.png)
Nature-based Hyperparameter Tuning of a Multilayer Perceptron Algorithm in Task Classification: A Case Study on Fear of Failure in Entrepreneurship
Abstract
Entrepreneurship plays a key role in generating economic growth, encouraging innovation, and creating job opportunities. Understanding which demographic, psychological, and socio-economic factors contribute to fear of failure in entrepreneurship is essential to developing proper standards in entrepreneurship education and policy. However, it remains challenging to accurately classify these factors, especially when balancing model performance with model complexity in a multilayer perceptron algorithm. An effective model requires the correct parameter setting via a hyperparameter tuning process. Adjusting each hyperparameter by hand requires significant effort and knowledge, as there are frequently multiple combinations to consider. Furthermore, manual tuning is prone to human error and may overlook optimal configurations, resulting in inferior model performance and prediction accuracy. This study evaluates nature-inspired optimization techniques, including particle swarm optimization (PSO), genetic algorithm (GA), and grey wolf optimization (GWO). Several parameters are tuned in the present multilayer perceptron model, including the number of hidden layers and the number of nodes in each hidden layer, learning rate, and activation functions. The used dataset which consists of 39 features from 333 samples captured individual fears, loss score, and computational efficiency as the required amount of time for finding the best parameter combination. Model accuracy performance scores are 45.16%, 53.76%, and 58.61% for GA, PSO, and GWO, respectively. Meanwhile their execution time are 10 minutes, 27 minutes, and 23 minutes, for GA, PSO, and GWO, respectively. Experiment results further reveal that each optimization algorithm has distinct advantages: GA excels at speedy convergence, PSO provides a robust exploration of hyperparameter space, and GWO offers remarkable adaptability to complicated parameter interdependencies. This study provides empirical evidence for the efficacy of nature-inspired hyperparameter modification in improving multilayer perceptron performance for fear of failure categorization tasks.
Keywords
Full Text:
PDFReferences
S. K. Halim, D. Hidayat, Y. Eni, and E. Fernando, “What is Entrepreneurial Fear of Failure?,” Binus Business Review, vol. 14, no. 1, pp. 73–84, 2023.
E. Hunter, A. Jenkins, and C. Mark-Herbert, “When fear of failure leads to intentions to act entrepreneurially: Insights from threat appraisals and coping efficacy,” International Small Business Journal, vol. 39, no. 5, pp. 407–423, 2021.
Y. Gao, X. Wang, J. Lu, B. Chen, and K. Morrin, “Entrepreneurial fear of failure among college students: A scoping review of literature from 2010 to 2023,” Heliyon, 2024.
M. Zhang et al., “MLP-like model with convolution complex transformation for auxiliary diagnosis through medical images,” IEEE J Biomed Health Inform, 2023.
M. K. Ogirala, R. Tallapaneni, S. M. Chalamcharla, and A. Chinta, “A Medical Diagnosis and Treatment Recommendation Chatbot using MLP,” in 2023 2nd International Conference on Applied Artificial Intelligence and Computing (ICAAIC), 2023, pp. 495–500.
Z. Ersozlu, S. Taheri, and I. Koch, “A review of machine learning methods used for educational data,” Educ Inf Technol (Dordr), pp. 1–21, 2024.
J. Shi, T. Wu, Y. Lei, and B. Li, “Course Correlation Analysis using MLP,” in 2023 International Conference on Cyber-Physical Social Intelligence (ICCSI), 2023, pp. 279–284.
A. Tashakkori, M. Talebzadeh, F. Salboukh, and L. Deshmukh, “Forecasting Gold Prices with MLP Neural Networks: A Machine Learning Approach,” International Journal of Science and Engineering Applications (IJSEA), vol. 13, pp. 13–20, 2024.
A. P. Wibawa et al., “Mean-Median Smoothing Backpropagation Neural Network to Forecast Unique Visitors Time Series of Electronic Journal,” Journal of Applied Data Sciences, vol. 4, no. 3, pp. 163–174, 2023.
F. Marini and B. Walczak, “Particle swarm optimization (PSO). A tutorial,” Chemometrics and Intelligent Laboratory Systems, vol. 149, pp. 153–165, 2015.
S. Mirjalili and S. Mirjalili, “Genetic algorithm,” Evolutionary algorithms and neural networks: theory and applications, pp. 43–55, 2019.
S. Mirjalili, S. M. Mirjalili, and A. Lewis, “Grey wolf optimizer,” Advances in engineering software, vol. 69, pp. 46–61, 2014.
