Syed Ahmed

Data Scientist

Bank of America • Vollzeit

Jul 2025 - Present • 10 mos

• Developed alfa mall merchant-level RFM segmentation model using Python to analyze GMV, order frequency, and repeat customer patterns for performance and risk assessment. • Develop, validate, and enhance credit scoring models to assess borrower creditworthiness, predict default risk, and support lending decisions using statistical and machine learning techniques. • Developed a Django-based data parsing portal for Bank Alfalah that automates XML-to-Excel conversion, processes batch credit reports with deduplication, and provides real-time CNIC search with SQL Server integration. • Analyze lending portfolios to identify risk trends, segmentation opportunities, and early warning signals, translating insights into actionable recommendations for credit policy and underwriting teams. • Conduct product-level analysis across lending portfolios (e.g., personal loans, auto loans, credit cards) to evaluate performance, profitability, risk appetite alignment, and customer uptake, supporting data-driven product strategy and optimization • Automate end-to-end business procedures using Python, reducing manual effort, turnaround time (TAT), and operational risk across reporting, data validation, and decision workflows.

Data Scientist

Standard Chartered • Vollzeit

Jul 2023 - Jul 2025 • 2 yrs

• OCR for Text Detection: Developed an end-to-end solution for instant verification of text images, including data labeling and key point detection using RNN with a CTC layer. • Conversational Chatbot for RPA team using large language models (LLMs) along with extensive prompt engineering for querying and responses. The app was deployed for business use. • Sentiment Analysis and Classification of Customer Service Emails: Implemented a sentiment analysis and classification solution to better understand customer service experiences through call center email exchanges • Lead project related to web development for better utilization and scheduling of RPA bots • Data Lake and ETL Operations: Designed and developed ETL pipelines to extract, transform, and load data from various sources • Data analysis and data manipulation operations using Scala and Pyspark.

AI Researcher

Coventry University

Jan 2024 - Apr 2024 • 3 mos

Leading a project funded by Coventry University. My objective is to develop a generative baseline and a mechanism for output synthetic data similar to actual timeseries sensorial data and a method that will benchmark against state-of-the-art methods like GANs, autoencoders, restricted Boltzmann machines, etc. using remote sensing data.