Up to the present, various methods such as Data Mining, Machine Learning, and Artificial Intelligence have been used to get the best assess from huge and important data resource. Deep Learning, one of these methods, is extended version of Artificial Neural Networks. Within the scope of this study, a model has been developed to classify the success of tele-marketing with different machine learning algorithms especially with Deep Learning algorithm. Naïve Bayes, C5.0, Extreme Learning Machine and Deep Learning algorithms have been used for modelling. To examine the effect of class label distribution on model success, Synthetic Minority Oversampling Technique have been used. The results have revealed the success of Deep Learning and Decision Trees algorithms. When the data set was not balanced, the Deep Learning algorithm performed better in terms of sensitivity. Among all models, the best performance in terms of accuracy, precision and F-score have been achieved with the C5.0 algorithm.
{"title":"Machine Learning Approach and Model Performance Evaluation for Tele-Marketing Success Classification","authors":"F. Koçoğlu, Şakir Esnaf","doi":"10.4018/ijban.298014","DOIUrl":"https://doi.org/10.4018/ijban.298014","url":null,"abstract":"Up to the present, various methods such as Data Mining, Machine Learning, and Artificial Intelligence have been used to get the best assess from huge and important data resource. Deep Learning, one of these methods, is extended version of Artificial Neural Networks. Within the scope of this study, a model has been developed to classify the success of tele-marketing with different machine learning algorithms especially with Deep Learning algorithm. Naïve Bayes, C5.0, Extreme Learning Machine and Deep Learning algorithms have been used for modelling. To examine the effect of class label distribution on model success, Synthetic Minority Oversampling Technique have been used. The results have revealed the success of Deep Learning and Decision Trees algorithms. When the data set was not balanced, the Deep Learning algorithm performed better in terms of sensitivity. Among all models, the best performance in terms of accuracy, precision and F-score have been achieved with the C5.0 algorithm.","PeriodicalId":42590,"journal":{"name":"International Journal of Business Analytics","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49087883","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this study, the most suitable normalization techniques for the multi-criteria decision making (MCDM) method proposed by Biswas and Saha were compared and a real situation was analyzed. In the study, the financial performance of the top 10 companies on the FORTUNE 500 list for 2019 was evaluated using seven financial ratios and five well-known normalization techniques. The results have shown that the max normalization procedure generated the most consistent results for Biswas and Saha’s MCDM method. The study is the first to test the suitability of different normalization techniques for the MCDM method proposed by Biswas and Saha. Also, this paper provides decision support that can be used for the selection of the best normalization techniques for other MCDM methods.
{"title":"The Influence of Statistical Normalization Techniques on Performance Ranking Results","authors":"Nazlı Ersoy","doi":"10.4018/ijban.298017","DOIUrl":"https://doi.org/10.4018/ijban.298017","url":null,"abstract":"In this study, the most suitable normalization techniques for the multi-criteria decision making (MCDM) method proposed by Biswas and Saha were compared and a real situation was analyzed. In the study, the financial performance of the top 10 companies on the FORTUNE 500 list for 2019 was evaluated using seven financial ratios and five well-known normalization techniques. The results have shown that the max normalization procedure generated the most consistent results for Biswas and Saha’s MCDM method. The study is the first to test the suitability of different normalization techniques for the MCDM method proposed by Biswas and Saha. Also, this paper provides decision support that can be used for the selection of the best normalization techniques for other MCDM methods.","PeriodicalId":42590,"journal":{"name":"International Journal of Business Analytics","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47919000","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Marcos Paulo Valadares de Oliveira, Kevin McCormack, Marcelo Bronzo, P. Trkman
Decision makers are exposed to an increasing amount of information. Algorithms can help people make better data-driven decisions. Previous research has focused on both companies’ orientation towards analytics use and the required skills of individual decision makers. However, each individual can make either analytically based or intuitive decisions. We investigated the characteristics that influence the likelihood of making analytical decisions, focusing on both analytical orientation and capabilities of individuals. We conducted a survey using 462 business students as proxies for decision makers and used partial least squares path modeling to show that analytical capabilities and analytical orientation influence each other and affect analytical decision-making, thereby impacting decision quality and decision regret. Our findings suggest that when implementing business analytics solutions, companies should focus on the development not only of technological capabilities and individuals’ skills but also of individuals’ analytical orientation.
