Deep Learning-Based Imputation Method to Enhance Crowdsourced Data on Online Business Directory Platforms for Improved Services

2023 | Journal of Management Information Systems | Citations: 0

Authors: Xu, Da; Hu, Paul Jen-Hwa; Fang, Xiao

Abstract: Popular online business directory (OBD) platforms, such as Yelp and TripAdvisor, ... Expand

Abstract: Popular online business directory (OBD) platforms, such as Yelp and TripAdvisor, depend on voluntarily user-submitted data about various businesses to assist consumers in finding appropriate options for transactions. Yet the crowdsourced nature of such data restricts the availability of attribute values for many businesses on the platform. Crowdsourced data often suffer serious completeness and timeliness constraints, with negative implications for key stakeholders such as users, businesses, and the platform. We thus develop a novel, deep learning–based imputation method, premised in institutional theory, to estimate missing attribute values of individual businesses on an OBD platform. The proposed method leverages a deep model architecture and considers both inter-business and inter-attribute relationships for imputations. An application to a Yelp data set reveals our method's greater imputation effectiveness relative to prevalent methods. To illustrate the method's practical utilities and values, we further examine the efficacy of business recommendations empowered by its imputed business attribute values, in comparison with those enabled by data imputed by benchmark methods. The results affirm that the proposed method substantially outperforms benchmarks for imputing missing attribute values and empowers more effective business recommendations. This study addresses crucial, prominent completeness and timeliness constraints in crowdsourced data on OBD platforms and offers insights for downstream applications that can improve user experiences, firm performance, and platform services. Collapse

Topics: missing data crowdsourcing data completeness wireless LAN healthcare data

Methods: data imputation autoencoder data transformation deep learning multivariate imputation with chained equations

Theories: institutional theory social learning theory

The impact of artificial intelligence on event experiences: a scenario technique approach

2021 | Electronic Markets | Citations: 2

Authors: Neuhofer, Barbara; Magnus, Bianca; Celuch, Krzysztof

Abstract: Digital technologies are transforming human relations, interactions and experien ... Expand

Abstract: Digital technologies are transforming human relations, interactions and experiences in the business landscape. Whilst a great potential of artificial intelligence (AI) in the service industries is predicted, the concrete influence of AI on customer experiences remains little understood. Drawing upon the service-dominant (SD) logic as a theoretical lens and a scenario technique approach, this study explores the impact of artificial intelligence as an operant resource on event experiences. The findings offer a conceptualisation of three distinct future scenarios for the year 2026 that map out a spectrum of experiences from value co-creation to value co-destruction of events. The paper makes a theoretical contribution in that it bridges marketing, technology and experience literature, and zooms in on AI as a non-human actor of future experience life ecosystems. A practical guideline for event planners is offered on how to implement AI across each touch point of the events ecosystem. Collapse

Topics: artificial intelligence participatory design electronic business decision making marketing management

Methods: design methodology multivariate imputation with chained equations theoretical contribution focus group

Advanced turbidity prediction for operational water supply planning

2019 | Decision Support Systems | Citations: 0

Authors: Stevenson, Matthew; Bravo, Cristián

Abstract: Turbidity is an optical quality of water caused by suspended solids that give th ... Expand

Abstract: Turbidity is an optical quality of water caused by suspended solids that give the appearance of ‘cloudiness'. While turbidity itself does not directly present a hazard to human health, it can be an indication of poor water quality and mask the presence of parasites such as Cryptosporidium. It is, therefore, a recommendation of the World Health Organisation (WHO) that turbidity should not exceed a level of 1 Nephelometric Turbidity Unit (NTU) before chlorination. For a drinking water supplier, turbidity peaks can be highly disruptive requiring the temporary shutdown of a water treatment works. Such events must be carefully managed to ensure continued supply; to recover the supply deficit, water stores must be depleted or alternative works utilised. Machine learning techniques have been shown to be effective for the modelling of complex environmental systems, often used to help shape environmental policy. We contribute to the literature by adopting such techniques for operational purposes, developing a decision support tool that predicts >1 NTU turbidity events up to seven days in advance allowing water supply managers to make proactive interventions. We apply a Generalised Linear Model (GLM) and a Random Forest (RF) model for the prediction of >1 NTU events. AUROC scores of over 0.80 at five of six sites suggest that machine learning techniques are suitable for predicting turbidity peaking events. Furthermore, we find that the RF model can provide a modest performance boost due to its stronger capacity to capture nonlinear interactions in the data. Collapse

