I have experience in developing automated data pipelines using Python and SQL, which significantly optimized data processing workflows, reducing processing time by 40%. This involved designing efficient ETL (Extract, Transform, Load) processes, automating data extraction from various sources, and ensuring seamless integration into databases for real-time analytics.

Additionally, I contributed to the development of secure messaging applications catering to users in Singapore and Hong Kong. To enhance data privacy, I implemented RSA encryption, ensuring end-to-end security for user communications.

In the area of data visualization and analytics, I designed and built interactive dashboards in Power BI, enabling real-time monitoring of application performance and user behavior trends. These dashboards provided actionable insights, helping stakeholders make informed decisions.

Moreover, I worked on integrating real-time communication features by incorporating the Agora SDK for audio and video calling, allowing seamless user interaction. To enhance accessibility, I also integrated the Google Translator API, enabling multilingual support and making the application more inclusive for diverse user groups.

This project focuses on revolutionizing the way clinical trial data is accessed and utilized by medical professionals. By developing an intuitive search engine powered by Natural Language Processing (NLP) and Generative AI, we created a real-time solution that enables medical staff to quickly and efficiently find relevant clinical trial information. Using the Interact library, we designed smart prompts that extract precise and meaningful answers from large datasets, streamlining the search process. Working closely with a team of developers, data scientists, and key stakeholders, we ensured that the solution met the specific needs of medical professionals. The result is a seamless, automated system that helps medical staff access critical information faster, enhancing the overall efficiency of clinical research and decision-making.

This project examines the impact of COVID-19 on travel trends in Canada from 2020 to 2024 using Statistics Canada data. By analyzing over 2.7 million records, we explored shifts in traveler demographics, transportation modes, and regional travel patterns. The study involved data cleaning, exploratory analysis, and predictive modeling using Python (Pandas, NumPy, Matplotlib, Seaborn, Scikit-learn) for data processing and visualization. SQL was used for dataset querying, while Tableau & Matplotlib helped create interactive dashboards. We applied K-Means clustering to categorize travel behaviors and Random Forest classification to predict traveler types. Findings highlight significant changes in Canadian and international travel behavior, offering key insights into post-pandemic mobility trends.

I conducted a comprehensive analysis of Canada’s electricity sector and its environmental impact, focusing on the country’s transition toward net-zero emissions by 2035. Utilizing five key datasets—population growth, electric vehicle (EV) adoption, greenhouse gas (GHG) emissions, energy consumption, and electricity generation—I examined trends shaping the future of sustainable energy in Canada.

To forecast the financial and environmental impact of these trends, I developed predictive models using Python and R, identifying key factors influencing emissions reduction and energy demand. Additionally, I designed interactive Power BI dashboards and SQL-based reports to visualize critical insights, enabling policymakers and industry stakeholders to make data-driven strategic decisions for a cleaner energy future.

I conducted an in-depth analysis of global adult mortality trends using datasets from the World Health Organization (WHO) and the United Nations (UN). My research focused on evaluating the impact of life expectancy, vaccination rates, and socioeconomic factors on mortality rates across different regions.

To identify key risk factors influencing adult mortality, I developed regression models in R, achieving an explanatory power of 97.35%. These models provided valuable insights into the relationship between health indicators and mortality, enabling a deeper understanding of global public health challenges.

To effectively communicate findings, I designed interactive Tableau visualizations, allowing stakeholders to explore trends and correlations dynamically. These visualizations were instrumental in facilitating global public health strategy discussions, aiding policymakers and researchers in making data-driven decisions.