{"title":"The Effect of Individual Analytical Orientation and Capabilities on Decision Quality and Regret","authors":"Marcos Paulo Valadares de Oliveira, Kevin McCormack, Marcelo Bronzo, P. Trkman","doi":"10.4018/ijban.288510","DOIUrl":"https://doi.org/10.4018/ijban.288510","url":null,"abstract":"Decision makers are exposed to an increasing amount of information. Algorithms can help people make better data-driven decisions. Previous research has focused on both companies’ orientation towards analytics use and the required skills of individual decision makers. However, each individual can make either analytically based or intuitive decisions. We investigated the characteristics that influence the likelihood of making analytical decisions, focusing on both analytical orientation and capabilities of individuals. We conducted a survey using 462 business students as proxies for decision makers and used partial least squares path modeling to show that analytical capabilities and analytical orientation influence each other and affect analytical decision-making, thereby impacting decision quality and decision regret. Our findings suggest that when implementing business analytics solutions, companies should focus on the development not only of technological capabilities and individuals’ skills but also of individuals’ analytical orientation.","PeriodicalId":42590,"journal":{"name":"International Journal of Business Analytics","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49217260","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In order to reduce the growing negative impact of CO2 emissions, manufacturing firms have begun to refocus efforts on energy management. Several studies have focused on drivers and inhibitors of energy management but few regarding manufacturing energy management maturity. This study investigates both drivers and the role of knowledge management on manufacturing energy management maturity. Using multivariate analyses, questionnaire data from manufacturing personnel throughout the United States is utilized to assess these relationships. The results provide the support that economic followed by organizational and corporate social responsibility (CSR) positively impact knowledge management practices within organizations. Additionally, this study provides support that knowledge management practices within U.S. manufacturing organizations have a positive association with environmental management maturity. Findings contribute to theory and practical knowledge by highlighting the configurational effects of knowledge management and energy management maturity.
{"title":"Energy Management in Manufacturing","authors":"Mehrnaz Khalaj Hedayati, Dara G. Schniederjans","doi":"10.4018/ijban.314224","DOIUrl":"https://doi.org/10.4018/ijban.314224","url":null,"abstract":"In order to reduce the growing negative impact of CO2 emissions, manufacturing firms have begun to refocus efforts on energy management. Several studies have focused on drivers and inhibitors of energy management but few regarding manufacturing energy management maturity. This study investigates both drivers and the role of knowledge management on manufacturing energy management maturity. Using multivariate analyses, questionnaire data from manufacturing personnel throughout the United States is utilized to assess these relationships. The results provide the support that economic followed by organizational and corporate social responsibility (CSR) positively impact knowledge management practices within organizations. Additionally, this study provides support that knowledge management practices within U.S. manufacturing organizations have a positive association with environmental management maturity. Findings contribute to theory and practical knowledge by highlighting the configurational effects of knowledge management and energy management maturity.","PeriodicalId":42590,"journal":{"name":"International Journal of Business Analytics","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"49323846","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, the authors create, justify, and document a system dynamics model of the oil and gas production within the Permian Basin of Texas. Then the researchers show how to fit the model to historical time series data (big data). The authors use the model to better understand the process structure, the production dynamics, and to explore the deleterious consequences of limited pipeline capacity in the Permian Basin. The model is also employed to better understand how to increase revenues derived from the basin. From this model, numerous suggestions are made as to how to improve the overall revenue and profitability coming from the Permian Basin. The model's ultimate purposes and its associated big data are to foster a basic appreciation of the causality inherent in the ‘system' and how basic model parameters affect and influence measures of model performance.
{"title":"Applications of System Dynamics and Big Data to Oil and Gas Production Dynamics in the Permian Basin","authors":"J. Burns, Pinyarat Sirisomboonsuk","doi":"10.4018/ijban.314223","DOIUrl":"https://doi.org/10.4018/ijban.314223","url":null,"abstract":"In this paper, the authors create, justify, and document a system dynamics model of the oil and gas production within the Permian Basin of Texas. Then the researchers show how to fit the model to historical time series data (big data). The authors use the model to better understand the process structure, the production dynamics, and to explore the deleterious consequences of limited pipeline capacity in the Permian Basin. The model is also employed to better understand how to increase revenues derived from the basin. From this model, numerous suggestions are made as to how to improve the overall revenue and profitability coming from the Permian Basin. The model's ultimate purposes and its associated big data are to foster a basic appreciation of the causality inherent in the ‘system' and how basic model parameters affect and influence measures of model performance.","PeriodicalId":42590,"journal":{"name":"International Journal of Business Analytics","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44526927","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nihan Yıldırım, Birden Tuluğ Siyahi, Oğuz Özbek, Imran Ahioğlu, Almira Selin Kahya
With the introduction of Industry 4.0 and supporting technologies, both service and manufacturing companies faced external and internal pressure for "going digital". In many cases, companies cannot decide on the digitalisation initiative due to preliminary groundwork to justify the required investment. For digitalisation priority setting under uncertain benefits, available digital technology selection methods lack the focus on process needs and do not fully utilise quality management tools in the Multi Criteria Decision Making (MCDM) framework. In this context, this study aims to propose a novel, context-independent, and process-based Digital Opportunity Priority Assessment (DOPA) methodology. The proposed approach utilizes critical to quality measures (CTQs), the causes with potential adversary effects as alternatives, and the importance, frequency, and digital control level of CTQs as the criteria in TOPSIS. AHP and Fuzzy AHP validate CTQ importance criteria. The study also presents a real industry application to validate the proposed model.
