Hi there!π This is a quick snapshot of my data projects, highlighting my skills and knowledge in this field.
Code: Airbnb NYC Analysis
Goal: To analyze Airbnb listings in New York City and identify which areas have the highest concentration of listings.
Description: This is a project based on the Airbnb New York City 2019 that aims to analyze various aspects of rental properties in New York. The analysis is conducted using SQL to answer several questions related to neighborhood distribution, host characteristics, pricing patterns, property availability throughout the year, and review trends as indicators of listing popularity.
Skills: SQL querying, Data aggregation and grouping, Filtering and sorting data, Data-driven insights
Technology: BigQuery
Code: Building a Predictive Sales Dashboard for FMCG
Goal: To analyze FMCG sales performance across time, promotion, channels, regions, and product lifecycle to identify key drivers of growth and support business decision-making.
Description: This project focuses on analyzing FMCG transactional sales data (2022β2024) of SKU MI-006. Using SQL for data preprocessing and Power BI for visualization, the dashboard highlights weekly sales trends, the impact of promotions, sales contribution by channel and region, and product lifecycle analysis. The insights help companies optimize pricing, inventory management, distribution, and promotional strategies to enhance overall business performance.
Skills:
- SQL querying and preprocessing (handling duplicates, NULL values, outliers, data consistency checks)
- Data visualization with Power BI (interactive dashboards, trend analysis, contribution analysis)
- Business insight generation (promotion impact, lifecycle management, regional and channel optimization)
Technology:
- SQL (Data Cleaning & Preprocessing)
- Power BI (Visualization & Dashboard)
Code: Interactive Dashboard for Skincare Product Segmentation using K-Means Clustering
Goal: The goal of this project is to build an interactive decision-support tool that segments skincare products using K-Means Clustering, enabling businesses to gain real-time insights on product distribution and consumer preferences for better marketing, pricing, and inventory strategies.
Description: This project develops an interactive dashboard for skincare product segmentation using the K-Means Clustering algorithm. By analyzing product attributes such as price, average rating, and total reviews, skincare products are grouped into distinct clusters (mass-market, mid-range, premium, and niche). The interactive dashboard, built with Streamlit, enables businesses to explore segmentation results in real-time and extract actionable insights for marketing strategy, inventory management, and brand positioning. The goal is to move beyond static spreadsheets and provide decision-makers with a practical decision-support tool that simplifies data analysis, accelerates insight discovery, and strengthens competitive advantage in the skincare market.
Skills: Data preprocessing, Exploratory Data Analysis (EDA), Unsupervised Learning, Data visualization, Dashboard Development
Technology: Python, Streamlit, Pandas, NumPy, Scikit-learn, Matplotlib, Seaborn, Plotly