Search results
1 – 10 of 319Fatemeh Ehsani and Monireh Hosseini
As internet banking service marketing platforms continue to advance, customers exhibit distinct behaviors. Given the extensive array of options and minimal barriers to switching…
Abstract
Purpose
As internet banking service marketing platforms continue to advance, customers exhibit distinct behaviors. Given the extensive array of options and minimal barriers to switching to competitors, the concept of customer churn behavior has emerged as a subject of considerable debate. This study aims to delineate the scope of feature optimization methods for elucidating customer churn behavior within the context of internet banking service marketing. To achieve this goal, the author aims to predict the attrition and migration of customers who use internet banking services using tree-based classifiers.
Design/methodology/approach
The author used various feature optimization methods in tree-based classifiers to predict customer churn behavior using transaction data from customers who use internet banking services. First, the authors conducted feature reduction to eliminate ineffective features and project the data set onto a lower-dimensional space. Next, the author used Recursive Feature Elimination with Cross-Validation (RFECV) to extract the most practical features. Then, the author applied feature importance to assign a score to each input feature. Following this, the author selected C5.0 Decision Tree, Random Forest, XGBoost, AdaBoost, CatBoost and LightGBM as the six tree-based classifier structures.
Findings
This study acclaimed that transaction data is a reliable resource for elucidating customer churn behavior within the context of internet banking service marketing. Experimental findings highlight the operational benefits and enhanced customer retention afforded by implementing feature optimization and leveraging a variety of tree-based classifiers. The results indicate the significance of feature reduction, feature selection and feature importance as the three feature optimization methods in comprehending customer churn prediction. This study demonstrated that feature optimization can improve this prediction by increasing the accuracy and precision of tree-based classifiers and decreasing their error rates.
Originality/value
This research aims to enhance the understanding of customer behavior on internet banking service platforms by predicting churn intentions. This study demonstrates how feature optimization methods influence customer churn prediction performance. This approach included feature reduction, feature selection and assessing feature importance to optimize transaction data analysis. Additionally, the author performed feature optimization within tree-based classifiers to improve performance. The novelty of this approach lies in combining feature optimization methods with tree-based classifiers to effectively capture and articulate customer churn experience in internet banking service marketing.
Details
Keywords
Ahmet Cetinkaya, Serhat Peker and Ümit Kuvvetli
The purpose of this study is to investigate and understand the performance of countries in individual Olympic Games, specifically focusing on the Tokyo 2020 Olympics. Employing…
Abstract
Purpose
The purpose of this study is to investigate and understand the performance of countries in individual Olympic Games, specifically focusing on the Tokyo 2020 Olympics. Employing cluster analysis and decision trees, the research aims to categorize countries based on their representation, participation and success.
Design/methodology/approach
This research employs a data-driven approach to comprehensively analyze and enhance understanding of countries' performances in individual Olympic Games. The methodology involves a two-stage clustering method and decision tree analysis to categorize countries and identify influential factors shaping their Olympic profiles.
Findings
The study, analyzing countries' performances in the Tokyo 2020 Olympics through cluster analysis and decision trees, identified five clusters with consistent profiles. Notably, China, Great Britain, Japan, Russian Olympic Committee and the United States formed a high-performing group, showcasing superior success, representation and participation. The analysis revealed a correlation between higher representation/participation and success in individual Olympic Games. Decision tree insights underscored the significance of population size, GDP per Capita and HALE index, indicating that countries with larger populations, better economic standing and higher health indices tended to perform better.
Research limitations/implications
The study has several limitations that should be considered. Firstly, the findings are based on data exclusively from the Tokyo 2020 Olympics, which may limit the generalizability of the results to other editions.
Practical implications
The research offers practical implications for policymakers, governments and sports organizations seeking to enhance their country's performance in individual Olympic Games.
Social implications
The research holds significant social implications by contributing insights that extend beyond the realm of sports.
Originality/value
The originality and value of this research lie in its holistic approach to analyzing countries' performances in individual Olympic Games, particularly using a two-stage clustering method and decision tree analysis.
