Javascript is required
Search
Volume 3, Issue 4, 2025

Abstract

Full Text|PDF|XML
Transaction data increasingly serves as a strategic knowledge source in data-driven decision support systems. However, many organizations still use transaction records primarily for operational purposes and do not systematically transform them into actionable knowledge that supports managerial decision-making. This study aims to investigate a knowledge discovery framework based on the Cross-Industry Standard Process for Data Mining (CRISP-DM) and the Frequent Pattern Growth (FP-Growth) algorithm for extracting transactional knowledge and supporting intelligent decision-making. A dataset containing 978 sales transactions and 157 active products was analyzed through six CRISP-DM stages, including business understanding, data understanding, data preparation, modeling, evaluation, and deployment. The FP-Growth algorithm was implemented to identify frequent itemsets and generate association rules. Twenty-one experimental scenarios involving different support and lift thresholds were conducted to determine an appropriate parameter configuration. The results showed that a minimum support value of 0.06 combined with a lift value of 2 produced a balanced set of association rules with strong business relevance. Stable purchasing patterns and contextual association patterns were identified. The extracted rules were integrated into a management information system to support product bundling and cross-selling functions. The results indicate that FP-Growth-based frequent pattern mining can transform transaction records into operational transactional knowledge with practical business value. This study demonstrates that integrating a complete CRISP-DM process with knowledge extraction and system deployment provides an effective pathway for developing data-driven marketing intelligence and decision-support mechanisms. The proposed framework provides a practical foundation for intelligent marketing systems and offers insights into knowledge discovery applications in transactional environments.

Abstract

Full Text|PDF|XML

Stakeholder engagement plays an important role in sustainable tourism development by supporting inclusive governance, information sharing, and collaborative learning among tourism actors. However, limited empirical evidence exists regarding how stakeholder interaction, knowledge exchange, and participation mechanisms influence sustainable tourism outcomes within local governance systems in developing countries. This study investigates stakeholder engagement as a driver of sustainable tourism development in Ghana, with particular attention to the roles of digital participation and local governance structures within Metropolitan, Municipal, and District Assemblies (MMDAs). A quantitative descriptive research design was adopted, and structured questionnaires were administered to 365 respondents across six tourism-hosting communities within the Ahanta West Municipal Assembly using stratified and convenience sampling approaches. The collected data were analysed using descriptive statistics and one-way analysis of variance (ANOVA). The results showed that respondents regarded stakeholder engagement, digital participation mechanisms, and collaboration with cultural institutions as important elements of sustainable tourism development. The findings also showed significant differences across age groups and length of residence, indicating uneven experiences of participation and information access among stakeholders. Digital engagement tools received the highest level of support, suggesting growing interest in technology-supported participation mechanisms within tourism governance. The findings indicate that stakeholder engagement contributes to sustainable tourism development when participation structures support meaningful interaction, knowledge exchange, and equitable involvement among community actors. This study provides empirical evidence from local governance settings in Ghana and contributes to tourism governance literature by linking stakeholder engagement with knowledge-sharing practices and digital participation mechanisms, while offering practical guidance for the development of more inclusive and context-sensitive tourism governance systems.

Abstract

Full Text|PDF|XML

University-Industry knowledge transfer plays a central role in converting academic research into technological and organizational innovation, but its success remains uneven in developing economies. This study investigates the factors associated with successful university-to-industry knowledge transfer in Iran and develops an empirical model for assessing such initiatives. Six explanatory constructsKnowledge Destination, Knowledge Source, Knowledge Characteristics, University-Industry Distance, Transfer Mechanisms, and Government Dimensionwere identified through a literature review and expert interviews. Survey data were then collected from 88 experts with experience in both academic and industrial settings and analyzed using partial least squares structural equation modeling (PLS-SEM). The results showed that Knowledge Characteristics, University-Industry Distance, Transfer Mechanisms, and Knowledge Destination had statistically significant positive relationships with Knowledge Transfer Success. In contrast, Knowledge Source and Government Dimension did not show statistically significant relationships with the outcome construct. The model explained 67% of the variance in Knowledge Transfer Success and demonstrated predictive relevance ($Q^2$ = 0.36). These findings indicate that successful knowledge transfer depends primarily on the nature and applicability of the knowledge, the distance between the participating organizations, the mechanisms used for transfer, and the receiving industry’s capacity and readiness. The proposed framework provides an empirically tested basis for diagnosing weaknesses in University-Industry knowledge transfer projects and supports more focused decisions by university administrators, industry managers, and innovation policymakers.

- no more data -