Search results

The purpose of this paper is to determine sales drivers for different OTC product categories.

The study uses data from both consumer and retail panels, which are gathered for various product categories. These long‐term data are analyzed per product category with two specific regression models, mainly time‐series analysis with VAR models and Shapley value regression.

It is found that purchase intention drives sales a lot in general. Besides, it is very important to distinguish seasonal vs non‐seasonal markets. The trend coefficient, which implies the stage of maturity of the market, indicates more or less saturated markets for the examples. The proposed models can be easily applied to different OTC categories without a lot of customization.

The study does not take into account different outlets (e.g. online, supermarkets) and does not estimate interaction effects between the single drivers.

The paper provides the market researcher with a guideline on how to proceed to model OTC product categories, e.g. which data are to be used, which models are to be estimated, which conclusions can be drawn.

The study develops an analysis approach which is readily applicable to different OTC product categories, which exhibit very distinct market characteristics. The advantage of this approach is that it applies a standardized tool kit of methods to analyze highly varying markets.

Engineering design and operational decisions depend largely on deep understanding of applications that requires assumptions for simplification of the problems in order to find proper solutions. Cutting-edge machine learning algorithms can be used as one of the emerging tools to simplify this process. In this paper, we propose a novel scalable and interpretable machine learning framework to automate this process and fill the current gap.

The essential principles of the proposed pipeline are mainly (1) scalability, (2) interpretibility and (3) robust probabilistic performance across engineering problems. The lack of interpretibility of complex machine learning models prevents their use in various problems including engineering computation assessments. Many consumers of machine learning models would not trust the results if they cannot understand the method. Thus, the SHapley Additive exPlanations (SHAP) approach is employed to interpret the developed machine learning models.

The proposed framework can be applied to a variety of engineering problems including seismic damage assessment of structures. The performance of the proposed framework is investigated using two case studies of failure identification in reinforcement concrete (RC) columns and shear walls. In addition, the reproducibility, reliability and generalizability of the results were validated and the results of the framework were compared to the benchmark studies. The results of the proposed framework outperformed the benchmark results with high statistical significance.

Although, the current study reveals that the geometric input features and reinforcement indices are the most important variables in failure modes detection, better model can be achieved with employing more robust strategies to establish proper database to decrease the errors in some of the failure modes identification.

The purpose of this paper is: to review the most commonly used approaches to the classification of quality attributes according to the Kano model; to identify the theoretical/practical strengths and weaknesses of these techniques; and to provide guidance for future research and managerial practice in this area.

Based on an extensive review of the literature on the Kano model and the relevant marketing/management literature, five approaches (Kano's method; “penalty‐reward contrast analysis”; “importance grid”; qualitative data methods; and “direct classification”) are evaluated in terms of their validity and reliability for categorising attributes in the Kano model. Several illustrative examples provide empirical evidence for the theoretical arguments advanced in the study.

The Kano questionnaire and the direct‐classification method are the only approaches that are capable of classifying Kano attributes in the design stage of a product/service. Penalty‐reward contrast analysis (PRCA) is useful for assessing the impact of product/service attributes on overall satisfaction with a product/service, but its applicability to the classification of Kano attributes is questionable. The importance grid (IG) is not recommended for use with the Kano model. The critical incident technique and the analysis of complaints/compliments are valid for the Kano model, but have questionable reliability.

The study makes some important points about accurate semantic terminology in describing issues related to the Kano model. In particular, researchers should be aware that an attractive quality element (must‐be quality element, respectively) might in fact be a dissatisfier (satisfier, respectively), due to significant conceptual differences between performance in terms of the Kano model (i.e. objective performance) and subjective performance perceptions.

The purpose of this study is to review and synthesise recent studies in the sharing economy literature and identify the knowledge gap and future opportunities for hospitality and tourism researchers.

The study commences by introducing sharing economy models and strategic frameworks for profitable service enabler performance. Following this, it identifies emerging overarching theories (e.g. complexity theory, social exchange theory, norm activation model, and value co-creation) and some emerging themes (i.e. trust and reputation, disruptive behaviour, choice and segmentation, pricing strategies, socially excluded consumers, personality and satisfaction) in current hospitality and tourism studies from top-tier journals.

The findings of the study suggest new paths for advancing theoretical and practical implications for hospitality and tourism studies.

The themes, models and overarching theories reviewed in this study are relevant and insightful across the fulcrum of hospitality and tourism research. It offers several useful guides for practitioners and academics to trace relevant literature on different aspects of sharing economy and perceptibly highlight the gaps in existing studies.

The paper provides new directions to broaden interdisciplinary and multidisciplinary approaches undertaken by scholars within both the field of hospitality and tourism management and beyond.

We examine the influence of ownership structure on a blockholder’s power in a firm. We first describe the presence and ownership stakes of blockholders in a comprehensive sample of US firms. We develop a measure of the influence of the ownership structure on a blockholder’s power and show that an average blockholder loses 12% of her potential power due to the presence and size of the ownership stakes of other blockholders. Further, the influence of ownership structure varies systematically with a blockholder’s rank and identity, with the second and nonfamily manager blockholders experiencing the largest loss of power.

