THE RELATIONSHIP BETWEEN COMMON FEATURE SELECTION METRICS AND ACCURACY
- Project Research
- 1-5 Chapters
- Abstract : Available
- Table of Content: Available
- Reference Style: APA
- Recommended for : Student Researchers
- NGN 5000
Abstract
Filter-based feature selection methods such as information gain, Gini index, and gain ratio are commonly used in machine learning. It is often assumed that these methods select the most accurate features, but we show this is not true. In this thesis, we study cases when these feature selection metrics and accuracy show “misorderings”: given a pair of features F1 and F2, where F1 has a higher accuracy than F2, the feature selection value is higher for F2 than F1. We first study the frequency of misorderings in randomly-produced synthetic data. Secondly, we study the potential for misordering as two key parameters of the features in a dataset are varied. Finally, we study misorderings in real data and show that misorderings are also prevalent there. Based on our results, we observe that different metrics exhibit different misordering rates, and imposing redundancy-elimination criteria may have the side effect of reducing misordering.
Related Project Materials
An investigation of the impact of mining activities on water quality in Shiroro Local Government Area, Niger State
Chapter One: Introduction
1.1 Background of the Study
Mining activities are a significant contributor to environmental degradat...
Challenges in Accounting Information System Deployment in Rural Banks in Kontagora Local Government Area
Background of the Study
Rural banks in Kontagora Local Government Area play a critical role in providin...
An appraisal of branch network expansion on increasing market penetration in banking: a case study of Union Bank of Nigeria
Background of the Study
Branch network expansion has long been a strategic approach for banks aiming to increase market penetration and e...
The effect of informal education on students' ability to use problem-solving strategies in Bade Local Government Area, Yobe State
Background of the Study
Informal education encompasses a wide range of learning experiences that occur outside traditional...
THE EFFECT OF ARTIFICIAL INTELLIGENCE IN SENTIMENT ANALYSIS FOR BRAND MONITORING: A CASE STUDY OF NIGERIAN BREWERIES, KADUNA STATE
Background of the Study
Sentiment analysis, also known as opinion mining, is a key tool in brand monitoring. By analyzin...
An appraisal of the challenges of rural development in Bauchi North Local Government Area, Bauchi State
Chapter One: Introduction
1.1 Background of the Study
Rural development remains one of the mo...
The effect of informal education on students’ ability to engage in meaningful debates in Ogori/Magongo Local Government Area, Kogi State
Background of the Study
Effective communication and critical debate skills are essential components of a well-rounded educ...
An investigation of interest rate benchmarking on lending competitiveness in banking: a case study of Access Bank Nigeria
Background of the Study
Interest rate benchmarking involves comparing a bank’s lending rates against industry standar...
An Evaluation of Fiscal Responsibility Laws on Financial Accountability in Nigeria: A Case Study of Ondo State Government
Background of the Study
Fiscal responsibility laws (FRLs) are essential tools for promoting financial a...
THE EFFECTS OF POOR INFRASTRUCTURAL FACILITIES ON SOCIO-ECONOMIC DEVELOPMENT
ABSTRACT
Today, poor infrastructural facilities are identified as a problem. It is important to know that most of the po...