Details
Keywords
Ali Pişirgen, Ali Mert Erdoğan and Serhat Peker
This study aims to identify the key hotel characteristics and facilities that significantly influence customer satisfaction based on Google review scores. By applying decision…
Abstract
Purpose
This study aims to identify the key hotel characteristics and facilities that significantly influence customer satisfaction based on Google review scores. By applying decision tree analysis, the research seeks to determine which aspects, such as service quality, hotel facilities and location, play pivotal roles in shaping customer experiences. The objective is to provide professional with practical recommendations to improve service quality and cultivate enduring customer loyalty.
Design/methodology/approach
The research used a data set collected from Hotels.com, featuring various characteristics of 802 hotels in Izmir Province. Decision tree analysis was conducted using Classification and Regression Tree algorithm to explore the relationship between hotel characteristics and facilities with customer satisfaction.
Findings
The analysis revealed that the number of rooms is the primary factor influencing hotel ratings, with proximity to the airport and hotel classification also being significant. Additional factors such as public transportation distance and laundry services were important, while facilities such as ATMs, beach access and spas showed no significant impact on customer satisfaction. These findings emphasize the importance of core facilities and accessibility.
Originality/value
This study contributes to the literature by offering a novel approach, using decision tree analysis to assess hotel customer satisfaction with structured data. It provides practical implications for hotel managers, enabling them to make data-driven improvements to achieve customer satisfaction. The integration rules created by the decision tree model into hotel management systems can enhance operational efficiency and competitive advantage in the hospitality industry.
Details
Keywords
Ruizhen Song, Xin Gao, Haonan Nan, Saixing Zeng and Vivian W.Y. Tam
This research aims to propose a model for the complex decision-making involved in the ecological restoration of mega-infrastructure (e.g. railway engineering). This model is based…
Abstract
Purpose
This research aims to propose a model for the complex decision-making involved in the ecological restoration of mega-infrastructure (e.g. railway engineering). This model is based on multi-source heterogeneous data and will enable stakeholders to solve practical problems in decision-making processes and prevent delayed responses to the demand for ecological restoration.
Design/methodology/approach
Based on the principle of complexity degradation, this research collects and brings together multi-source heterogeneous data, including meteorological station data, remote sensing image data, railway engineering ecological risk text data and ecological restoration text data. Further, this research establishes an ecological restoration plan library to form input feature vectors. Random forest is used for classification decisions. The ecological restoration technologies and restoration plant species suitable for different regions are generated.
Findings
This research can effectively assist managers of mega-infrastructure projects in making ecological restoration decisions. The accuracy of the model reaches 0.83. Based on the natural environment and construction disturbances in different regions, this model can determine suitable types of trees, shrubs and herbs for planting, as well as the corresponding ecological restoration technologies needed.
Practical implications
Managers should pay attention to the multiple types of data generated in different stages of megaproject and identify the internal relationships between these multi-source heterogeneous data, which provides a decision-making basis for complex management decisions. The coupling between ecological restoration technologies and restoration plant species is also an important factor in improving the efficiency of ecological compensation.
Originality/value
Unlike previous studies, which have selected a typical section of a railway for specialized analysis, the complex decision-making model for ecological restoration proposed in this research has wider geographical applicability and can better meet the diverse ecological restoration needs of railway projects that span large regions.
Details
Keywords
Biplab Bhattacharjee, Kavya Unni and Maheshwar Pratap
Product returns are a major challenge for e-businesses as they involve huge logistical and operational costs. Therefore, it becomes crucial to predict returns in advance. This…
Abstract
Purpose
Product returns are a major challenge for e-businesses as they involve huge logistical and operational costs. Therefore, it becomes crucial to predict returns in advance. This study aims to evaluate different genres of classifiers for product return chance prediction, and further optimizes the best performing model.
Design/methodology/approach
An e-commerce data set having categorical type attributes has been used for this study. Feature selection based on chi-square provides a selective features-set which is used as inputs for model building. Predictive models are attempted using individual classifiers, ensemble models and deep neural networks. For performance evaluation, 75:25 train/test split and 10-fold cross-validation strategies are used. To improve the predictability of the best performing classifier, hyperparameter tuning is performed using different optimization methods such as, random search, grid search, Bayesian approach and evolutionary models (genetic algorithm, differential evolution and particle swarm optimization).
