Projects
Welcome to my Projects section, where I showcase my hands-on experience and expertise in implementing innovative solutions across various domains. Explore how I've applied my skills in data analysis, software development, and machine learning to solve real-world problems and drive impactful outcomes.
T20 world cup cricket data analytics
Sport Data Analysis [Python | Web scrapping | Pandas | Power BI]
• Created a Power BI report to identify top 11 players for a T20 cricket team by scraping data from espncricinfo with a Brightdata website tool.
• Cleaned and transformed the data with pandas and evaluating various player performance metrics.
• Used the resulting Power BI dashboard to select players for various categories and ultimately choose the top 11 players to play in the match.
• Selected team using the Power BI dashboard has 90% of chances to win the game.
Data Pipeline for Graph Processing
[Python, Kafka, Neo4j, Data Processing]
• Implemented a data pipeline using Minikube as the orchestrator and Kafka as the messaging queue.
• Integerated Neo4j and ensured seamless data flowdata flow from producer to Kafka, Neo4j, and data analytics phase.
• Applied data analytics techniques including PageRank and Breadth-First Search (BFS) to extract valuable insights.
Face Recognition with AWS Lambda
[Lambda, S3, DynamoDB, Python.]
• Developed a Paas Application using Docker and combining it with AWS Lambda and Elastic Container Registry.
• Lambda Trigger was created from the S3 Buckets and the face recognition logic was implemented in lambda function.
• Employed DynamoDB to retrieve person-specific details through facial recognition and returned as an Output
Revenue insights in hospitality domain
Business Analysis [Power BI | Excel]
• Atliq Grands noticed a loss in their market share and revenue over a few months. To understand the cause of this loss, they needed a way to analyze this. I created a dashboard in Power BI using three months of data.
• With the created dashboard, Revenue team of Atliq Grands were able to gain insights about their revenue trend. This could help in regaining their revenue and market share by 20% in the next month.
Google Data Analytics Capstone Project
[Data analysis, R, Tableau, Excel]
-
Analyzed a dataset using R for a company, Cyclistic, a bike sharing company in Chicago.
-
Created an interactive dashboard showing how annual members and casual riders use Cyclistic bikes differently.
-
Provided marketing strategies to convert casual riders to annual members.
Real Estate Price Prediction
[Python, Pandas, Scikit-learn, Seaborn]
-
Gathered relevant data, Cleaned and prepared the collected data by handling missing values, removing outliers.
-
Created new features and transformed existing ones to capture important information that can influence real estate prices.
-
Explore and visualize the data to gain insights into its distribution, correlations, and patterns.
-
Chose appropriate machine learning algorithm or predictive model for the task.
-
Trained the selected model on the training data, optimizing its parameters to make accurate predictions.
Food Delivery Cost and Profitability Analysis
[Python, Pandas, Matplotlib, Datetime]
​
-
Gathered and cleaned data from various sources, ensuring data integrity.
-
Extracted relevant features impacting cost and profitability.
-
Analyzed cost breakdown and revenue generation:
-
Identified fixed and variable costs associated with each order.
-
Calculated revenue from commission fees and order values.
-
Developed strategic recommendations for enhancing profitability.
-
Identified the impact of discounts on profitability and proposed adjustments.
-
Simulated financial impact of proposed changes to discount and commission rates.
-
Implemented a new profitability strategy.
-
Established optimal commission and discount percentages based on profitable order characteristics.
-
Advocated for a higher commission rate and lower discount percentage to improve profitability.
Loan Approval Prediction with Machine Learning
[Python, Data Processing, Pandas, Scikit-learn ]
-
Analyzed and preprocessed dataset:
-
Removed irrelevant columns like 'Loan_ID'.
-
Handled missing values appropriately.
-
-
Explored data through EDA:
-
Visualized feature distributions.
-
Investigated relationships with 'Loan_Status'.
-
-
Prepared data for modeling:
-
Converted categorical columns using one-hot encoding.
-
Split dataset into training and testing sets.
-
Scaled numerical features using StandardScaler.
-
-
Trained and evaluated ML model:
-
Selected Support Vector Machine (SVM) classifier.
-
Trained model on training data.
-
Evaluated performance using accuracy and other metrics.
-