Results

Found 12 articles

Clear filters

Handling the Efficiency–Personalization Trade-Off in Service Robotics: A Machine-Learning Approach
PDF
2021 | Journal of Management Information Systems | Citations: 0
Authors: Tofangchi, Schahin; Hanelt, André; Marz, David; Kolbe, Lutz M.

Abstract: While multiple mechanisms for value creation from big data analytics (BDA) exist ... Expand

Abstract: While multiple mechanisms for value creation from big data analytics (BDA) exist, their application in everyday life can create trade-offs, particularly in the context of service robotics where the dispersion of autonomous digital technologies creates potentials for data-driven efficiency gains. Attending to personal preferences in such contexts, increasingly vital for customer acceptance, may run counter to efficiency, thus constraining value creation and rendering efficiency-personalization trade-offs a key managerial challenge. For the case of autonomous vehicles (AVs), we formalize this trade-off and design a machine-learning approach to handle it by drawing on a unique dataset comprising 35,000 drives by 1,850 users. We consider the real-time dynamics and user interactions that affect the decisions of AVs and develop a model extension that allows for leveraging the properties of sharing business models to make better-informed decisions. Our study contributes to information systems (IS) AV research by providing an artifact that targets both efficiency and personalization of AV operations as well as the dynamic balance between the two. With the focus on everyday life contexts, our study points to the value of incorporating trade-offs between competing goals as well as human-centered perspectives in information systems designs for research on BDA value creation. For practitioners, our work provides a practical and generalizable approach to realize the potentials of service robots without risking customer acceptance. Collapse

Semantic filters: average absolute deviation

Topics: personalization usability ride sharing platform value creation robotic

Methods: design artifact experiment machine learning descriptive statistic design artifact testing
Data Analysis of Delays in Airline Networks
PDF
2016 | Business & Information Systems Engineering | Citations: 0
Authors: Ionescu, Lucian; Gwiggner, Claus; Kliewer, Natalia

Abstract: Cost-optimized airline resource schedules often imply a lack of delay tolerance ... Expand

Abstract: Cost-optimized airline resource schedules often imply a lack of delay tolerance in case of unforeseen disruptions, e.g. late check-ins, technical defects or airport and airspace congestion. Therefore, the consideration of timeliness and robustness has become an important topic in robust resource scheduling and a wide range of sophisticated scheduling approaches has been developed in recent years. However, these approaches depend on assumptions made concerning delay occurrences. A better understanding of delay mechanisms may lead to a better trade-off between cost-efficiency and robustness and is therefore the purpose of this paper. We provide a data-driven detection of decision rules for daytime delay trends, depending on spatio-temporal attributes. The focus is on interpretable rules whose prediction accuracy is compared to random forests as a non-parametric, automated modeling approach. The obtained results give an insight into both the nature of primary delay occurrence and the methodical potential of delay prediction in the context of robust resource scheduling. Collapse

Semantic filters: average absolute deviation

Topics: logistics management programming language

Methods: random forest classification analysis of covariance descriptive statistic parametric test ANOVA
urCF: User Review Enhanced Collaborative Filtering

2014 | Americas Conference on Information Systems | Citations: 0
Authors: Zhang, Zhenxue; Zhang, Dongsong; Lai, Jianwei

Abstract: Despite of success in both research and industry, traditional collaborative filt ... Expand

Abstract: Despite of success in both research and industry, traditional collaborative filtering (CF) based recommender systems suffer from a fundamental problem, which lies in its dependence on users’ numeric ratings as its sole source of user preference information. User ratings are often unable to fully represent user preferences. As a result, it is difficult and error prone to identify genuinely similar users based on ratings only. On the other hand, online consumer product reviews have become a common source for consumers to share and acquire information about products, but there have been very few studies on how those text reviews can be analyzed and integrated with traditional CF approaches to improve the prediction of consumers’ preferences. We propose a novel approach to memory-based collaborative filtering called urCF (User Review enhanced Collaborative Filtering) that integrates user text reviews and user numeric ratings in order to model users’ preferences better and in turn improve the performance of CF-based recommender systems. This research extracts user opinions on individual item features from online reviews, and proposes a new weighting scheme by following the general idea of TF-IDF to measure the priority of item features in influencing users’ overall opinions on different items. This study also explores and compares two different methods for integrating user opinion into user similarity measurement. The proposed urCF system is evaluated against existing approaches using a dataset collected from Yahoo! Movies. The results show that urCF significantly improves the performance of memory-based CF systems. Collapse

Semantic filters: average absolute deviation

Topics: collaborative filtering recommender system online review usability information retrieval

