Divergent Innovation: Directing the Wisdom of Crowd to Tackle Societal Challenges

2023 | International Conference on Information Systems | Citations: 0

Authors: Cao, Chuhan; Zhu, Jiantao; Xiong, Bingqing; Lim, Eric; Liu, Hefu; Cai, Zhao; Tan, Chee-Wee

Abstract: Crowdsourcing is acknowledged as a promising avenue for addressing societal cha ... Expand

Abstract: Crowdsourcing is acknowledged as a promising avenue for addressing societal challenges by drawing on the wisdom of the crowd to offer diverse solutions to complex problems. Advancing a new conceptual framework of 'divergent innovation' which delineates between topic and quality divergence as focal metrics of performance when crowdsourcing for solutions to societal challenges, this study investigates the impacts of four ideation stimuli on divergent innovation. These four stimuli include task description concreteness, resource richness, topic entropy, and judging criteria comprehensiveness. Empirical analysis based on data sourced from an online crowd-ideation platform reveals that task description concreteness negatively affects topic divergence but positively influences quality divergence, whereas resource richness positively affects topic divergence but negatively influences quality divergence. Additionally, the relationship between topic entropy and topic divergence is U-shaped, with no significant impact on quality divergence. These findings contribute to extant literature on crowdsourcing and offer invaluable insights for practitioners. Collapse

Topics: innovation management societal challenge crowdsourcing evaluation criteria media richness

Methods: BERT literature study statistical hypothesis test regression analysis method language model

Exploring the Synergies in Human-AI Hybrids: A Longitudinal Analysis in Sales Forecasting

2023 | Americas Conference on Information Systems | Citations: 0

Authors: Fahse, Tobias; Schmitt, Anuschka

Abstract: Despite the promised potential of artificial intelligence (AI), insights into r ... Expand

Abstract: Despite the promised potential of artificial intelligence (AI), insights into real-life human-AI hybrids and their dynamics remain obscure. Based on digital trace data of over 1.4 million forecasting decisions over a 69-month period, we study the implications of an AI sales forecasting system's introduction in a bakery enterprise on decision-makers' overriding of the AI system and resulting hybrid performance. Decisionmakers quickly started to rely on AI forecasts, leading to lower forecast errors. Overall, human intervention deteriorated forecasting performance as overriding resulted in greater forecast error. The results confirm the notion that AI systems outperform humans in forecasting tasks. However, the results also indicate previously neglected, domain-specific implications: As the AI system aimed to reduce forecast error and thus overproduction, forecasting numbers decreased over time, and thereby also sales. We conclude that minimal forecast errors do not inevitably yield optimal business outcomes when detrimental human factors in decision-making are ignored. Collapse

Topics: artificial intelligence task productivity decision making IT productivity usability

Methods: digital trace data longitudinal research theory development ordinary least square qualitative interview

Theories: technology acceptance model socio technical theory

Near-Infrared Spectroscopy for Bladder Monitoring: A Machine Learning Approach

2023 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Fechner, Pascal; König, Fabian; Kratsch, Wolfgang; Lockl, Jannik; Röglinger, Maximilian

Abstract: Patients living with neurogenic bladder dysfunction can lose the sensation of th ... Expand

Abstract: Patients living with neurogenic bladder dysfunction can lose the sensation of their bladder filling. To avoid over-distension of the urinary bladder and prevent long-term damage to the urinary tract, the gold standard treatment is clean intermittent catheterization at predefined time intervals. However, the emptying schedule does not consider actual bladder volume, meaning that catheterization is performed more often than necessary, which can lead to complications such as urinary tract infections. Time-consuming catheterization also interferes with patients' daily routines and, in the case of an empty bladder, uses human and material resources unnecessarily. To enable individually tailored and volume-responsive bladder management, we design a model for the continuous monitoring of bladder volume. During our design science research process, we evaluate the model's applicability and usefulness through interviews with affected patients, prototyping, and application to a real-world in vivo dataset. The developed prototype predicts bladder volume based on relevant sensor data (i.e., near-infrared spectroscopy and acceleration) and the time elapsed since the previous micturition. Our comparison of several supervised state-of-the-art machine and deep learning models reveals that a long short-term memory network architecture achieves a mean absolute error of 116.7 ml that can improve bladder management for patients. Collapse

