Projects
Welcome to my portfolio! This page showcases a selection of the projects I’ve worked on, reflecting my journey in data analytics and my passion for solving complex problems using data. Each project represents a unique challenge that I tackled using tools such as Python, SQL, MS Excel, and Tableau, with a focus on delivering actionable insights. From predictive models to interactive visualizations, these projects demonstrate my ability to turn raw data into meaningful solutions. Feel free to explore my work, and I hope you find inspiration in the stories and methods behind each project!
Python
In the e-commerce sector, understanding and predicting customer purchase behavior is essential for enhancing revenue and customer satisfaction. This study aims to use logistic regression methods to uncover the factors behind online purchase behavior. By analyzing visitor behavior metrics, we aim to provide insights that can help businesses boost conversion rates and refine their marketing strategies.
By performing data analysis and comparing models, we seek to transform complex data into actionable insights. Each variable examined and coefficient analyzed contributes to strategic decision-making. Understanding how visitor behavior affects purchase decisions can guide organizational growth strategies.
Python
Analyzing and interpreting large amounts of text data has become crucial across many sectors, including market research and customer service. Sentiment analysis, an essential tool in natural language processing (NLP), enables organizations to gauge public opinion and customer feedback by identifying the emotions conveyed in written content. This paper examines how neural networks can be applied to sentiment analysis, with a focus on evaluating the performance of various models in predicting sentiment accurately. By utilizing sophisticated machine learning techniques, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs), this study seeks to highlight the capability of these models to improve the precision of sentiment analysis and extract valuable insights from text data.
Python
Accurate forecasting plays a crucial role in shaping effective business strategies, as it allows companies to anticipate future trends and make data-driven decisions. For the telecommunications industry, predicting revenue trends is essential for maintaining a competitive edge and efficiently managing resources. This paper examines the use of time series analysis, with a focus on the ARIMA (AutoRegressive Integrated Moving Average) model, to forecast daily revenue in the telecom sector. By leveraging historical data to uncover patterns, this study seeks to improve the precision of financial predictions, thereby offering insights that are valuable for strategic planning and enhancing operational performance.
Python, Tableau, MS Excel
This paper details the creation and launch of a web application aimed at promoting wellness in the workplace through tailored mental health strategies. Developed during the Winter '24 Hackathon organized by Chegg Skills, this project utilized data analysis and a user-focused approach to offer practical insights and tools for better sleep and mental well-being. The application includes features such as personalized recommendations, interactive dashboards, and tailored coping methods, showcasing the importance of collaborative efforts from various disciplines in successfully bringing the product to life. This paper specifically focuses on the data analysis process that underpinned these features, showcasing the role of interdisciplinary collaboration in achieving a successful product launch.
Tableau
In the telecommunications industry, where competition is fierce, gaining a deep understanding of customer behavior and finding ways to reduce churn are crucial for keeping customers and achieving long-term success. This paper examines how data analytics can be utilized to study customer churn, drawing on datasets from Western Governors University and Kaggle to uncover the main factors that affect customer retention. By creating an interactive dashboard using Tableau, the research offers a practical tool for displaying these findings and aiding strategic decisions. The project showcases how integrating data analysis with powerful visual tools can improve customer satisfaction and decrease churn rates within the telecom sector.
SQL, Tableau
In the competitive telecommunications industry, retaining customers is a key priority, as reducing customer churn directly impacts profitability and growth. Companies need to understand the underlying reasons why customers leave and how different factors contribute to churn. This paper focuses on the application of data analytics to examine customer churn, using datasets from Western Governors University and Kaggle to uncover trends and behaviors that influence retention. The study utilizes SQL to clean and transform the data, making it suitable for analysis, and Tableau to create interactive visualizations that offer deeper insights. Through the development of a user-friendly dashboard, stakeholders can explore the data, identify patterns, and take informed actions to reduce churn. This approach illustrates the importance of integrating data analysis with visualization tools to enhance strategic decision-making in customer retention.
Python
In today’s telecommunications industry, retaining customers is increasingly challenging due to high competition and rapidly evolving consumer needs. Understanding the factors that influence customer behavior and churn is critical for creating effective retention strategies. This paper explores the use of k-means clustering, a popular machine learning technique, to segment customers based on tenure, monthly charges, and data usage. By categorizing customers into distinct groups, companies can develop more tailored services and interventions that align with the specific needs of each segment. Through this approach, businesses can not only reduce churn but also enhance customer satisfaction and long-term loyalty. The study highlights how data-driven customer segmentation plays a vital role in shaping retention strategies, providing actionable insights that are key to maintaining a competitive edge.
SQL
In the telecommunications sector, managing customer churn is crucial for maintaining a stable customer base and achieving long-term success. Recognizing how different services impact churn rates can provide valuable insights into retention strategies. This paper focuses on acquiring data through SQL to merge internal customer churn information with external service subscription data. By combining these datasets, the paper provides an initial look at how various services, such as phone and online security, might relate to customer churn. The integration of this data emphasizes the importance of data-driven approaches in understanding and improving customer retention.
MS Excel, MS PowerPoint
Managing a rental car fleet efficiently requires balancing costs and revenue generation, especially in a competitive market. This study uses data analysis to assess the performance of Lariat's rental vehicle fleet by integrating multiple datasets that include vehicle specifications, operational expenses, rental income, and branch details. By employing pivot tables and scenario analysis, the research uncovers key insights and trends that can inform decisions about pricing, fleet structure, and rental strategies. The analysis provides recommendations to help Lariat minimize costs and maximize profits, ultimately improving the company’s overall operational and financial outcomes.
MS Excel, MS PowerPoint
In the real estate sector, gaining insight into the factors that affect home prices and lot sizes is crucial for guiding smart investment decisions. The architectural style of a home—whether it’s a one-story or two-story design—could have a significant impact on both the size of the lot and the final sale price. This research examines whether there are notable differences in these variables between one-story and two-story homes. Drawing on data from the "House Prices - Advanced Regression Techniques" dataset, this study uses statistical methods to compare these home styles, offering insights that can help real estate investors refine their strategies based on property features and market behavior.
Python, MS PowerPoint
Understanding how healthcare resources and environmental factors interact with life expectancy and population size is essential for shaping policies aimed at improving public health and addressing environmental concerns. This study examines global data to explore the relationships between life expectancy, healthcare access (represented by the number of physicians per thousand), and financial burden (out-of-pocket health expenditure). Additionally, it investigates how population size correlates with environmental impact, specifically CO2 emissions. By analyzing these factors, the study offers insights that can guide policy decisions in both healthcare systems and environmental sustainability efforts.
