serve as guidelines for interface developments of legal technology software. We introduce three approaches to interactive contract visualisations and discuss their strengths and weaknesses. They all address the negotiation phase preceding an agreement. We believe the nature of contracts is to capture and organise potential future events and therefore introduce the concept of “possibility spaces” as a starting point for the first two visualizations. Focusing on the “modalities” of contracts seems to us the most promising approach and is explored in the third example. From a methodological point of view, we develop visualisations through abstraction and focus on the common characteristics of all contracts. In that sense, we do not “illustrate” contracts. Through these visualisations we hope to make contracts easier to understand, be it on paper or via legal technology.

Color is a complex visual and design element that can produce various emotional, psychological and physical outcomes that can be expressed through religious, cultural, political or social meanings. Past studies have confirmed that culture is an important and integral part of the decision-making process in which color appeal is a salient antecedent to behavioral intentions in culturally distinct countries. However, in the context of computer warning messages, we are lacking clear evidence of how color risk appropriateness (CRA) affects users’ decision-making processes. Supported by the color-in-context theory, our research investigates the color risk appropriateness impact on the perceived risk in two different cultures. We found that different colors behave differently in the specific warning banner context in which CRA is an important antecedent to users’ compliance. Overall, we advance current theoretical understanding on the color-risk dimension and its importance for the user’s decision-making processes.

The study proposes a novel construct of “representativeness” that aims to measure the degree to which a book in the user’s online bookshelf is able to represent his/her reading preference, based on the assumption that not all books are equally important when it comes to constructing individual users’ preference profiles. Thirty-five online bookshelf aNobii users were recruited, who were asked to perform a judgment task involving evaluating the degree of “representativeness” and “involvement” of 10 books self-selected from their bookshelves. The results show that there is a high correlation between “representativeness’ and “involvement”, a well-established construct in marketing. Book similarity networks for every participants was generated based on book co-ownership data extracted from aNobii. Two social network analytical (SNA) metrics: coreness and connectivity, were then applied to measure a book’s “representativeness” relative to the individual bookshelves. Results show that there were significant correlations between the SNA metrics and the user’s self-assessed “representativeness” and “involvement” of the books. Furthermore, it was found the correlations were stronger among bookshelves owned by users who have low reading diversity.

Nowadays a growing number of countries’ emergency management mechanisms are based on the network governance mechanism. The task group such as emergency support function (ESF) of the United States is the basic component of emergency response network. How to share function units among task groups is a basic problem of network structure design. This paper proposes a model to decompose transaction cost structure of cooperation between groups and evaluate different choices of sharing units between groups. Through applying this model to the case with only two groups, it shows the equilibrium solution to both sides could be obtained by a bottom-up method.

Given the problems of gradual oil depletion and global warming, energy consumption has become a critical factor for energy-intensive sectors, especially the semiconductor, manufacturing, iron and steel, and aluminum industries. In turn, reducing energy consumption for sustainability and both tracking and managing energy efficiently have become critical challenges. In response, we analyzed electricity consumption from the perspective of load profiling, which charts variation in electrical load during a specified period in order to track energy consumption. As a result, we proposed a time series data mining and analytic framework for electricity consumption analysis and pattern extraction by streaming data mining and machine learning techniques. We identified key factors to predict the state of the annealing furnace and detect abnormal patterns of the load profile of their electricity consumption. Our experimental results show that the dimension reduction method known as piecewise aggregate approximation can help to detect the state of the annealing furnace.