Findings
A comparison of F1-scores revealed that the Bayesian approach outperformed all other optimization approaches in terms of accuracy. The predictability of the Bayesian-optimized model is further compared with that of other classifiers using experimental analysis. The Bayesian-optimized XGBoost model possessed superior performance, with accuracies of 77.80% and 70.35% for holdout and 10-fold cross-validation methods, respectively.
Research limitations/implications
Given the anonymized data, the effects of individual attributes on outcomes could not be investigated in detail. The Bayesian-optimized predictive model may be used in decision support systems, enabling real-time prediction of returns and the implementation of preventive measures.
Originality/value
There are very few reported studies on predicting the chance of order return in e-businesses. To the best of the authors’ knowledge, this study is the first to compare different optimization methods and classifiers, demonstrating the superiority of the Bayesian-optimized XGBoost classification model for returns prediction.
Details
Keywords
Jurui Zhang, Shan Yu, Raymond Liu, Guang-Xin Xie and Leon Zurawicki
This paper aims to explore factors contributing to music popularity using machine learning approaches.
Abstract
Purpose
This paper aims to explore factors contributing to music popularity using machine learning approaches.
Design/methodology/approach
A dataset comprising 204,853 songs from Spotify was used for analysis. The popularity of a song was predicted using predictive machine learning models, with the results showing the superiority of the random forest model across key performance metrics.
Findings
The analysis identifies crucial genre and audio features influencing music popularity. Additionally, genre specific analysis reveals that the impact of music features on music popularity varies across different genres.
Practical implications
The findings offer valuable insights for music artists, digital marketers and music platform researchers to understand and focus on the most impactful music features that drive the success of digital music, to devise more targeted marketing strategies and tactics based on popularity predictions, and more effectively capitalize on popular songs in this digital streaming age.
Originality/value
While previous research has explored different factors that may contribute to the popularity of music, this study makes a pioneering effort as the first to consider the intricate interplay between genre and audio features in predicting digital music popularity.
Details
Keywords
Ali Albada, Eimad Eldin Abusham, Chui Zi Ong and Khalid Al Qatiti
Empirical examinations of initial public offering (IPO) initial returns often rely heavily on linear regression models. However, these models can prove inefficient owing to their…
Abstract
Purpose
Empirical examinations of initial public offering (IPO) initial returns often rely heavily on linear regression models. However, these models can prove inefficient owing to their susceptibility to outliers, a common occurrence in IPO data. This study introduces a machine learning method, known as random forest, to address issues that linear regression may struggle to resolve.
Design/methodology/approach
The study’s sample comprises 352 fixed-priced IPOs from the year 2004 until 2021. A unique aspect of this research is its application of the random forest method. The accuracy of random forest in comparison to other methods is evaluated. The findings indicate that the random forest model significantly outperforms other methods in all of the evaluated aspects.
Findings
The variable importance measure indicates that investors’ demand, divergence of opinion among investors and offer price are the most crucial predictors of IPO initial returns. These determinants hold particular significance due to the widespread use of the fixed-price method in Malaysia, as this method amplifies the information asymmetry in the IPO market.
Originality/value
To the best of the authors’ knowledge, this study is among the pioneering works in Malaysian literature to apply the random forest method to address the constraints of conventional linear regression models. This is achieved by considering a more extensive array of factors and acknowledging the influence of outliers. Additionally, this study adds value to Malaysian literature by ranking and identifying the ex-ante information that best signals the issuing firm’s quality. This contribution facilitates prospective investors’ decision-making processes and provides issuing firms with effective means to communicate their value and quality to the IPO market.
Details
Keywords
Buse Un, Ercan Erdis, Serkan Aydınlı, Olcay Genc and Ozge Alboga
This study aims to develop a predictive model using machine learning techniques to forecast construction dispute outcomes, thereby minimizing economic and social losses and…
Abstract
Purpose
This study aims to develop a predictive model using machine learning techniques to forecast construction dispute outcomes, thereby minimizing economic and social losses and promoting amicable settlements between parties.
Design/methodology/approach
This study develops a novel conceptual model incorporating project characteristics, root causes, and underlying causes to predict construction dispute outcomes. Utilizing a dataset of arbitration cases in Türkiye, the model was tested using five machine learning algorithms namely Logistic Regression, Support Vector Machines, Decision Trees, K-Nearest Neighbors, and Random Forest in a Python environment. The performance of each algorithm was evaluated to identify the most accurate predictive model.
