Evaluating the Impact of Different Feature Scaling Techniques on Breast Cancer Prediction Accuracy
Journal Title: Advance Knowledge for Executives - Year 2024, Vol 3, Issue 1
Abstract
Objective: To investigate the influence of different feature scaling techniques on the performance of machine learning algorithms in breast cancer prediction and identify the optimal combination of algorithm and scaler that yields the highest predictive accuracy. Method: Machine Learning Models (SVM, AdaBoost and RF), Feature Scaling Techniques (StandardScaler, MinMaxScaler, RobustScaler and Normalizer) Result: Effect of Feature Scaling. For SVM, feature scaling improved the performance. The best accuracy (98.25%) was obtained with MinMaxScaler. AdaBoost's performance remained consistent (~97.66%) across all scaling techniques. RF showed minor variations in performance across different scalers, but the differences were marginal. Conclusion: By experimenting with different combinations, practitioners can optimise model performance, ensuring more reliable and accurate predictions. Recommendation & Implication: Considering more than 30 features using a larger dataset in further study. Fine-tuning might lead to different results, testing the model with real-world data and exploring other preprocessing methods.
Authors and Affiliations
Chitcharoen, E. , Suwanwijit, N. , Mongkonchoo, K. , Utakrit, N. , Nuchitprasitchai, S. , & Bhumpenpein, N.
Keywords
Related Articles
- EP ID EP731718
- DOI -
- Views 44
- Downloads 0
A Review of Digital Marketing and Service Marketing during the COVID-19 and the Digital Economy
Objective: As the COVID-19 pandemic expands its influence across the globe, businesses are continuously adopting techniques for developing the business model that incorporates organisational change due to digital economy...
Goodness Bank, Volunteer Bank, and Time Bank in the Digital Age
Objective: This study aimed to evaluate the literature on good-deed, goodness bank, volunteer bank, and time bank in the digital age. Method: A narrative synthesis was employed. The data was analyzed using the documen...
Tourist Behavior in Cultural Tourism: A Case Study of Tourism Routes in Phetchaburi, Thailand
Objective: The primary purposes of the present study were to 1) examine the behaviour of Thai tourists who visited the cultural destinations in the Khlong Krachaeng Sub-district in the Mueang District of Phetchaburi, Tha...
Evaluating the Impact of Different Feature Scaling Techniques on Breast Cancer Prediction Accuracy
Objective: To investigate the influence of different feature scaling techniques on the performance of machine learning algorithms in breast cancer prediction and identify the optimal combination of algorithm and scaler t...
The Correlation between Academic and Work Performance among Master’s in International Hospitality Management Graduates in one Higher Education Institution in the Philippines
Objective: A post-graduate degree is an advantage to obtaining a higher position, although not a requirement. In line with this, this paper is of great importance as this study assesses the correlation between academic p...