{"title":"A Combined Multi-Criteria Decision-Making Framework for Process-Based Digitalisation Opportunity and Priority Assessment (DOPA)","authors":"Nihan Yıldırım, Birden Tuluğ Siyahi, Oğuz Özbek, Imran Ahioğlu, Almira Selin Kahya","doi":"10.4018/ijban.298018","DOIUrl":"https://doi.org/10.4018/ijban.298018","url":null,"abstract":"With the introduction of Industry 4.0 and supporting technologies, both service and manufacturing companies faced external and internal pressure for \"going digital\". In many cases, companies cannot decide on the digitalisation initiative due to preliminary groundwork to justify the required investment. For digitalisation priority setting under uncertain benefits, available digital technology selection methods lack the focus on process needs and do not fully utilise quality management tools in the Multi Criteria Decision Making (MCDM) framework. In this context, this study aims to propose a novel, context-independent, and process-based Digital Opportunity Priority Assessment (DOPA) methodology. The proposed approach utilizes critical to quality measures (CTQs), the causes with potential adversary effects as alternatives, and the importance, frequency, and digital control level of CTQs as the criteria in TOPSIS. AHP and Fuzzy AHP validate CTQ importance criteria. The study also presents a real industry application to validate the proposed model.","PeriodicalId":42590,"journal":{"name":"International Journal of Business Analytics","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43447505","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the fourth industrial revolution period, multinational companies and start-ups have applied a sharing economy concept to their business and have attempted to better serve customer demand by integrating demand prediction results into their business operations. For survival amongst today’s fierce competition, companies need to upgrade their prediction model to better predict customer demand in a more accurate manner. This study explores a new feature for bike share demand prediction models that resulted in an improved RMSLE score. By applying this new feature, the number of daily vehicle accidents reported in the Washington, D.C. area, to the Random Forest, XGBoost, and LightGBM models, the RMSLE score results improved. Many previous studies have primarily focused on feature engineering and regression techniques within given dataset. However, this study is meaningful because it focuses more on finding a new feature from an external data source.
{"title":"Prediction of Bike Share Demand by Machine Learning","authors":"Tae You Kim, M. Park, J. Shin, Sung-Baik Oh","doi":"10.4018/ijban.288513","DOIUrl":"https://doi.org/10.4018/ijban.288513","url":null,"abstract":"In the fourth industrial revolution period, multinational companies and start-ups have applied a sharing economy concept to their business and have attempted to better serve customer demand by integrating demand prediction results into their business operations. For survival amongst today’s fierce competition, companies need to upgrade their prediction model to better predict customer demand in a more accurate manner. This study explores a new feature for bike share demand prediction models that resulted in an improved RMSLE score. By applying this new feature, the number of daily vehicle accidents reported in the Washington, D.C. area, to the Random Forest, XGBoost, and LightGBM models, the RMSLE score results improved. Many previous studies have primarily focused on feature engineering and regression techniques within given dataset. However, this study is meaningful because it focuses more on finding a new feature from an external data source.","PeriodicalId":42590,"journal":{"name":"International Journal of Business Analytics","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45784054","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The paper develops an order quantity model with trade credit plus shortages under learning effects for deteriorating imperfect quality products. Generally, when the lot has imperfect items, the inspection of a lot is necessary to improve the quality of the lot. In this article, the seller provides a defective lot to his buyer under credit financing scheme, and after that buyer separates the whole lot under the screening process into two categories, one is defective and the other is non-defective items. The buyer sells out defective items at a low price as compared to non-defective items. It is assumed that customers' demand of good quality items is greater than the inspection rate for the whole lot to neglect the shortages situation. After keeping all points together, the buyer optimized his total profit concerning order quantity and shortage. A suitable numerical example and a sensitivity analysis have been provided for the validity of this model. The aim and utility of this paper have been presented in the conclusion section.
