Welcome to my data portfolio! Here, I document a summary of my data projects.
| Project Link | Completion Date | Tools | Project Description |
|---|---|---|---|
| ⚡ End-to-End Energy Forecasting ML System: MLOps Implementation and Deployment | Jul 2024 - | Python, W&B, Hopswork (feature Store), Streamlit, Airflow, GitHub Actions | I'm building an end-to-end energy forecasting ML system that applies MLOps best practices—designing batch-serving architecture, implementing feature engineering with Hopsworks, training models with hyperparameter tuning using Weights & Biases, orchestrating workflows with Airflow, and deploying the solution on Google Cloud Platform with Docker and CI/CD pipelines—all adapted for a Windows environment. |
| ⚡ Supervised Machine Learning for Predicting Sustainable Energy Needs | Sep 2023 | Python, Sci-kit, ARIMA | Using supervised machine learning models in Python, I predicted future energy consumption and forecasted carbon emission levels for 176 countries based on the Global Data on Sustainable Energy. This project achieved accurate five-year forecasts, supporting the United Nations' Sustainable Development Goal 7 by providing insights into global energy needs and environmental impact. |
| Project Link | Completion Date | Tools | Project Description |
|---|---|---|---|
| May 2024 | Python | This analysis aims to understand the factors influencing customer satisfaction at British Airways, including popular routes, holiday seasons, and overall customer experiences. | |
| 🤑 Data Analysis of Customer Buying Habits at CardioGood Fitness | Sep 2023 | SPSS | As a marketing enthusiast, I explored customer data of CardioGood Fitness Company and discovered trends in the buying behavior and characteristics of customers. I then presented my actionable insights and recommendations to the marketing team which can lead to business success. |
| Project Link | Completion Date | Tools | Project Description |
|---|---|---|---|
| 📈 Datacamp's Data Analysis in Excel | Sep 2023 | Microsoft Excel | Acquired valuable techniques such as EDA with pivot tables, Advanced Logical functions, What if Analysis and Forecasting to make informed decisions and uncover hidden insights within data. |
| 🏠 House Prices in California | May 2023 | Microsoft Excel | I performed Data Analysis of House Prices in California from 1990 to find a correlation of prices with various variables along with a dashboard and presented key insights. This public dataset is taken from Kaggle. |
| 📈 Microsoft Financial Performance Dashboard | May 2023 | Microsoft Excel, PowerQuery | Scrapped data from Yahoo Finance using power query in Excel and created a minimalist dashboard of Microsoft financial performance from 2019 - 2022. Insights such as Total Return over 4 years, Monthly Average Return over 4 years, etc. are presented in the dashboard. |
| Project Link | Area | Project Description | Libraries |
|---|---|---|---|
| EDA & Hypothesis Testing | This analysis aims to understand the factors influencing customer satisfaction at British Airways, including popular routes, holiday seasons, and overall customer experiences. | Pandas, Matplotlib, Seaborn | |
| 👩🏻💻 Harvard's CS50p - Ongoing | Programming | This repo contains the solution to the problem sets in Harvardx CS50P Introduction to Programming with Python. | - |
| 🧹 Data Cleaning in Python | Data Preprocessing & Data Cleaning | As a part of LinkedIn Course of data cleaning in Python essential training, I explored various methods and problems related to data cleaning such as data validation, missing values, duplicates etc. | Pandas |
| 🏨 Hotel Booking Cancelation Analysis | Data Wrangling & EDA | Analysis of Hotel Booking data to explore the major reason behind the increasing trend in booking cancelation across its two franchises. | Pandas, Matplotlib |
| Project Link | Area of Analysis | Project Description |
|---|---|---|
| 💻 Intro to SQL | SQL queries for Complex Big Query datasets | Developed SQL queries for Google BigQuery datasets to support real-world data problems |
| Project Link | Completion Date | Project Description |
|---|---|---|
| 🤑 Data Analysis of Customer Buying Habits at CardioGood Fitness | Sep 2023 | As a marketing enthusiast, I explored customer data of CardioGood Fitness Company and discovered trends in the buying behaviour and characteristics of customers. I then presented my actional insights and recommendations to the marketing team which can lead to business success. |
| 💻 [Project] | Soon | Projects are underway |
| Project Link | Project Description | Dashboard Link |
|---|---|---|
| Human Resource Dashboard | This HR Dashboard provides in-depth insights into key human resource metrics, including employee demographics, salary analysis, and performance evaluations. | Tableau Dashboard |
| Sales & Customer Dashboards | A comprehensive Tableau dashboard providing detailed insights into sales performance and customer analysis. | Tableau Dashboard |
| Video Game Sales Analysis: 1994-2010 | I performed thorough competitor analysis on video game sales data from 1994 to 2010. The resulting dashboard provides insights into Playstation, Xbox and Nintendo sales trends, platform popularity, and top games/genres. | Tableau Dashboard |
| The Health and Lifestyle Dashboard | This dashboard presents visualization of health and Lifestyle data. you can filter the charts based on Sleeping disorders. Thus providing valuable insights on how the behavior of individuals from different occupations is affected by sleeping disorders such as Sleep Apnea and Insomnia. | Tableau Dashboard |
Thanks to Katie Huang for her great guide to making this portfolio.