Topics: computer hardware open source mobile application user interface programming language

Methods: design artifact qualitative interview design process support vector machine computational algorithm

Green Data Analytics of Supercomputing from Massive Sensor Networks: Does Workload Distribution Matter?

2023 | Information Systems Research | Citations: 0

Authors: Guo, Zhiling; Li, Jin; Ramesh, Ram

Abstract: Energy costs represent a significant share of the total cost of ownership in hig ... Expand

Abstract: Energy costs represent a significant share of the total cost of ownership in high-performance computing (HPC) systems. Using a unique data set collected by massive sensor networks in a petascale national supercomputing center, we first present an explanatory model to identify key factors that affect energy consumption in supercomputing. Our analytic results show that, not only does computing node utilization significantly affect energy consumption, workload distribution among the nodes also has significant effects and could effectively be leveraged to improve energy efficiency. Next, we establish the high model performance using in-sample and out-of-sample analyses. We then develop prescriptive models for energy-optimal runtime workload management and extend the models to consider energy consumption and job performance tradeoffs. Specifically, we present four dynamic resource management methodologies (packing, load balancing, threshold-based switching, and energy optimization), model their application at two levels (purely within-rack and jointly cross-rack resource allocation), and explore runtime resource redistribution policies for jobs under the emergent principle of computational steering and comparatively evaluate strategies that use computational steering with those that do not. Our experimental studies show that packing is preferred when the total workload of a rack is higher than a threshold and load balancing is preferred when it is lower. These results lead to a threshold strategy that yields near-optimal energy efficiency under all workload conditions. We further calibrate the energy-optimal resource allocations over the full range of workloads and present a bicriteria evaluation to consider energy consumption and job performance tradeoffs. We demonstrate significant energy savings of our proposed strategies under various workload conditions. We conclude with implementation guidelines and policy insights into energy-efficient computing resource management in large supercomputing data centers. History: Olivia Liu Sheng, Senior Editor; Xiaobai Li, Associate Editor. Funding: The authors thank the National Supercomputing Center of Singapore for enabling and supporting this research. J. Li received support from the National Natural Science Foundation of China [Grants 71901169, 72032006, and T2293774]. Supplemental Material: The online appendices are available at https://doi.org/10.1287/isre.2023.1208. Collapse

Topics: data center high-performance computing task productivity resource allocation analytical information system

Methods: optimization model experiment simulation descriptive statistic longitudinal research

Addressing Learners' Heterogeneity in Higher Education: An Explainable AI-based Feedback Artifact for Digital Learning Environments

2023 | International Conference on Business Informatics | Citations: 0

Authors: Haag, Felix; Günther, Sebastian A.; Hopf, Konstantin; Handschuh, Philipp; Klose, Maria; Staake, Thorsten

Abstract: ... Expand

Abstract: Collapse

Topics: explainable artificial intelligence online learning system analytical information system project management IT project management

Methods: design science survey design principle design artifact two sample t-test with equal variance

Improved learning performance for small datasets in high dimensions by new dual-net model for non-linear interpolation virtual sample generation

2023 | Decision Support Systems | Citations: 0

Authors: Lin, Liang-Sian; Lin, Yao-San; Li, Der-Chiang; Liu, Yun-Hsuan

Abstract: The number of reliable samples obtained in early decision-making activity is usu ... Expand