{"title":"Impact of Credit Financing on the Ordering Policy for Imperfect Quality Items With Learning and Shortages","authors":"M. Jayaswal, Isha Sangal, M. Mittal","doi":"10.4018/ijban.304829","DOIUrl":"https://doi.org/10.4018/ijban.304829","url":null,"abstract":"The paper develops an order quantity model with trade credit plus shortages under learning effects for deteriorating imperfect quality products. Generally, when the lot has imperfect items, the inspection of a lot is necessary to improve the quality of the lot. In this article, the seller provides a defective lot to his buyer under credit financing scheme, and after that buyer separates the whole lot under the screening process into two categories, one is defective and the other is non-defective items. The buyer sells out defective items at a low price as compared to non-defective items. It is assumed that customers' demand of good quality items is greater than the inspection rate for the whole lot to neglect the shortages situation. After keeping all points together, the buyer optimized his total profit concerning order quantity and shortage. A suitable numerical example and a sensitivity analysis have been provided for the validity of this model. The aim and utility of this paper have been presented in the conclusion section.","PeriodicalId":42590,"journal":{"name":"International Journal of Business Analytics","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43611197","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
R. D. L. Torre, Laura Calvet, David López-López, A. Juan, Sara Hatami
Recruitment of young talented players is a critical activity for most professional teams in different sports such as football, soccer, basketball, baseball, cycling, etc. In the past, the selection of the most promising players was done just by relying on the experts’ opinion, but without a systematic data support. Nowadays, the existence of large amounts of data and powerful analytical tools have raised the interest in making informed decisions based on data analysis and data-driven methods. Hence, most professional clubs are integrating data scientists to support managers with data-intensive methods and techniques that can identify the best candidates and predict their future evolution. This paper reviews existing work on the use of data analytics, artificial intelligence, and machine learning methods in talent acquisition. A numerical case study, based on real-life data, is also included to illustrate some of the potential applications of business analytics in sport talent acquisition. In addition, research trends, challenges, and open lines are also identified and discussed.
{"title":"Business Analytics in Sport Talent Acquisition. Methods, Experiences, and Open Research Opportunities","authors":"R. D. L. Torre, Laura Calvet, David López-López, A. Juan, Sara Hatami","doi":"10.4018/ijban.290406","DOIUrl":"https://doi.org/10.4018/ijban.290406","url":null,"abstract":"Recruitment of young talented players is a critical activity for most professional teams in different sports such as football, soccer, basketball, baseball, cycling, etc. In the past, the selection of the most promising players was done just by relying on the experts’ opinion, but without a systematic data support. Nowadays, the existence of large amounts of data and powerful analytical tools have raised the interest in making informed decisions based on data analysis and data-driven methods. Hence, most professional clubs are integrating data scientists to support managers with data-intensive methods and techniques that can identify the best candidates and predict their future evolution. This paper reviews existing work on the use of data analytics, artificial intelligence, and machine learning methods in talent acquisition. A numerical case study, based on real-life data, is also included to illustrate some of the potential applications of business analytics in sport talent acquisition. In addition, research trends, challenges, and open lines are also identified and discussed.","PeriodicalId":42590,"journal":{"name":"International Journal of Business Analytics","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47404824","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
This research was motivated by the need to identify the most effective Data Envelopment Analysis (DEA) model and associated data analytics software for measuring, comparing, and optimizing building energy efficiency. By analyzing literature sources, the authors identified several gaps in the existing DEA approaches that were resolved in this research. In particular, the authors introduced energy efficiency indices like energy consumption per square foot and per occupant as a part of DEA models’ outputs. They also utilized inverse and min-max normalized output variables to resolve the issue of undesirable outputs in the DEA models. The evaluation of these models was done by utilizing various data analytics software including Python, R, Matlab, and Excel. The authors identified that the CCR DEA model with inverse output variables provided the most reliable energy efficiency scores, and the Python’s PyDEA package produces the most consistent efficiency scores while running the CCR model.
{"title":"Data Envelopment Analysis and Analytics Software for Optimizing Building Energy Efficiency","authors":"Z. Radovilsky, P. Taneja, P. Sahay","doi":"10.4018/ijban.290404","DOIUrl":"https://doi.org/10.4018/ijban.290404","url":null,"abstract":"This research was motivated by the need to identify the most effective Data Envelopment Analysis (DEA) model and associated data analytics software for measuring, comparing, and optimizing building energy efficiency. By analyzing literature sources, the authors identified several gaps in the existing DEA approaches that were resolved in this research. In particular, the authors introduced energy efficiency indices like energy consumption per square foot and per occupant as a part of DEA models’ outputs. They also utilized inverse and min-max normalized output variables to resolve the issue of undesirable outputs in the DEA models. The evaluation of these models was done by utilizing various data analytics software including Python, R, Matlab, and Excel. The authors identified that the CCR DEA model with inverse output variables provided the most reliable energy efficiency scores, and the Python’s PyDEA package produces the most consistent efficiency scores while running the CCR model.","PeriodicalId":42590,"journal":{"name":"International Journal of Business Analytics","volume":null,"pages":null},"PeriodicalIF":1.1,"publicationDate":"2022-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47482812","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：