Chapter One — 1.1 Background to the Study

Organizations that depend on ride-hailing applications are under increasing pressure to modernize, and Machine Learning has emerged as one of the more promising avenues for doing so, given its demonstrated impact in related domains.

In practice, however, adoption of machine learning within ride-hailing applications has been uneven, and its actual impact on fraud detection accuracy is not yet well understood in a rigorous, evaluable way — a gap this study is positioned to address.

1.2 Statement of the Problem

Current ride-hailing applications in many organizations struggle with inadequate fraud detection accuracy, often relying on manual processes or outdated architectures that were not designed for today's operating environment. Without a structured approach to integrating machine learning, these limitations are likely to persist, exposing organizations to inefficiency, risk, and a poor user experience. This study is motivated by the need to design and evaluate a machine learning-based approach to addressing this problem.

1.3 Objectives of the Study

1. To design and implement a machine learning-based approach to improving fraud detection accuracy in ride-hailing applications.
2. To evaluate the effectiveness of Machine Learning in enhancing fraud detection accuracy within ride-hailing applications.
3. To identify the key requirements and constraints relevant to deploying machine learning in this context.
4. To assess user and stakeholder perception of the resulting system.

1.4 Research Questions

1. How can machine learning be applied to improve fraud detection accuracy in ride-hailing applications?
2. How effective is Machine Learning at enhancing fraud detection accuracy within ride-hailing applications?
3. What requirements and constraints are relevant to deploying machine learning in this context?
4. How do users and stakeholders perceive the resulting system?

1.5 Significance of the Study

Beyond its immediate technical contribution, this study offers value to organizations evaluating whether to invest in machine learning for their own ride-hailing applications, and contributes to the broader literature on applied software technology / IT by documenting a concrete implementation and evaluation case.

1.6 Scope of the Study

As a BSc-level study, its scope is confined to designing and evaluating a machine learning-based solution for ride-hailing applications, focused specifically on fraud detection accuracy; broader deployment considerations fall outside this scope.