Python: Machine Learning and Deep Learning Projects

The Iris Classification project is a machine learning project. I used TensorFlow to build and train a model for classifying iris flowers based on their physical attributes.

The IRIS dataset, a commonly used dataset in the machine learning community, includes 150 observations of iris flowers with four features: sepal length, sepal width, petal length, and petal width. My goal is to develop a model that can accurately predict the species of an iris flower based on these four features. I used TensorFlow's powerful tools and techniques in this project to build and train a neural network model.

Started by preprocessing the data, which involved splitting the data into training and test sets and scaling the features. Then, I trained the model using the training data and evaluated its performance on the test data. I measured the model's accuracy using various metrics, such as precision, recall, and F1 score.

By working on this personal project, I aimed to gain practical experience using TensorFlow to build and train machine learning models. Additionally, I learned about the importance of data preprocessing, feature scaling, and model evaluation in ensuring the model's accuracy.

Tableau: Business and Data Analysis Projects

Boston BLUEBIKES analysis

Boston BLUEbikes Rider Analysis: Unveiling Key Insights into Rider Types, Usage Patterns, and Peak Hours

In a comprehensive analysis of Boston's popular bike-sharing program, known as BLUEbikes, I delved into the wealth of data available to uncover valuable insights.

By meticulously examining rider types, usage patterns, and peak hours, the analysis aimed to shed light on the program's impact and inform strategies for optimizing its efficiency. The findings revealed many fascinating trends, showcasing a diverse range of rider profiles and significant timeframes of high demand.

Armed with these insights, stakeholders can now make data-driven decisions to enhance the overall experience of BLUEbikes users and further promote sustainable transportation alternatives within the bustling city.

Survey Analysis for Taperk - an early-stage Loyalty Management Startup

Survey Analysis Uncovers Key Customer Insights for Taperk - Revolutionizing Loyalty Management

In an ambitious endeavor to revolutionize loyalty management, Taperk, an early-stage startup, conducted an in-depth survey analysis to better understand customer motivations, touchpoints, and pain points within loyalty programs.

By meticulously examining survey responses, the analysis aimed to unearth valuable insights that would shape Taperk's future strategies and enhance customer experiences. The findings unveiled a wealth of information, illuminating the diverse motivations driving customers to engage with loyalty programs, the crucial touch points contributing to program success, and the joint pain points that users often encounter.

Armed with these customer-centric insights, Taperk is poised to refine its offering, design innovative solutions, and cement its position as a frontrunner in the loyalty management industry, providing exceptional value to both businesses and their loyal customers.