A complexity of business dynamics often forces decision-makers to make decisions based on subjective mental models, reflecting their experience. However, research has shown that companies perform better when they apply data-driven decision-making. This creates an incentive to introduce intelligent, data-based decision models, which are comprehensive and support the interactive evaluation of decision options necessary for the business environment. Recently, a new general explanation methodology has been proposed, which supports the explanation of state-of-the-art black-box prediction models. Uniform explanations are generated on the level of model/individual instance and support what-if analysis. We present a novel use of this methodology inside an intelligent system in a real-world case of businessto-business (B2B) sales forecasting, a complex task frequently done judgmentally. Users can validate their assumptions with the presented explanations and test their hypotheses using the presented what-if parallel graph representation. The results demonstrate effectiveness and usability of the methodology. A signicant advantage of the presented method is the possibility to evaluate seller's actions and to outline general recommendations in sales strategy. This flexibility of the approach and easy-to-follow explanations are suitable for many different applications. Our well-documented real-world case shows how to solve a decision support problem, namely that the best performing black-box models are inaccessible to human interaction and analysis. This could extend the use of the intelligent systems to areas where they were so far neglected due to their insistence on comprehensible models. A separation of the machine learning model selection from model explanation is another signicant benefit for expert and intelligent systems. Explanations unconnected to a particular prediction model positively influence acceptance of new and complex models in the business environment through their easy assessment and switching.
COBISS.SI-ID: 7842323
This paper addresses the problem of weak acceptance of machine learning (ML) models in business. The proposed framework of top-performing ML models coupled with general explanation methods provides additional information to the decision-making process. This builds a foundation for sustainable organizational learning. To address user acceptance, participatory approach of action design research (ADR) was chosen. The proposed framework is demonstrated on a B2B sales forecasting process in an organizational setting, following CRISP-DM data mining methodology.The provided ML model explanations efficiently support business decision makers,reduce forecasting error for new sales opportunities, and facilitate discussion about the context of opportunities in the sales team. The quality and quantity of available data affects the performance of models and explanations. The application in the real-world company demonstrates utility of the approach and provides evidence that transparent explanations of ML models contribute to individual and organizational learning. All used methods are available as an open-source software and can improve acceptance of ML in data-driven decision-making. The proposed framework incorporates existing ML models and general explanation methodology into a decision-making process. To our knowledge, this is the first attempt to support organizational learning with a framework combining ML explanations, action design research and data mining methodology based on CRISP-DM industry standard.
COBISS.SI-ID: 7947795
This paper presents the results of research investigating the impact of business model factors on cloud computing adoption. The introduced research model consists of 40 cloud computing business model factors, grouped into eight factor groups. Their impact and importance for cloud computing adoption were investigated among enterpirses in Slovenia. Furthermore, differences in opinion according to enterprise size were investigated. Research results show no statistically significant impacts of investigated business model factor groups to cloud computing adoption. Nevertheless, based on slope coefficient directions and statistics values, some factor groups can be recognized as having moderate or strong, positive impact on cloud computing adoption; although their impact cannot be statistically confirmed with 95 % or 90 % levels of confidence. Furthermore, significant differences in opinion about the importance of business model factor groups and factors to cloud computing adoption according to enterprises size have been identified. The results represent a contribution to the theory of cloud computing adoption from the perspective of the provider%s business model. In addition, findings provide orientation for innovation of existing business models towards the creation of a customer-oriented business model for more successful exploitation of cloud computing services and new business opportunities.
COBISS.SI-ID: 7943443
Structural changes in farming present serious challenges at all spatial levels, from individual farms to the state level. The reorientation of a farm (i.e., changing from livestock production to one of horticulture or crops) represents one of these challenges. Here, a model assessing the potential for reorganizing farms to focus on horticulture is presented. The model accounts for various criteria, including: natural resources, demographic, economic, and social factors. The selection, structure, and importance of criteria and their interrelationships in the model are based on statistical data about farms, data gathered through surveys, and expert opinion groups. The model was developed using the Decision Expert method, implemented by the software DEXi, and was validated using a selection of farms. The added value of the approach is a transparent assessment of a farm’s potential, which provides vital support for deciding about its reorientation.
COBISS.SI-ID: 7944723
This study intends to clarify the understanding of the role of the contingency factors (i.e. long-term orientation, competitiveness and uncertainty) in the relation between sustainability practices (sustainability exploitation and sustainability exploration) and organizational performance. Using empirical data based on a large-scale survey among European organizations, this paper utilizes the regression analysis to gain insight into the relationship between sustainability practices and organizational performance. In general, the results support the contingency view of the relationship between sustainability practices and performance rather than relying upon “universal” view of sustainability practices. Particularly, the results show that in moderate environmental contexts (moderate competitiveness and uncertainty) sustainability exploitation practices seem to be a predominant predictor of organizational performance.
COBISS.SI-ID: 7966739