I am responsible for the ongoing development, maintenance, and enhancement of our real estate duplicate listing detection project. This system processes inputs including images, text, and numerical data to accurately identify duplicate listings in our database.Key Responsibilities:- Development and Maintenance: Continue to develop and maintain the existing duplicate detection system, ensuring its reliability and efficiency.- Rule-Based Detection: Implement and refine rule-based algorithms to compare various data points and accurately detect true duplicates while avoiding overmatching.- Data Analysis: Analyze listing data to uncover patterns that indicate duplicates and translate these patterns into code rules to improve detection accuracy.- Continuous Improvement: Regularly update the system with new insights and techniques to enhance its performance and effectiveness.

As a Data Scientist, my primary responsibilities include extracting data from databases, performing ETL (Extract, Transform, Load) processes, and preparing structured reports. I ensure that data is accurately and efficiently extracted, transformed to meet the required standards, and loaded into appropriate formats, typically CSV files, to meet client specifications. My role involves close collaboration with clients to understand their requirements and deliver high-quality, actionable data insights. I leverage my technical skills to streamline data workflows, maintain data integrity, and support data-driven decision-making processes within the organization.

As the Tech Team Lead of the Data Collection team, I am responsible for ensuring the accurate and timely collection of data. Under my leadership, the team has grown from 5 to over 15 members. One of my key responsibilities has been to manage the dynamic nature of the team, as many members, primarily students, gain valuable experience and knowledge and then advance to other roles within the company. My role involves guiding and supporting the team to meet our data collection goals effectively and efficiently, fostering an environment of growth and development.

Under a little guidance from the senior developer, I created:- Excel Add In using C# language- Python package (https://pypi.python.org/pypi/tradingeconomics)- R package hosted on the GitHub- Transferred the old API documentation to the new format http://docs.tradingeconomics.com/. This project required modifying the .js, .scss and Markdown files.