Findings
The analysis revealed that the Support Vector Machine algorithm achieved the highest prediction accuracy at 71.65%. Twelve significant variables were identified for the best model namely, work type, root causes, delays from a contractor, extension of time, different site conditions, poorly written contracts, unit price determination, penalties, price adjustment, acceptances, delay of schedule, and extra payment claims. The study’s results surpass some existing models in the literature, highlighting the model’s robustness and practical applicability in forecasting construction dispute outcomes.
Originality/value
This study is unique in its consideration of various contract, dispute, and project attributes to predict construction dispute outcomes using machine learning techniques. It uses a fact-based dataset of arbitration cases from Türkiye, providing a robust and practical predictive model applicable across different regions and project types. It advances the literature by comparing multiple machine learning algorithms to achieve the highest prediction accuracy and offering a comprehensive tool for proactive dispute management.
Details
Keywords
Franck Marle and François Robin
This paper aims to propose an accurate and efficient decision-making process adapted to the specific context of Claim Management situations, implying partners engaged in a…
Abstract
Purpose
This paper aims to propose an accurate and efficient decision-making process adapted to the specific context of Claim Management situations, implying partners engaged in a high-involvement relationship.
Design/methodology/approach
We used a three-step approach: first, an inductive phase based on 12 past case studies. Second, a theory-building phase. Third, a theory-testing phase based on an ongoing case study to observe and test our propositions.
Findings
Proposal 1: Partner’s Strategic Value is an influential decision parameter that must be incorporated into Claim Management-related decision-making processes in high-involvement relationships. Proposal 2: The Fast-and-Frugal Heuristic is adapted to the intense, interactive and iterative nature of the Claim Management context. Our final proposal combines these two findings, i.e. a Fast-and-Frugal Heuristic incorporating the Partner’s Strategic Value and based on using decision criteria as a sequence, not simultaneously.
Originality/value
In the context of high-involvement business relationships and Claim Management, this study introduces the importance of selecting an appropriate decision methodology and integrating a strategic decision parameter (Partner’s Strategic Value) into an operational decision-making context. Furthermore, the principle of considering decision parameters in a specific sequence corresponds to the iterative and interactive nature of the Claim Management processes.
Details
Keywords
This study aims to find the key drivers of green innovation in family firms by examining firm characteristics and geographical factors. It seeks to develop a conceptual framework…
Abstract
Purpose
This study aims to find the key drivers of green innovation in family firms by examining firm characteristics and geographical factors. It seeks to develop a conceptual framework that explains how internal resources and external environments influence environmental innovation practices in these businesses.
Design/methodology/approach
Using machine learning (ML) methods, this study develops a predictive model for green innovation in family firms, drawing on data from 3,289 family businesses across 27 EU Member States and 12 additional countries. The study integrates the Resource-Based View (RBV) and Location Theory to analyze the impact of firm-level resources and geographical contexts on green innovation outcomes.
Findings
The results show that both firm-specific resources, such as size, digital capabilities, years of operation and geographical factors, like country location, significantly influence the likelihood of family firms engaging in environmental innovation. Larger, technologically advanced firms are more likely to adopt sustainable practices, and geographic location is crucial due to different regulatory environments and market conditions.
Research limitations/implications
The findings reinforce the RBV by showing the importance of firm-specific resources in driving green innovation and extend Location Theory by emphasizing the role of geographic factors. The study enriches the theoretical understanding of family businesses by showing how noneconomic goals, such as socioemotional wealth and legacy preservation, influence environmental innovation strategies.
Practical implications
Family firms can leverage these findings to enhance their green innovation efforts by investing in technology, fostering sustainability and recognizing the impact of geographic factors. Aligning innovation strategies with both economic and noneconomic goals can help family businesses improve market positioning, comply with regulations and maintain a strong family legacy.
Originality/value
This research contributes a new perspective by integrating the RBV and Location Theory to explore green innovation in family firms, highlighting the interplay between internal resources and external environments. It also shows the effectiveness of machine learning methods in predicting environmental innovation, providing deeper insights than traditional statistical techniques.
Details