Topics: decision support system missing data operational information system online learning system individual characteristic

Methods: machine learning correlation analysis longitudinal research random forest classification descriptive statistic

Pursuing weak paths: A Proposal for performance evaluation of imputation in PLS

2018 | International Conference on Information Systems | Citations: 0

Authors: Reitz, Andreas; Beimborn, Daniel

Abstract: The ongoing discussion about the use of Partial least squares structural equatio ... Expand

Abstract: The ongoing discussion about the use of Partial least squares structural equation modeling highlights a much bigger problem: the simplicity of handling makes it easy, to undervalue the required academic rigor (Petter 2018). As PLS obtains results for virtually any data, the problem is not restricted to structural and measurement models but also extends to the quality of the data. One important facet of data quality is completeness of data. Missing data occurs in all scientific areas. Yet, there seems to be a gap in methodical treatment in the IS and management literature. But, ignoring or mishandling missing data may reduce efficiency and power as well as bias the results and lead to inaccurate variances and standard deviations. Especially when it comes to PLS-SEM, most papers seem to not report the portion of missing data or how the researchers handled this issue. We therefore propose an evaluation of the most recent and advanced techniques in combination with PLS-SEM, in particular, multiple imputation by fully conditional specification (FCS MI). Collapse

Topics: missing data customer satisfaction mobile phone

Methods: data imputation partial least squares regression experiment decision tree classification structural equation modeling

Cognition-based Task Routing: Towards Highly-Effective Task-Assignments in Crowdsourcing Settings

2014 | International Conference on Information Systems | Citations: 0

Authors: Feldman, Michael; Bernstein, Abraham

Abstract: In recent years the rising popularity of outsourcing work to crowds has led to i ... Expand

Abstract: In recent years the rising popularity of outsourcing work to crowds has led to increasing importance to find an effective assignment of suitable workers with tasks. Even though attempts have been made in related areas such as expertise identification most crowdsocuring jobs today are assigned without any predefined policy. Whilst some have investigated assigning jobs based on availability or experience no dominant method has been identified so far. We propose an assignment of tasks to crowd-workers based on their cognitive capability, by conducting a set of cognitive tests and comparing them with performance on typical crowdtasks. Moreover, we examine different setups to predict task performance where a) cognitive abilities, b) performance on previous crowdtasks, or c) both of them, are partially known. Preliminary results show that cognition-based task assignment leads to an improvement in task performance prediction and may pave the way to more intelligent crowd-worker recruitment. Collapse

Topics: crowdsourcing task productivity collaborative filtering missing data Elance

Methods: experiment descriptive statistic data imputation multivariate imputation with chained equations singular value decomposition

Theories: cognitive load theory

Distributed decision support systems under limited degrees of competence: A simulation study

1997 | Decision Support Systems | Citations: 0

Authors: Dragoni, Aldo Franco

Abstract: We report the results of a simulation experiment inspired by a popular board gam ... Expand

Abstract: We report the results of a simulation experiment inspired by a popular board game. Nine agents are wandering, searching for clues to fill the three slots of a detective case. They have a limited perceptive capacity so that they can discern a clue badly. On meeting each others, agents exchange their current results. They can be insincere, i.e., they can provide false information to divert the others' investigations. Each agent is equipped with a same belief revision mechanism that makes them able to recognize and solve contradictions, assign a degree of credibility to each piece of information and assign a degree of reliability to each agent (itself included). The purpose of the experiment is that of evaluating the performances of the entire agency on the varying of the local strategies for belief revision and communication. Collapse

Topics: decision support system database system anonymity distributed system robotic

Methods: simulation experiment computational algorithm multivariate imputation with chained equations design artifact