On the potentials of quantum computing – An interview with Heike Riel from IBM Research

2022 | Electronic Markets | Citations: 0

Authors: Alt, Rainer

Abstract: In this interview, Dr. Heike Riel, a leading scientist and Fellow at IBM Researc ... Expand

Abstract: In this interview, Dr. Heike Riel, a leading scientist and Fellow at IBM Research, reports on the current state of research in the field of quantum computing. Building on the distinction of gateable quantum computers and quantum annealers, the interview sheds light on how research has evolved on gateable quantum computers, which are the path developed by IBM. These gateable quantum computers are described with their current status as well as the improvements and challenges regarding speed, scale, and quality. All three parameters are important for increasing the performance of these universal quantum computers and for leveraging their potentials compared to classical computers. In particular, complex mathematical problems being present in numerous applications in science and business may be solved. Among the examples mentioned are optimization problems that tend to scale exponentially with the number of parameters, for example, in material and natural sciences or simulation problems in the financial industry and in manufacturing. The interview concludes with a critical assessment of possible risks and expectations for the future. Collapse

Topics: quantum computing computer hardware competitive advantage innovation management digital innovation

Methods: computational algorithm machine learning application qualitative interview

Adaptive cognitive fit: Artificial intelligence augmented management of information facets and representations

2022 | International Journal of Information Management | Citations: 2

Authors: Samuel, Jim; Kashyap, Rajiv; Samuel, Yana; Pelaez, Alexander

Abstract: Explosive growth in big data technologies and artificial intelligence (AI) appli ... Expand

Abstract: Explosive growth in big data technologies and artificial intelligence (AI) applications have led to increasing pervasiveness of information facets and a rapidly growing array of information representations. Information facets, such as equivocality and veracity, can dominate and significantly influence human perceptions of in­ formation and consequently affect human performance. Extant research in cognitive fit, which preceded the big data and AI era, focused on the effects of aligning information representation and task on performance, without sufficient consideration to information facets and attendant cognitive challenges. Therefore, there is a compelling need to understand the interplay of these dominant information facets with information representations and tasks, and their influence on human performance. We suggest that artificially intelligent technologies that can adapt information representations to overcome cognitive limitations are necessary for these complex information environments. To this end, we propose and test a novel “Adaptive Cognitive Fit” (ACF) framework that explains the influence of information facets and AI-augmented information representations on human performance. We draw on information processing theory and cognitive dissonance theory to advance the ACF framework and a set of propositions. We empirically validate the ACF propositions with an economic experiment that demonstrates the influence of information facets, and a machine learning simulation that establishes the viability of using AI to improve human performance. Collapse

Topics: artificial intelligence website digital ecosystem big data decision support

Methods: experiment simulation machine learning parametric test ANOVA

Theories: cognitive fit theory cognitive dissonance theory information processing theory information systems theory behavioral economics

Exploring Information Systems Curricula

2021 | Business & Information Systems Engineering | Citations: 2

Authors: Föll, Patrick; Thiesse, Frédéric

Abstract: The study considers the application of text mining techniques to the analysis of ... Expand

Abstract: The study considers the application of text mining techniques to the analysis of curricula for study programs offered by institutions of higher education. It presents a novel procedure for efficient and scalable quantitative content analysis of module handbooks using topic modeling. The proposed approach allows for collecting, analyzing, evaluating, and comparing curricula from arbitrary academic disciplines as a partially automated, scalable alternative to qualitative content analysis, which is traditionally conducted manually. The procedure is illustrated by the example of IS study programs in Germany, based on a data set of more than 90 programs and 3700 distinct modules. The contributions made by the study address the needs of several different stakeholders and provide insights into the differences and similarities among the study programs examined. For example, the results may aid academic management in updating the IS curricula and can be incorporated into the curricular design process. With regard to employers, the results provide insights into the fulfillment of their employee skill expectations by various universities and degrees. Prospective students can incorporate the results into their decision concerning where and what to study, while university sponsors can utilize the results in their grant processes. Collapse

Topics: IT skill database system IS curriculum Java soft skill

Methods: topic model natural language processing qualitative content analysis computational algorithm machine learning

Theories: complexity theory

Transfer Learning to enable Flexibility of Demand Forecasting: Dropout Profiles to protect from Negative Transfer

2021 | European Conference On Information Systems | Citations: 3

Authors: Hütsch, Marek

Abstract: One of the largest investments of a company is its implementation of an enterpr ... Expand