Abstract: The number of reliable samples obtained in early decision-making activity is usually relatively small. Due to variable distribution and incomplete structure of tiny datasets, it is challenging to create reliable and robust predictive modeling using classic statistical and machine learning models in small sample settings. The virtual sample generation (VSG) technique improves model learning accuracies for minimal datasets across diverse applications. Virtual samples on independent variables were generated using established VSG methods predi­ cated on the assumption of a probability distribution or a membership function to fill data gaps. However, in the actual world, non-linear function interactions between variables are common. To address this issue, this paper developed a novel VSG method called Dual-VSG, which generates non-linear interpolation virtual samples using a self-supervised learning (SSL) framework to improve learning performance on small datasets. We generated non-linear interpolation virtual samples without labels by estimating non-linear functions and transforming them into a high-dimensional space using the proposed dual-net model. The weights of the dual-net model are transferred to a downstream task to generate virtual sample labels. To demonstrate the effectiveness of the suggested strategy, this research employed five datasets. On the Backpropagation Neural Networks (BPNN) predictive model, we compared the suggested method’s prediction performance to two state-of-the-art VSG approaches. To assess prediction performance on a regression dataset, the Mean Absolute Percentage Error (MAPE) and the Root Mean Square Error (RMSE) are used. Furthermore, the classification accuracy (ACC) and the Fl measure are used to assess classification capability on classification datasets. In addition, the paired t-test was utilized to see if the suggested Dual-VSG approach differed significantly from the other VSG methods in terms of RMSE, MAPE, accuracy (ACC), or F1 score. For short datasets, the suggested Dual-VSG method out­ performs those VSG methods, according to our experimental results. Collapse

Topics: Python programming language

Methods: data transformation t-distributed stochastic neighbor embedding experiment machine learning parametric test

A deep multi-embedding model for mobile application recommendation

2023 | Decision Support Systems | Citations: 0

Authors: Liu, Yi-Hung; Chen, Yen-Liang; Chang, Po-Ya

Abstract: With the explosion in the number of mobile applications, it becomes difficult an ... Expand

Abstract: With the explosion in the number of mobile applications, it becomes difficult and time-consuming for users to find the most suitable and interesting application from the millions of applications that exist today. Therefore, mobile app recommendation becomes a top priority to help people solve this problem. In previous studies, there are two common methods to solve this problem, one is to apply matrix factorization to the rating data to predict the target user's ratings for other applications, and the other is to predict ratings based on the user's review text. In addition to combining the above two traditional methods, this study also combines deep learning methods to generate better models. For rating data, we use a deep matrix factorization method to obtain latent factor vectors of users and items from the rating matrix to improve the embedding of ratings. For review text, we improve the text representation by using a multi-embedding approach. Most importantly, our model also incorporates deep neural networks with nonlinear transformation capabilities to extract more representative abstract features. We conduct experiments on datasets collected from the real world. Extensive experimental results show that our proposed method has better performance than other existing methods. Collapse

Topics: mobile application mobile application market recommender system digital distribution mobile system

Methods: BERT deep learning experiment sensitivity analysis artificial neural network

Estimating Life Cycle Sales of Technology Products with Frequent Repeat Purchases: A Fractional Calculus-Based Approach

2023 | Information Systems Research | Citations: 0

Authors: Lotfi, Aslan; Jiang, Zhengrui; Lotfi, Ali; Jain, Dipak C.

Abstract: Accurately predicting the sales trajectory of a product in its life cycle is cri ... Expand