I. Muis, A. N. Hamid, and others, “Fear of failure and Entrepreneurial intentions in University Students.,” Journal of Educational, Health & Community Psychology (JEHCP), vol. 13, no. 2, 2024.
E. C. Santos, A. R. Galvão, C. S. Marques, and T. Mendes, “Enlightening the shadow dimensions of part-time entrepreneurship: Navigating fear of failure and enhancing social status,” Strategic Change.
M. Shahid Satar, G. Alarifi, A. A. Alkhoraif, and M. Asad, “Influence of perceptual and demographic factors on the likelihood of becoming social entrepreneurs in Saudi Arabia, Bahrain, and United Arab Emirates–an empirical analysis,” Cogent Business & Management, vol. 10, no. 3, p. 2253577, 2023.
C. Camelo-Ordaz, J. P. Diánez-González, and J. Ruiz-Navarro, “The influence of gender on entrepreneurial intention: The mediating role of perceptual factors: La influencia del género sobre la intención emprendedora: El papel mediador de los factores de percepción,” BRQ business research quarterly, vol. 19, no. 4, pp. 261–277, 2016.
S. S. Sagar and J. Stoeber, “Perfectionism, fear of failure, and affective responses to success and failure: The central role of fear of experiencing shame and embarrassment,” J Sport Exerc Psychol, vol. 31, no. 5, pp. 602–627, 2009.
C. K. Lee, G. W. Cottle, S. A. Simmons, and J. Wiklund, “Fear not, want not: Untangling the effects of social cost of failure on high-growth entrepreneurship,” Small Business Economics, vol. 57, no. 1, pp. 531–553, 2021.
S. Ansari, K. A. Alnajjar, S. Abdallah, M. Saad, and A. A. El-Moursy, “Parameter tuning of MLP, RBF, and ANFIS models using genetic algorithm in modeling and classification applications,” in 2021 International Conference on Information Technology (ICIT), 2021, pp. 660–666.
F. Itano, M. A. de A. de Sousa, and E. Del-Moral-Hernandez, “Extending MLP ANN hyper-parameters Optimization by using Genetic Algorithm,” in 2018 International joint conference on neural networks (IJCNN), 2018, pp. 1–8.
V. Rajalakshmi and S. G. Vaidyanathan, “MLP-PSO Framework with Dynamic Network Tuning for Traffic Flow Forecasting.,” Intelligent Automation & Soft Computing, vol. 33, no. 3, 2022.
D. Sarkar, T. Khan, F. A. Talukdar, and S. R. Rengarajan, “Hyperparameters tuning of prior knowledge-driven multilayer perceptron model using particle swarm optimization for inverse modeling,” in 2022 IEEE International Symposium on Antennas and Propagation and USNC-URSI Radio Science Meeting (AP-S/URSI), 2022, pp. 441–442.
C. Tang et al., “Multi-strategy Grey Wolf Optimizer for Engineering Problems and Sewage Treatment Prediction,” Advanced Intelligent Systems, vol. 6, no. 7, p. 2300406, 2024.
C. Tian, S. Ni, Z. Wang, and Y. Zhang, “Application of Grey Wolf Optimization Algorithm in Tuning Controller Parameters of Hypersonic Vehicle,” in 2022 41st Chinese Control Conference (CCC), 2022, pp. 323–328.
S.-H. Liao, P.-H. Chu, and P.-Y. Hsiao, “Data mining techniques and applications–A decade review from 2000 to 2011,” Expert Syst Appl, vol. 39, no. 12, pp. 11303–11311, 2012.
I. Anwar, P. Thoudam, M. Samroodh, M. Thoudam, and I. Saleem, “The dataset on fear of failure, entrepreneurship education, psychological and contextual predictors of entrepreneurial intention,” Front Psychol, vol. 13, p. 954285, 2022.
S. Sharma, S. Sharma, and A. Athaiya, “Activation functions in neural networks,” Towards Data Sci, vol. 6, no. 12, pp. 310–316, 2017.
DOI: https://doi.org/10.47738/jads.v6i2.539
Refbacks
- There are currently no refbacks.
Journal of Applied Data Sciences
| ISSN | : | 2723-6471 (Online) |
| Publisher | : | Bright Publisher |
| Website | : | http://bright-journal.org/JADS |
| : | taqwa@amikompurwokerto.ac.id (principal contact) | |
| support@bright-journal.org (technical issues) |
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0