Abstract: One of the largest investments of a company is its implementation of an enterprise system. Sometimes, companies, and thus their enterprise systems, face changes that were not foreseen at the time the system was implemented. One example can be found in the COVID-19 pandemic in which retailers are facing the huge problem that current forecasting models no longer produce accurate forecasts and changes in feature spaces are needed. In this paper transfer learning and a proposed method, called dropout profiles, are used to react faster to changes in feature space. This method is implemented in a case study with changes in the feature space of a demand forecast. It is shown that the proposed method performs significantly better than traditional methods. In practice, this means that neural networks can expect a longer life cycle and companies can react faster to changes in the market. Collapse

Topics: enterprise information system knowledge sharing Python logistics management pandemic

Methods: artificial neural network case study simulation computational algorithm design science

LINDA-BN: An interpretable probabilistic approach for demystifying black-box predictive models

2021 | Decision Support Systems | Citations: 0

Authors: Moreira, Catarina; Chou, Yu-Liang; Velmurugan, Mythreyi; Ouyang, Chun; Sindhgatta, Renuka; Bruza, Peter

Abstract: The use of sophisticated machine learning models for critical decision-making fa ... Expand

Abstract: The use of sophisticated machine learning models for critical decision-making faces the challenge that these models are often applied as a ‘black-box’. This has led to an increased interest in interpretable machine learning, where post-hoc model-agnostic algorithms present a useful mechanism for generating interpretations of complex learning models. This paper proposes a novel approach based on Bayesian Networks to generate local post-hoc model-agnostic interpretations of a black-box predictive model. Consequently, the proposed approach presents features that are conditionally dependent between each other and that are directly influencing the class variable. This enables the decision-maker to better understand how features are related and why a certain prediction was made. Compared to the existing post-hoc interpretation methods, the contribution of our approach is three-fold: (1) as a probabilistic graphical model, the extracted Bayesian network can provide interpretations through conditional dependencies in a graphical structure regarding what input features and how/why they contributed to a prediction; (2) for complex decision problems with many features, a Markov blanket can be generated from the extracted Bayesian network to provide interpretations with a focused view on those input features that directly contributed to a prediction; (3) the extracted Bayesian network enables the identification of four different rules which can inform the decision-maker about the confidence level in a prediction, thus helping the decision-maker assess the reliability of predictions learned by a black-box model. We implemented the proposed approach, applied it in the context of two well-known public datasets and analysed the results, which are made available in an open-source repository: https://github.com/catarina-moreira/LINDA_DSS. Collapse

Topics: shapley additive explanation local interpretable model agnostic explanation explainable artificial intelligence

Methods: Bayesian network computational algorithm experiment decision tree classification deep learning

Theories: game theory

A two-stage machine learning framework to predict heart transplantation survival probabilities over time with a monotonic probability constraint

2020 | Decision Support Systems | Citations: 0

Authors: Ahady Dolatsara, Hamidreza; Chen, Ying-Ju; Evans, Christy; Gupta, Ashish; Megahed, Fadel M.

Abstract: The overarching goal of this paper is to develop a modeling framework that can b ... Expand

Abstract: The overarching goal of this paper is to develop a modeling framework that can be used to obtain personalized, data-driven and monotonically constrained probability curves. This research is motivated by the important problem of improving the predictions for organ transplantation outcomes, which can inform updates made to organ allocation protocols, post-transplantation care pathways, and clinical resource utilization. In pursuit of our overarching goal and motivating problem, we propose a novel two-stage machine learning-based framework for obtaining monotonic probabilities over time. The first stage uses the standard approach of using independent machine learning models to predict transplantation outcomes for each time-period of interest. In the second stage, we calibrate the survival probabilities over time using isotonic regression. To show the utility of our framework, we applied it on a national registry of U.S. heart transplants from 1987 to 2016. The first stage produces an area under the receiver operating curve (AUC) between 0.60 and 0.71 for years 1–10. While the 1year prediction AUC result is comparable to the reported results in the literature, our 10-year AUC of 0.70 is higher than the current state-of-the-art results. More importantly, we show that the application of isotonic regression to calibrate the survival probabilities for each patient over the 10-year period guarantees mono­ tonicity, while capitalizing on the data-driven and individualized nature of machine learning models. To pro­ mote future research, our code and analysis are publicly available on GitHub. Furthermore, we created a web app titled “H-TOP: Heart Transplantation Outcome Predictor” to encourage practical applications. Collapse

Topics: mobile application missing data web application decision making decision support system

Methods: machine learning data imputation computational algorithm support vector machine lasso regression

Automating Lead Scoring with Machine Learning: An Experimental Study

2020 | HICSS | Citations: 0

Authors: Nygård, Robert; Mezei, József

Abstract: Companies often gather a tremendous amount of data, such as browsing behavior, e ... Expand

