THE ROLE OF GENERATIVE AI IN THE OPTIMIZATION OF HYPERPARAMETERS FOR STRATEGY MAKING: AN ANALYSIS OF ITS IMPACT ON DECISION-MAKING PROCESSES.
Abstract
The optimal hyperparameters issue is a critical issue in the field of machine learning (ML) and artificial intelligence (AI) techniques developing, with the traditional strategies are mostly a waste of time and not efficient. In this context, the emergence of generative AI presents a promising opportunity to automate and enhance the hyperparameter optimization process. This research paper delves into the role of generative AI in optimizing hyperparameters for strategy-making, focusing on its potential impact on decision-making processes.The applicability of generative AI techniques in the area of strategy search space definition is explored in this study. Moreover, it delves into whether the generative AI adds an additional advantage for strategies over those traditional methods. Finally, this study also examines the capability of generative AI to improve the interpretability of strategy models.Through a combination of theoretical analysis and empirical assessment across numerous datasets and complexities, these studies will benchmark generative AI techniques in opposition to established optimization techniques using key metrics which include method performance, computational performance, and robustness. Ultimately, this paper seeks to make contributions to the continued discourse on the transformative capacity of generative AI in optimizing hyperparameters for strategic decisions-making.
Keyword : Hyperparameter optimization, Machine learning (ML), Artificial intelligence (AI), Generative AI, Strategy-making, Decision-making processes,Strategy search space definition, Traditional optimization methods.
This work is licensed under a Creative Commons Attribution 4.0 International License.
References
1. Fine-tuning Hyperparameters in Generative AI. (n.d.) retrieved April 12, 2024, from docs.oracle.com 2. Fine-tuning Models: Hyperparameter Optimization. (n.d.) retrieved April 12, 2024, from encord.com 3. Overview of hyperparameter tuning | Vertex AI. (n.d.) retrieved April 12, 2024, from cloud.google.com 4. Understanding the Effect of Hyperparameter Optimization .... (n.d.) retrieved April 12, 2024, from www.sciencedirect.com 5. Hyperparameter Optimization in Machine Learning. (n.d.) retrieved April 12, 2024, from www.linkedin.com 6. Maximizing AI Performance: A Guide to Optimization. (n.d.) retrieved April 12, 2024, from medium.com 7. What are some tools for optimizing AI algorithms?. (n.d.) retrieved April 12, 2024, from www.linkedin.com 8. Hyperparameter Tuning. (n.d.) retrieved April 12, 2024, from www.larksuite.com 9. Generative AI for SEO: Unveiling the Future of Search Optimization. (n.d.) retrieved April 12, 2024, from www.upgrow.io/blog/generative-ai-for-seo 10. The rise of Generative AI: Insights from search trends. (n.d.) retrieved April 12, 2024, from about.ads.microsoft.com 11. Will Search Be Generative AI or Blue Links? Actually It's Both. (n.d.) retrieved April 12, 2024, from www.cmswire.com 12. On the Challenges and Opportunities in Generative AI. (n.d.) retrieved April 12, 2024, from arxiv.org/html/2403.00025v1 13. How to Harness the Potential of Generative AI in Your Business Strategy Frameworks. (n.d.) retrieved April 12, 2024, from www.untaylored.com 14. What every CEO should know about generative AI. (n.d.) retrieved April 12, 2024, from www.mckinsey.com 15. R. Ramesh, M. Kannan and M. Seenivasan, “Achievement Estimations of Priority Queue System in Fuzzy Environment”, Advances in Mathematical Modelling and Scientific Computing, Trends in Mathematics, Springer Link (Book Chapter),2024, pp. 637-658. 16. R. Ramesh and M. Seenivasan, “Analysis of Attainment Estimates of Loss System Queue”, Advances in Mathematical Modelling and Scientific Computing, Trends in Mathematics, Springer Link (Book Chapter),2024, pp. 519 – 531. 17. K. Sakthivel, N. Paramaguru, R. Ramesh and P. Syamala., “ Accomplishment Expedients of Batch Arrival Queuing Model by Fuzzy Ordering Approach ”, Advances in Mathematical Modelling and Scientific Computing, Trends in Mathematics, Springer Link (Book Chapter),2024, pp. 487 – 496. 18. A. Hari Ganesh, N. Jaimurthi, R. Ramesh and M. Seenivasan, “On testing of Fuzzy Hypothesis for mean and variance using centroid-based new distance functions under symmetric fuzzy environment”, Contemporary Mathematics, Vol. 5. Issue 1, December 26, 2023, pp. 60-92, https://doi.org/10.37256/cm.5120243317. 19. M. Seenivasan, S. Chandiraleka, H. Manikandan and R. Ramesh, “Single Server Queueing Model with Multiple Working Vacation, Feedback and Catastrophe”, 4th International Conference on Material Science and Applications, AIP Conference Proceedings 2822, November 14, 2023,pp.020245-1 – 020245-9,ISBN NO: 978-0-7354-4724-0. 20. M. Seenivasan, F. Patricia and R. Ramesh, “Analysis of Single Server Queue with single working vacation subject to Catastrophe”, 4th International Conference on Material Science and Applications, AIP Conference Proceedings 2822, November 14, 2023,Pp.020246-1to 020246-6,ISBN NO: 978-0-7354-4724-0. 