Methods: descriptive statistic literature study term frequency–inverse document frequency product review computational algorithm
Impact of data characteristics on recommender systems performance
PDF
2012 | ACM Transactions on Management Information Systems | Citations: 7
Authors: Adomavicius, Gediminas; Zhang, Jingjing

Abstract: This article investigates the impact of rating data characteristics on the perfo ... Expand

Abstract: This article investigates the impact of rating data characteristics on the performance of several popular recommendation algorithms, including user-based and item-based collaborative filtering, as well as matrix factorization. We focus on three groups of data characteristics: rating space, rating frequency distribution, and rating value distribution. A sampling procedure was employed to obtain different rating data subsamples with varying characteristics; recommendation algorithms were used to estimate the predictive accuracy for each sample; and linear regression-based models were used to uncover the relationships between data characteristics and recommendation accuracy. Experimental results on multiple rating datasets show the consistent and significant effects of several data characteristics on recommendation accuracy. Collapse

Semantic filters: average absolute deviation

Topics: collaborative filtering recommender system digital service Netflix IT productivity

Methods: computational algorithm descriptive statistic machine learning regression analysis method experiment
REDUCING INFORMATION OVERLOAD: DESIGN AND EVALUATION OF FILTERING & RANKING ALGORITHMS FOR SOCIAL NETWORKING SITES

2012 | European Conference On Information Systems | Citations: 0
Authors: Koroleva, Ksenia; JosÃ, Antonio

Abstract: Recognizing the detrimental impact of information overload on user participation ... Expand

Abstract: Recognizing the detrimental impact of information overload on user participation, in this paper we design and evaluate several algorithms to filter and rank the information on Social Networking Sites (SNS). As a first step we identify the factors that impact user evaluations of information shared through these networks in a set of regression analyses. Second, we use a Neural Network algorithm to predict three dimensions of user evaluations: affective, cognitive and instrumental value of information shared. Moreover, we design algorithms that allow not only to filter out the irrelevant information, but also rank the information on SNS in order of its relevance. As a result, the filtering algorithm accurately predicts in 73% of the cases, whereas for more than 70% of the users the individual ranking accuracy lies over 70%. The designed algorithms can be implemented by SNS providers in order to present users with more relevant and better structured information. Collapse

Semantic filters: average absolute deviation

Topics: Facebook information overload application programming interface data relevance social network

Methods: computational algorithm artificial neural network usability testing binary classification regression analysis method
A trust-semantic fusion-based recommendation approach for e-business applications
PDF
2012 | Decision Support Systems | Citations: 0
Authors: Shambour, Qusai; Lu, Jie

Abstract: Collaborative Filtering (CF) is the most popular recommendation technique but st ... Expand

Abstract: Collaborative Filtering (CF) is the most popular recommendation technique but still suffers from data sparsity, user and item cold-start problems, resulting in poor recommendation accuracy and reduced coverage. This study incorporates additional information from the users' social trust network and the items' semantic domain knowledge to alleviate these problems. It proposes an innovative Trust–Semantic Fusion (TSF)-based recommendation approach within the CF framework. Experiments demonstrate that the TSF approach significantly outperforms existing recommendation algorithms in terms of recommendation accuracy and coverage when dealing with the above problems. A business-to-business recommender system case study validates the applicability of the TSF approach. Collapse

Semantic filters: average absolute deviation

Topics: electronic business business-to-business recommender system social network decision support system

Methods: computational algorithm experiment case study descriptive statistic sensitivity analysis
Enabling individualized recommendations and dynamic pricing of value-added services through willingness-to-pay data
PDF
2010 | Electronic Markets | Citations: 0
Authors: Backhaus, Klaus; Becker, Jörg; Beverungen, Daniel; Frohs, Margarethe; Müller, Oliver; Weddeling, Matthias; Knackstedt, Ralf; Steiner, Michael

Abstract: When managing their growing service portfolio, many manufacturers in B2B markets ... Expand

Abstract: When managing their growing service portfolio, many manufacturers in B2B markets face two significant problems: They fail to communicate the value of their service offerings and they lack the capability to generate profits with value-added services. To tackle these two issues, we have built and evaluated a collaborative filtering recommender system which (a) makes individualized recommendations of potentially interesting value-added services when customers express interest in a particular physical product and also (b) leverages estimations of a customer’s willingness to pay to allow for a dynamic pricing of those services and the incorporation of profitability considerations into the recommendation process. The recommender system is based on an adapted conjoint analysis method combined with a stepwise componential segmentation algorithm to collect individualized preference and willingness-to-pay data. Compared to other state-of-the-art approaches, our system requires significantly less customer input before making a recommendation, does not suffer from the usual sparseness of data and cold-start problems of collaborative filtering systems, and, as is shown in an empirical evaluation with a sample of 428 customers in the machine tool market, does not diminish the predictive accuracy of the recommendations offered. Collapse

