Interpretable cost-sensitive regression through one-step boosting

2023 | Decision Support Systems | Citations: 0

Authors: Decorte, Thomas; Raymaekers, Jakob; Verdonck, Tim

Abstract: In most practical prediction problems, such as regression and classification, th ... Expand

Abstract: In most practical prediction problems, such as regression and classification, the different types of prediction errors are not equally costly in the decision-making process. Although there exist numerous real-world costsensitive regression problems, ranging from loan charge-off forecasting to house price predictions, the literature on cost-sensitive learning mainly focuses on classification and only a few solutions are proposed for regression problems. These regressions are typically characterized by an asymmetric cost structure, where over- and underpredictions of a similar magnitude face vastly different costs. In this paper, we present a one-step boosting method (OSB) for cost-sensitive regression. The proposed methodology leverages a secondary learner to incorporate cost-sensitivity into an already trained cost-insensitive regression model. The secondary learner is defined as a linear function of certain variables deemed interesting for cost-sensitivity. These variables do not necessarily need to be the same as in the already trained model. An efficient optimization algorithm is achieved through iteratively reweighted least squares using the asymmetric cost function. The obtained results become interpretable through bootstrapping, enabling decision makers to distinguish important variables for cost-sensitivity as well as facilitating statistical inference. Applying different cost functions and various initial cost-insensitive learning methods on several public datasets consistently yields a significant reduction in the average misprediction cost, illustrating the excellent performance of our approach. Collapse

Topics: Python decision making ease of use operating system Microsoft Windows

Methods: computational algorithm regression analysis method LightGBM boosting method linear regression analysis

In Search of Inspiration: External Mobility and the Emergence of Technology Intrapreneurs

2022 | Organization Science | Citations: 0

Authors: Ng, Weiyi; Sherman, Eliot L.

Abstract: Recent scholarship has established several ways in which external hiring—versus ... Expand

Abstract: Recent scholarship has established several ways in which external hiring—versus filling a role with a comparable internal candidate—is detrimental to firms. Yet, organizational learning theory suggests that external hires benefit firms: by importing knowledge that is unavailable or obscured to insiders and applying it toward experimentation and risky recombination. Accordingly and consistent with studies of learning by hiring and innovation, we predict that external hires are at greater risk of intrapreneurship than internal hires. We test this prediction via a study of product managers in large technology companies. We use machine learning to operationalize intrapreneurship by comparing product manager job descriptions with the founding statements of venture-backed technology entrepreneurs. Our research design employs coarsened exact matching to balance pretreatment covariates between product managers who arrived at their roles internally versus externally. The results of our analysis indicate that externally hired product managers are substantially more intrapreneurial than observably equivalent internal hires. However, we also find that intrapreneurial product managers have a higher turnover rate, an effect that is primarily driven by external hires. This suggests that hiring for intrapreneurship may be a difficult strategy to sustain. Funding: The authors acknowledge financial support from London Business School, the National University of Singapore [Grant WBS R-313-000-128-133], and a dissertation grant from the Ewing Kauffman Foundation, Kansas City, Missouri. Supplemental Material: The online appendix is available at https://doi.org/10.1287/orsc.2021.1530. Collapse

Topics: intrapreneurship LinkedIn IT career entrepreneurship online labor market

Methods: machine learning lasso regression nonparametric test logrank test experimental group

Theories: organizational learning theory

Incorporating External Trust Signals on Service Sharing Platforms

2018 | European Conference On Information Systems | Citations: 19

Authors: Otto, Lisa; Angerer, Peter; Zimmermann, Steffen

Abstract: Besides matchmaking, the major success factor of service sharing platforms is to ... Expand

Abstract: Besides matchmaking, the major success factor of service sharing platforms is to build trust in service providers. Therefore, service sharing platforms typically provide a rating system where service consumers can rate service providers, which signals the trustworthiness of service providers. Based on signaling theory, we examine if external trust signals, namely a star rating from another online platform and mutual friends between service providers and service consumers on social networks, can serve as alternative signals to build trust in service providers who have no rating at the service sharing platform yet. Using a laboratory experiment, we find that a star rating from another online platform positively influences trust in service providers, while mutual friends on social networks and the combination of both external trust signals have no significant influence. Furthermore, we find evidence that the combination slightly decreases trust in service providers compared to the sole presence of a star rating from another online platform. In addition, trust in service providers positively influences willingness to pay of service consumers. Consequently, service sharing platforms have to be aware that not every external trust signal increases trust in service providers and ultimately leads to a higher willingness to pay of service consumers. Collapse

Topics: social network willingness to pay sharing platform Facebook ride sharing platform

Methods: experiment laboratory experiment survey multiple linear regression statistical hypothesis test

Theories: signaling theory lemon market theory

Does Social Media Marketing Really Work for Online SMEs?: An Empirical Study

2016 | International Conference on Information Systems | Citations: 2

Authors: Ha, Sangwook; Kankanhalli, Atreyi; Kishan, Jai S; Huang, Ke-wei

Abstract: Social media has become a major channel for firms’ marketing communications. Yet ... Expand

Abstract: Social media has become a major channel for firms’ marketing communications. Yet studies on the impact of social media marketing (SMM) have been limited to a few large firms. Motivated by the lack of understanding of the effectiveness of SMM for small and medium-sized enterprises (SMEs), this study investigates the impact of online SMEs’ SMM messages on their sales performance through customer engagement. Fixed-effects regression analyses on weekly data from 288 online SMEs from the fashion retailing industry in China indicate that both customer endorsement and promotion information SMM messages positively influence customer engagement in the form of likes, shares, and comments. Additionally, customer engagement behaviors (likes and shares) lead to increased sales performance only if the SMEs verified their identity (a trust cue) with the social networking services and online e-commerce platform providers. Overall, the findings of this study highlight the crucial role of trust in SMEs’ SMM activities. Collapse

Topics: social media electronic commerce marketing management online marketing social media marketing

Methods: regression analysis method longitudinal research statistical hypothesis test theory development qualitative interview

A Hybrid Information System that Combines Statistical and Expert System Models for Decision Making

1995 | Americas Conference on Information Systems | Citations: 0

Authors: Lenard, Mary Jane; Madey, Gregory R; Alam, Pervaiz

Abstract: ... Expand

Abstract: Collapse

Topics: expert system spreadsheet decision making

Methods: nonparametric test M estimator protocol analysis artificial neural network