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

A Review of Artificial Intelligence (AI) in Education during the Digital Era

Objective: Artificial intelligence (AI) plays a critical role in education. This paper aims to review the artificial intelligence adoption in learning and teaching during the digital era. Method: A narrative synthesis...

NVivo for Social Sciences and Management Studies: A Systematic Review

Objective: This systematic review aims to explore the utilisation and impact of NVivo, a qualitative data analysis software, in the fields of Social Sciences and Management Studies. Method: A narrative synthesis was e...

Influencing Factors Behind Dating App Usage: A Case Study in Bangkok, Thailand

Objective: The objective of this study is to examine the primary factors influencing an individual's inclination to use dating apps in Bangkok, Thailand, particularly focusing on perceived ease of use, perceived usefulne...

A Strategic Cooperative Model: The Case of Islamic Financing Hub

Objective: This case study aimed to propose a strategic cooperative model and discuss the challenges encountered by Belt Road Initiatives (BRI) and the need to address those gaps to unleash the potential and impacts of B...

The Role of Student Satisfaction between TAM and Intentions to Use English Online Dictionary : A Conceptual Review

Objective: This study reviewed the mediating role of student satisfaction between perceived usefulness and perceived ease of use (the TAM model) and intentions to use an English online dictionary. Method: The research...

Download PDF file
  • EP ID EP731718
  • DOI -
  • Views 62
  • Downloads 0

How To Cite

Chitcharoen, E. , Suwanwijit, N. , Mongkonchoo, K. , Utakrit, N. , Nuchitprasitchai, S. , & Bhumpenpein, N. (2024). Evaluating the Impact of Different Feature Scaling Techniques on Breast Cancer Prediction Accuracy. Advance Knowledge for Executives, 3(1), -. https://europub.co.uk/articles/-A-731718