Knowledge Extraction
Mohammad Hossein Rahmati; Farshid Namamian; Seyed Reza Hasani; Afshin Baghfalaki
Abstract
Brand resilience knowledge helps companies maintain customer trust and strengthen relationships through proper planning and strategies. This research was conducted to model brand resilience in Iran's handwoven carpet industry using background knowledge and data mining in critical conditions. In brand ...
Read More
Brand resilience knowledge helps companies maintain customer trust and strengthen relationships through proper planning and strategies. This research was conducted to model brand resilience in Iran's handwoven carpet industry using background knowledge and data mining in critical conditions. In brand resilience, knowledge analysis is considered highly significant for identifying key factors and effective patterns. This mixed research has been done based on qualitative data techniques in NVIVO software and quantitative data mining method in MATLAB software. 12 people were selected purposefully from carpet industry experts. Interviews were analyzed, coded, according to Strauss and Corbin method, and compared with the data mining method of the trained model and the MLP method. Based on the proposed model, 6 categories, 15 core codes, and 41 primary codes were identified. The proposed model could predict 98% brand resilience in crisis conditions. This model can help brands to maintain their business interests and implement appropriate strategies for active development, internal resistance, creative support, and production under sanctions. Furthermore, this model can help brands strengthen their capabilities and brand value, and identity in critical situations.
Knowledge Extraction
Ali Zare Abarghouei; Mohammad Reza Dalvi; Zahra Dashtlaali
Abstract
The current research was conducted to apply knowledge extraction in the classification of jobs to identify the key role players using a mixed method (qualitative and sufficient data). The application of expert systems or decision support systems based on organizational data is increasing in the selection ...
Read More
The current research was conducted to apply knowledge extraction in the classification of jobs to identify the key role players using a mixed method (qualitative and sufficient data). The application of expert systems or decision support systems based on organizational data is increasing in the selection and hiring of personnel. The data was derived from in-depth and semi-structured interviews with 17 subject experts in bank human resources, who were selected based on purposeful sampling.Data analysis was done based on the Strauss and Corbin model in the form of open, axial, and selective coding in the Atlas TI8 software. The results showed that the classification of jobs for the key role players in public and private banks includes causal conditions (requirement of talent substitution, human resource management developments, and organizational challenges), intervening conditions (organizational limitations and fear and resistance), and contextual conditions (strengthens and drivers) strategies (developmental, supportive and creating) and short-term and long-term consequences are among the components of the job classification model for the key role players in public and private banks. Next, based on the database with the CART method, the data mining of job classification was done. Regarding the performance of the model, it showed variance values of 311.92 and a risk value of 288.19. The predictions in the model explained 28.9% of the differences observed in the variable "employment status of A employees' category".
Data mining
Aliakbar Vakili; Mahdi Bagheri; Sirajuddin Mohebi; Kobra Haji Alizadeh
Abstract
This research aims to identify the knowledge management infrastructure due to reducing employee absenteeism based on data mining. Examining the status and reports of employees using data recording systems, creating information dashboards, and applying data mining techniques is important for the transparency ...
Read More
This research aims to identify the knowledge management infrastructure due to reducing employee absenteeism based on data mining. Examining the status and reports of employees using data recording systems, creating information dashboards, and applying data mining techniques is important for the transparency of the mental state of employees. The mixed research method (qualitative-quantitative) has been done in two phases. The first phase was conducted with a qualitative-inductive approach using the Delphi method and a semi-structured interview tool. In the second step, codes were grouped in a common axis and 13 axis codes based on the similarity and distinction between the extracted codes. The interview sample was 10 people selected using the purposeful sampling method. In the second phase, the quantitative research method was data mining; Then, according to the research literature and experts' opinion, the researcher-made questionnaire was designed with a five-point Likert scale. The data mining technique is based on neural networks and decision trees in Rosseta and Weka software. The results showed that knowledge management can increase the quality of organizational processes based on data, increase the empowerment of employees, and reduce absenteeism. The knowledge obtained from the data mining of organizational information dashboards is important for strengthening the mental health systems of employees and increasing productivity.
Data mining
Tina Malekolkalami; Khadijah Khodabakhshi Parijani; Maliheh Alifari
Abstract
The purpose of this research is to use data mining to detect accounting fraud in the database of stock exchange member companies. The combination of discrete and continuous data has increased the necessity of using data mining and machine learning methods in the field of fraud detection. This research ...
Read More
The purpose of this research is to use data mining to detect accounting fraud in the database of stock exchange member companies. The combination of discrete and continuous data has increased the necessity of using data mining and machine learning methods in the field of fraud detection. This research is applied in terms of purpose and descriptive in terms of method. The document review method was used to collect information in the field of literature and research background. The prepared questionnaire includes 7 main indicators consisting of 48 questions for each of the variables. This questionnaire was made available by the researcher to 400 accountants of companies admitted to the Tehran Stock Exchange by sampling method. In order to fit the model, the structural equation method was used in SMARTPLS software. In the data mining section, all IB1, IBK, LWL, KSTAR, and KNN algorithms were used to simulate the proposed model in Rapidminer software. Effectiveness of internal control, compensation system, asymmetry of information, compliance with accounting rules, management ethics, and ethical principles are effective and meaningful on accounting fraud. In evaluating parameters and according to the graphs, the K-STAR algorithm has better performance than other algorithms. The proposed data mining model for financial fraud detection showed that since the amount of data creation in financial companies is increasing day by day with the development of technology, it is possible to provide early detection of fraud by reviewing and analyzing the data.
Data mining
Seyed Rohollah Abbasi; Abdul Khalegh Gholami Chenaristan Alia; Foad Makvandi
Abstract
This study aimed to design a data-driven decision-making model for managers in the direction of empowering human resources in the police headquarter of Kohgiluyeh and Boyer-Ahmad province. Increasing amount of information and rapid changes in the environment and the need to create continuous communication ...
Read More
This study aimed to design a data-driven decision-making model for managers in the direction of empowering human resources in the police headquarter of Kohgiluyeh and Boyer-Ahmad province. Increasing amount of information and rapid changes in the environment and the need to create continuous communication with the complex and dynamic environment requires management, acquisition and distribution of knowledge as well as, proper organizing and analysis of information. The present research uses a qualitative approach. The statistical population included experts in the police force, 19 people were selected through purposive sampling and interviewed. The identified indicators of the data-driven decision-making model of managers in empowering employees were extracted in the form of 3 main categories, 17 sub-categories, and 69 concepts. The identified model was also tested based on the AdaBoost regression algorithm in Rapidminer software which led to development of the intelligence of the managers' decision-making model compared to the traditional model. The findings showed structural factors (including strategic orientations, organizational structure dynamics, performance management system, training and improvement, knowledge management system, job design system, and information technology system) behavioral factors (including management orientations, leadership style, development of psychological characteristics of employees), development of decision-making skills and competences of employees, human relations system, job attitudes, and organizational culture) and environmental factors (including legal factors, political factors, and economic factors). Based on the proposed model, the accuracy of data-driven decision-making of managers was tested and the results indicated the significance of intelligence and information in the organization.