IJCATR Volume 14 Issue 2

A Supervised Machine Learning Approach to Predicting Innovation Success in Major Software Corporations

Gabriel James, Enefiok Etuk, Anietie Ekong, Victor Ufford, Emmanuel Ododo, Iniobong Okon, Aniekan Effiong, Mfon Umoh
10.7753/IJCATR1402.1020
keywords : Standard Adoption, Sustainable Technology, Technological Advancement, Supervised Machine Learning, Linear Regression.

PDF
This research investigates intelligent-based methodologies for navigating the dual imperatives of innovation and standard adoption within system developments aimed at sustainable technological progress. Employing a mixed-methods approach that includes literature reviews, case studies, surveys, interviews, workshops, and focus groups, the study examines the interplay between innovative practices and standard adoption across various industries. In the rapidly evolving technological landscape, balancing the drive for innovation with adherence to established standards presents both synergies and trade-offs. Key findings highlight the importance of leveraging intelligent systems, adaptive regulatory frameworks, multi-stakeholder engagement, and early integration of standards in the innovation process. Achieving long-term sustainable outcomes also relies on agile innovation management techniques and comprehensive sustainability evaluation tools. The study culminates in a strategic technology roadmap offering firms practical guidance on effectively balancing innovation with regulatory requirements. With the use of a supervised machine learning (SML) approach, it was noticed that the R² of 0.92, suggested that 92% of the variance in innovation project success rate is explained by the model. Positive Coefficients in features like R&D Investment, Patents Filed, Balancing Innovation and Standards, and Market Competition positively impact the success rate. The Negative Coefficients in features like Compliance with Major Standards, Frequency of Audits, and Rapid Technological Changes negatively impact the success rate. This research provides valuable insights for achieving sustainable technological advancements and contributes to the body of knowledge on navigating the challenges of innovation and standard adoption.
@artical{g1422025ijcatr14021020,
Title = "A Supervised Machine Learning Approach to Predicting Innovation Success in Major Software Corporations ",
Journal ="International Journal of Computer Applications Technology and Research(IJCATR)",
Volume = "14",
Issue ="2",
Pages ="280 - 292",
Year = "2025",
Authors ="Gabriel James, Enefiok Etuk, Anietie Ekong, Victor Ufford, Emmanuel Ododo, Iniobong Okon, Aniekan Effiong, Mfon Umoh "}
  • Developed a linear regression-based model to analyze the balance between innovation and compliance in major software organizations.
  • Identified key success factors such as R&D investment, patents filed, and regulatory compliance influencing innovation project outcomes.
  • Achieved a high predictive accuracy (R² = 0.92) in modeling the impact of various organizational strategies on innovation success.
  • Proposed strategic recommendations for businesses and policymakers to optimize innovation while maintaining regulatory compliance.