Allocation of the marketing budget has become increasingly challenging due to the diverse channel exposure to customers. This study aims to enhance global marketing knowledge by introducing an ensemble attribution model to optimize marketing budget allocation for online marketing channels. As empirical research, this study demonstrates the supremacy of the ensemble model over standalone models.

The transactional data set for car insurance from an Indian insurance aggregator is used in this empirical study. The data set contains information from more than three million platform visitors. A robust ensemble model is created by combining results from two probabilistic models, namely, the Markov chain model and the Shapley value. These results are compared and validated with heuristic models. Also, the performances of online marketing channels and attribution models are evaluated based on the devices used (i.e. desktop vs mobile).

Channel importance charts for desktop and mobile devices are analyzed to understand the top contributing online marketing channels. Customer relationship management-emailers and Google cost per click a paid advertising is identified as the top two marketing channels for desktop and mobile channels. The research reveals that ensemble model accuracy is better than the standalone model, that is, the Markov chain model and the Shapley value.

To the best of the authors’ knowledge, the current research is the first of its kind to introduce ensemble modeling for solving attribution problems in online marketing. A comparison with heuristic models using different devices (desktop and mobile) offers insights into the results with heuristic models.

The study seeks to identify the impact of variables in a deep learning-based bankruptcy prediction model, which has achieved superior performance to other prediction models but cannot easily interpret hidden processes.

This study developed three LSTM-RNN–based models that predicted the probability of bankruptcy before 1, 2 and 3 years using financial, the construction market and macroeconomic variables as input variables. Then, the impacts of the input variables that affected prediction accuracy in each model were identified by using Shapley value and compared among the three models. This study also investigated the prediction accuracy using variants of input variables grouped sequentially by high-impact ranking.

The results showed that the prediction accuracies were largely impacted by “housing starts” in all models. As the prediction period increased, the effects of macroeconomic variables on prediction accuracy increased, whereas the impact of “return on assets” on prediction accuracy decreased. It also found that the “current ratio” and “debt ratio” significantly influenced the prediction accuracies in all models. Also, the results revealed that similar prediction accuracies could be achieved using only 8, 10, and 10 variables out of a total of 18 variables for the 1-, 2-, and 3-year prediction models, respectively.

This study provides a Shapley value-based approach to identify how each input variable in a deep-learning bankruptcy prediction model. The findings of this study can not only assist in obtaining better insights into the underlying concept of bankruptcy but also use to select variables by removing those identified as less significant.

This study aims to develop a regression-based machine learning model to predict housing price, determine and interpret factors that contribute to housing prices using different data sets available publicly. The significant determinants that affect housing prices will be first identified by using multinomial logistics regression (MLR) based on the level of relative importance. A comprehensive study is then conducted by using SHapley Additive exPlanations (SHAP) analysis to examine the features that cause the major changes in housing prices.

Predictive analytics is an effective way to deal with uncertainties in process modelling and improve decision-making for housing price prediction. The focus of this paper is two-fold; the authors first apply regression analysis to investigate how well the housing independent variables contribute to the housing price prediction. Two data sets are used for this study, namely, Ames Housing dataset and Melbourne Housing dataset. For both the data sets, random forest regression performs the best by achieving an average R² of 86% for the Ames dataset and 85% for the Melbourne dataset, respectively. Second, multinomial logistic regression is adopted to investigate and identify the factor determinants of housing sales price. For the Ames dataset, the authors find that the top three most significant factor variables to determine the housing price is the general living area, basement size and age of remodelling. As for the Melbourne dataset, properties having more rooms/bathrooms, larger land size and closer distance to central business district (CBD) are higher priced. This is followed by a comprehensive analysis on how these determinants contribute to the predictability of the selected regression model by using explainable SHAP values. These prominent factors can be used to determine the optimal price range of a property which are useful for decision-making for both buyers and sellers.

By using the combination of MLR and SHAP analysis, it is noticeable that general living area, basement size and age of remodelling are the top three most important variables in determining the house’s price in the Ames dataset, while properties with more rooms/bathrooms, larger land area and closer proximity to the CBD or to the South of Melbourne are more expensive in the Melbourne dataset. These important factors can be used to estimate the best price range for a housing property for better decision-making.

A limitation of this study is that the distribution of the housing prices is highly skewed. Although it is normal that the properties’ price is normally cluttered at the lower side and only a few houses are highly price. As mentioned before, MLR can effectively help in evaluating the likelihood ratio of each variable towards these categories. However, housing price is originally continuous, and there is a need to convert the price to categorical type. Nonetheless, the most effective method to categorize the data is still questionable.

The key point of this paper is the use of explainable machine learning approach to identify the prominent factors of housing price determination, which could be used to determine the optimal price range of a property which are useful for decision-making for both the buyers and sellers.