Semantic filters: average absolute deviation

Topics: willingness to pay price management recommender system dynamic pricing collaborative filtering

Methods: conjoint analysis machine learning survey design artifact computational algorithm
TOWARDS AUTONOMIC COST-AWARE ALLOCATION OF CLOUD RESOURCES

2010 | International Conference on Information Systems | Citations: 0
Authors: Hedwig, Markus; Malkowski, Simon; Neumann, Dirk

Abstract: While clouds conceptually facilitate very fine-grained resource provisioning, in ... Expand

Abstract: While clouds conceptually facilitate very fine-grained resource provisioning, information systems that are able to fully leverage this potential remain an open research problem. This is due to factors such as significant reconfiguration lead-times and non-trivial dependencies between software and hardware resources. In this work we address these factors explicitly and introduce an accurate workload forecasting model, based on Fourier Transformation and stochastic processes, paired with an adaptive provisioning framework. By automatically identifying the key characteristics in the workload process and estimating the residual variation, our model forecasts the workload process in the near future with very high accuracy. Our preliminary experimental evaluation results show great promise. When evaluated empirically on a real Wikipedia trace our resource provisioning framework successfully utilizes the workload forecast module to achieve superior resource utilization efficiency under constant service level objective satisfaction. More generally, this work corroborates the potential of holistic cloud management approaches that fuse domain specific solutions from areas such as workload prediction, autonomic system management, and empirical analysis. Collapse

Semantic filters: average absolute deviation

Topics: Wikipedia cloud computing database system IS management IT productivity

Methods: experiment computational algorithm longitudinal research time series analysis stochastic model
A support system for predicting eBay end prices
PDF
2008 | Decision Support Systems | Citations: 6
Authors: van Heijst, Dennis; Potharst, Rob; van Wezel, Michiel

Abstract: We create a support system for predicting end prices on eBay. The end price pred ... Expand

Abstract: We create a support system for predicting end prices on eBay. The end price predictions are based on the item descriptions found in the item listings of eBay, and on some numerical item features. The system uses text mining and boosting algorithms from the field of machine learning. Our system substantially outperforms the naive method of predicting the category mean price. Moreover, interpretation of the model enables us to identify influential terms in the item descriptions and shows that the item description is more influential than the seller feedback rating, which was shown to be influential in earlier studies. Collapse

Semantic filters: average absolute deviation

Topics: extended reality internet technology decision support system online auction source code

Methods: computational algorithm experiment decision tree classification machine learning descriptive statistic
Across the Digital Divide: A Cross-Country Multi-Technology Analysis of the Determinants of IT Penetration

2005 | Journal of the Association for Information Systems | Citations: 0
Authors: Dewan, Sanjeev; Ganley, Dale; Kraemer, Kenneth L.

Abstract: This paper studies the country-level digital divide across successive generation ... Expand

Abstract: This paper studies the country-level digital divide across successive generations of IT, providing detailed insights into the magnitude and changing nature of the divide. We examine a panel of 40 countries from 1985-2001, based on data from three distinct generations of IT: mainframes, personal computers, and the Internet. Using two measures of IT penetration, we conduct an empirical investigation of socio-economic factors driving the digital divide. We find that IT penetration is positively associated with national income for all three technology generations, and the association between penetration and income is stronger for countries with higher levels of IT penetration. We also examine other demographic and economic factors, going beyond income, and find significant differences in the nature of their effects across countries at different stages of IT adoption. Importantly, factors that previously may have been expanding the divide with earlier technologies are narrowing the gap as the Internet becomes the defining technology of the Information Age. Collapse

Semantic filters: average absolute deviation

Topics: digital divide internet technology mainframe telephone technology adoption

Methods: descriptive statistic regression analysis method survey statistical hypothesis test longitudinal research

Page 1 of 2 Next

AIS11

Journals

Conferences

Semantic Filter

Found 12 articles

Handling the Efficiency–Personalization Trade-Off in Service Robotics: A Machine-Learning Approach

Data Analysis of Delays in Airline Networks

urCF: User Review Enhanced Collaborative Filtering

Impact of data characteristics on recommender systems performance

REDUCING INFORMATION OVERLOAD: DESIGN AND EVALUATION OF FILTERING & RANKING ALGORITHMS FOR SOCIAL NETWORKING SITES

A trust-semantic fusion-based recommendation approach for e-business applications

Enabling individualized recommendations and dynamic pricing of value-added services through willingness-to-pay data

TOWARDS AUTONOMIC COST-AWARE ALLOCATION OF CLOUD RESOURCES

A support system for predicting eBay end prices

Across the Digital Divide: A Cross-Country Multi-Technology Analysis of the Determinants of IT Penetration