21. R. Ramesh and M. Seenivasan, “Cost Appraises of a Phosphorescent Bulk Arrival Queueing system by Wingspans Fuzzy Ranking Approach”, Stochastic Processes and Their Applications in Artificial UIntelligence chapter 5, Pp. 50-64 ACIR Book Series: ISSN NO: 2327-0411 (Scopus). 22. P. Syamala, R. Ramesh, M. Seenivasan and R. Singaravel, “3D Based CT Scan Retrial Queuing Models by Fuzzy 23. Ordering Approach”, 2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT), Trichirappalli, India, 2023, Pp. 01-05,(Scopus). 24. P. Gnaanachandra, A.M. Kumar, M. Seenivasan and R. Ramesh, “On Generalization of Fuzzy Topological Groups and Modelling Robotic Crash*”,IEEE Xplore, 2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT), Trichirappalli, India 2023, Pp.1-8, DOI: 10.1109/ICEEICT56924.2023.10157226 (Scopus). 25. R. Ramesh and M. Seenivasan, “Discouraged Arrivals Queuing System in Inter valued type-2 Fuzzy Environment, Recent trends on Type-2 Fuzzy Logic systems: Theory, methodology and Application”, Studies in Fuzziness and Soft Computating, Pp. 235-247, 2023, Volume 425, (Springer): ISSN: 1434 – 9922. 26. R. Ramesh and M. Seenivasan, Performance Analysis of Single Server Low Priority Queue Based on Electronic Transmitter, Lecture Notes in Electrical Engineering, Springer Book Series, (ICAECT 2021), Vol.881,Pp.347-359,June 26th, 2022, ISBN: 978-981-19-1110-1&ISBN 978-981-19-1111-8. 27. R. Ramesh and M. Seenivasan, “Achievement expedients of fuzzy queuing models with an unreliable electrical transformer”, IEEE Xplore (ICEEICT 2022) Vol. 22, February 2022(Scopus), ISBN:978-1-6654-3647-2. 28. Bhaskaran, S. S. (2024). Discovery of contextual factors using clustering. Multimedia Tools and Applications, 1-30. 29. Bhaskaran, S. S. (2021). Investigation of student performance with contextual factors using association rules in higher educational institutions (HEIs). In Data Engineering and Intelligent Computing: Proceedings of ICICC 2020 (pp. 431-442). Springer Singapore. 30. Bhaskaran, S. S., Al Aali, M., & Lu, K. Contextual Data Mining for Higher Educational Institutions. 31. Bhaskaran, S. S. (2017). An Investigation into the Knowledge Discovery and Data Mining (KDDM) process to generate course taking pattern characterised by contextual factors of students in Higher Education Institution (HEI) (Doctoral dissertation, Brunel University London). 32. Bhaskaran, S. S. (2021). Investigation of factors affecting adoption of FinTech in financial institutions. In Innovative strategies for implementing FinTech in banking (pp. 222-241). IGI Global. 33. Sailesh, S. B. (2022). Adapting IT governance policies and technology to cope with COVID-19 at Ahlia University. In COVID-19 Challenges to University Information Technology Governance (pp. 359-372). Cham: Springer International Publishing. 34. Intelligent context driven data mining to analyse student performance in higher educational institutions (HEIs) Bhaskaran, S.S 35. International Journal of Recent Technology and Engineering, 2019, 8(2), pp. 856–861 36. Khalaf, F., & Baskaran, S. S. (2023, March). Predicting Acute Respiratory Failure Using Fuzzy Classifier. In 2023 International Conference on IT Innovation and Knowledge Discovery (ITIKD) (pp. 1-4). IEEE. 37. Hasan, Z., & Baskaran, S. S. (2023, March). Propose a Recommender System to Dynamically Align Higher Education Curriculums With 4IR Market Needs. In 2023 International Conference on IT Innovation and Knowledge Discovery (ITIKD) (pp. 1-7). IEEE. 38. Bhaskaran, S. S., & Al Aali, M. (2021). Investigation on the Influence of English Expertise on Non-native English-Speaking Students’ Scholastic Performance Using Data Mining. In Smart Computing Techniques and Applications: Proceedings of the Fourth International Conference on Smart Computing and Informatics, Volume 2 (pp. 9-14). Springer Singapore. 39. Bhaskaran, S. S., & Aali, M. A. (2021). Data mining model for better admissions in higher educational institutions (heis)—a case study of bahrain. In Advanced Machine Learning Technologies and Applications: Proceedings of AMLTA 2020 (pp. 141-150). Springer Singapore. 40. Sailesh, S. B., Lu, K. J., & Al Aali, M. (2016, August). Profiling students on their course-taking patterns in higher educational institutions (HEIs). In 2016 international conference on information science (icis) (pp. 160-167). IEEE. 41. Sailesh, S. B., Lu, K. J., & Al Aali, M. (2016, August). Context driven data mining to classify students of higher educational institutions. In 2016 International Conference on Inventive Computation Technologies (ICICT) (Vol. 2, pp. 1-7). IEEE. 42. Bhaskaran, S. S., Lu, K., & Aali, M. A. (2017). Student performance and time-to-degree analysis by the study of course-taking patterns using J48 decision tree algorithm. International Journal of Modelling in Operations Management, 6(3), 194-213. 43. Bhaskaran, S. S. (2018). Facilitate decision making in higher educational institutions by linking course-taking pattern and student performance characterised by contextual knowledge. International Journal of Society Systems Science, 10(3), 182-200.