Abstract: Accurately predicting the sales trajectory of a product in its life cycle is critically important for firms’ medium- and long-term planning. Because classic product-diffusion models such as the Bass model consider only initial product purchases, they are ill-fitted for sales prediction for today’s technology products with a shorter life cycle and frequent repeat purchases or subscription renewals. Despite the long tradition of product diffusion research, there exists no viable model option when repeat purchases constitute a large proportion of product sales. The present study introduces a new sales growth model, termed the generalized diffusion model with repeat purchases (GDMR), to fill this void. The GDMR formulates the growth rate of sales using a noninteger-order integral equation rather than the integer-order differential equation typically adopted in existing diffusion models. The GDMR is parsimonious and easy to implement. Empirical results show that the GDMR fits sales data with varying proportions of repeat purchases quite well, making it suitable for predicting sales of a wide variety of products. In addition, the GDMR can be extended to incorporate marketing mix variables, thus enhancing its applicability in business decision making. Furthermore, using both real and simulated data, we show that the GDMR can reliably recover a product’s adoption trend using only sales data, thus cementing its theoretical validity and empirical effectiveness. Finally, we show that the GDMR is superior to generic time series and machine learning models in predicting future product sales. History: Ram Gopal, Senior Editor; Wenjing Duan, Associate Editor. Supplemental Material: The online appendix is available at https://doi.org/10.1287/isre.2022.1131. Collapse

Topics: marketing management DVD innovation management diffusion of innovation tablet

Methods: longitudinal research time series analysis machine learning simulation autoregressive integrated moving average

Deep Learning in Predicting Real Estate Property Prices: A Comparative Study

2023 | HICSS | Citations: 0

Authors: Shi, D.; Zhang, H.; Guan, J.; Zurada, J.; Chen, Z.; Li, X.

Abstract: The dominant methods for real estate property price prediction or valuation are ... Expand

Abstract: The dominant methods for real estate property price prediction or valuation are multi-regression based. Regression-based methods are, however, imperfect because they suffer from issues such as multicollinearity and heteroscedasticity. Recent years have witnessed the use of machine learning methods but the results are mixed. This paper introduces the application of a new approach using deep learning models to real estate property price prediction. The paper uses a deep learning approach for modeling to improve the accuracy of real estate property price prediction with data representing sales transactions in a large metropolitan area. Three deep learning models, LSTM, GRU and Transformer, are created and compared with other machine learning and traditional models. The results obtained for the data set with all features clearly show that the RF and Transformer models outperformed the other models. LSTM and GRU models produced the worst results, suggesting that they are perhaps not suitable to predict the real estate price. Furthermore, the implementations of Transformer and RF on a data set with feature reduction produced even more accurate prediction results. In conclusion, our research shows that the performance of the Transformer model is close to the RF model. Both models produce significantly better prediction results than existing approaches in terms of accuracy. Collapse

Topics: Python open source

Methods: deep learning transformer model machine learning autoregressive moving average model experiment

A Human-in-the-Loop Segmented Mixed-Effects Modeling Method for Analyzing Wearables Data

2023 | ACM Transactions on Management Information Systems | Citations: 0

Authors: Srinivasan, Karthik; Currim, Faiz; Ram, Sudha

Abstract: Wearables are an important source of big data, as they provide real-time high-re ... Expand

Abstract: Wearables are an important source of big data, as they provide real-time high-resolution data logs of health indicators of individuals. Higher-order associations between pairs of variables is common in wearables data. Representing higher-order association curves as piecewise linear segments in a regression model makes them more interpretable. However, existing methods for identifying the change points for segmented modeling either overfit or have low external validity for wearables data containing repeated measures. Therefore, we propose a human-in-the-loop method for segmented modeling of higher-order pairwise associations between variables in wearables data. Our method uses the smooth function estimated by a generalized additive mixed model to allow the analyst to annotate change point estimates for a segmented mixed-effects model, and thereafter employs Brent's constrained optimization procedure to fine-tune the manually provided estimates. We validate our method using three real-world wearables datasets. Our method not only outperforms state-of-the-art modeling methods in terms of prediction performance but also provides more interpretable results. Our study contributes to health data science in terms of developing a new method for interpretable modeling of wearables data. Our analysis uncovers interesting insights on higher-order associations for health researchers. Collapse

Topics: smart wearable device mobile system analytical information system human computer interaction human in the loop

Methods: design science wearables based research conceptual modelling hierarchical linear modeling computational algorithm