Abstract: Companies often gather a tremendous amount of data, such as browsing behavior, email activities and other contact data. This data can be the source of important competitive advantage by utilizing it in estimating a contact's purchase probability using predictive analytics. The calculated purchase probability can then be used by companies to solve different business problems, such as optimizing their sales processes. The purpose of this article is to study how machine learning can be used to perform lead scoring as a special application case of purchase probabilities. Historical behavioral data is used as training data for the classification algorithm, and purchase moments are used to limit the behavioral data for the contacts that have purchased a product in the past. Different ways of aggregating time-series data are tested to ensure that limiting the activities of buyers does not result in model bias. The results suggest that it is possible to estimate the purchase probability of leads using supervised learning algorithms, such as random forest, and one can obtain novel business insights from the results using visual analytics relevant for decision makers. Collapse

Topics: business-to-consumer customer relationship management business-to-business visual analytics data visualization

Methods: machine learning random forest classification computational algorithm literature study artificial neural network

Towards Deep Learning for Weed Detection: Deep Convolutional Neural Network Architectures for Plant Seedling Classification

2020 | Americas Conference on Information Systems | Citations: 6

Authors: Ofori, Martinson; El-Gayar, Omar

Abstract: Traditional means of on-farm weed control mostly relies on manual labor. This p ... Expand

Abstract: Traditional means of on-farm weed control mostly relies on manual labor. This process is time consuming, costly and contributes to major yield losses. The conventional application of chemical weed control, however, goes against the strive for sustainability. To solve this using computer vision, precision agriculture researchers have used remote sensing weed maps, but this has been largely ineffective for early season weed control due to problems such as solar reflectance and cloud cover in satellite imagery. With the current advances in artificial intelligence, this study leverages the automatic feature extraction capabilities of deep convolutional neural networks (DCNN) to classify plant seedlings. In a comparative study, we demonstrate that DCNNs can successfully classify crops and weeds in various phenological growth stages. Our results indicate that while training DCNNs from scratch can achieve state-of-the-art performance for weed classification tasks, model performance can be improved by fine-tuning a pre-trained model. Collapse

Topics: artificial intelligence information system use digital transformation information technology capability Google+

Methods: experiment ImageNet Keras TensorFlow deep learning

Cultural Differences in Machine Learning Adoption: An International Comparison between Germany and the United States

2020 | European Conference On Information Systems | Citations: 9

Authors: Eitle, Verena; Buxmann, Peter

Abstract: Taking the lead in artificial intelligence (AI) forms part of the national agen ... Expand

Abstract: Taking the lead in artificial intelligence (AI) forms part of the national agenda of several countries. Despite the investment volume of other countries, Germany and the United States are superior in implementing AI applications due to their high number of early adopters. Therefore, one area of interest refers to the adoption of machine learning, as a subfield of AI, from a cultural and organizational perspective. Through qualitative research, this study explores how culture affects the technological, organizational, and environmental (TOE) determinants of machine learning adoption by conducting a comparative case study between Germany and the United States. Based on Hofstede's cultural dimensions and the TOE framework, the results of 21 expert interviews show that distinct cultural characteristics impact the TOE determinants. For instance, the varying extent of uncertainty avoidance results in different technological and environmental approaches. Germany tends to take preparatory actions for data management, while the low index of the United States is reflected in the absence of data protection regulations. By combining the TOE framework with a national culture construct, our study identifies cultural characteristics that influence machine learning adoption and, thus, could serve as a guideline for future cultural research and managerial decisions for machine learning adoption. Collapse

Topics: artificial intelligence national culture open source online learning system IT skill

Methods: machine learning case study machine learning application qualitative interview multiple case study

Theories: theory of everything cultural dimensions theory

CHALLENGES IN THE DEPLOYMENT AND OPERATION OF MACHINE LEARNING IN PRACTICE

2019 | European Conference On Information Systems | Citations: 0

Authors: Baier, Lucas; Jã, Fabian

Abstract: Machine learning has recently emerged as a powerful technique to increase operat ... Expand

Abstract: Machine learning has recently emerged as a powerful technique to increase operational efficiency or to develop new value propositions. However, the translation of a prediction algorithm into an operationally usable machine learning model is a time-consuming and in various ways challenging task. In this work, we target to systematically elicit the challenges in deployment and operation to enable broader practical dissemination of machine learning applications. To this end, we first identify relevant challenges with a structured literature analysis. Subsequently, we conduct an interview study with machine learning practitioners across various industries, perform a qualitative content analysis, and identify challenges organized along three distinct categories as well as six overarching clusters. Eventually, results from both literature and interviews are evaluated with a comparative analysis. Key issues identified include automated strategies for data drift detection and handling, standardization of machine learning infrastructure, and appropriate communication and expectation management. Collapse

Topics: organizational value data quality digital service analytical information system database system

Methods: qualitative interview cross sectional research structured literature research literature study machine learning