Khaled Abughoush

Key Skills

Software

Surge AI

Top Subject Matter

No subject matter listed

Top Data Types

Audio

Image

Text

Top Task Types

Relationship

Segmentation

Text Generation

Text Summarization

Translation Localization

Freelancer Overview

With a strong foundation as a data scientist at PwC, I have specialized in developing and refining fraud and money laundering detection systems for large-scale financial institutions. My hands-on experience includes designing and implementing data labeling pipelines for financial transactions, ensuring that datasets are accurately tagged to train advanced AI models for anomaly and risk detection. This work has given me deep insight into the complexities of labeling sensitive financial data, maintaining high standards for data quality, consistency, and compliance. In addition to financial transaction labeling, I have broadened my expertise to include annotation of written information and diverse transactional data. My expanding skill set covers the end-to-end lifecycle of AI training data, from initial schema design and annotation guideline development to quality assurance and model feedback integration. My ability to bridge technical and domain-specific requirements sets me apart, enabling me to deliver high-impact training datasets that drive robust AI solutions in both structured and unstructured data environments.

Labeling Experience

Data Tagging

Surge AIDocumentSegmentation

In my role, I focused on document analysis to train AI models for detecting fraud and money laundering by carefully curating and annotating a diverse set of financial documents, such as transaction records and account statements. I developed detailed annotation guidelines to identify key entities, suspicious patterns, and contextual cues that signal potential illicit activity. By designing clear schemas and implementing rigorous quality checks, I ensured the training data accurately reflected real-world scenarios. This process enabled the AI models to learn how to recognize both straightforward and subtle indicators of financial crime, ultimately improving their effectiveness in identifying and preventing fraudulent activities.

In my role, I focused on document analysis to train AI models for detecting fraud and money laundering by carefully curating and annotating a diverse set of financial documents, such as transaction records and account statements. I developed detailed annotation guidelines to identify key entities, suspicious patterns, and contextual cues that signal potential illicit activity. By designing clear schemas and implementing rigorous quality checks, I ensured the training data accurately reflected real-world scenarios. This process enabled the AI models to learn how to recognize both straightforward and subtle indicators of financial crime, ultimately improving their effectiveness in identifying and preventing fraudulent activities.

2024 - 2025

Education

Work History