Project Details

The Delhi Metro Operations Optimization project aims to enhance the efficiency of train services through data-driven insights. By leveraging historical ridership data, the project analyzes passenger flow patterns and identifies peak travel times, enabling the optimization of train schedules. Utilizing Python and libraries such as Pandas, NumPy, and Scikit-learn, we clean and process the data to uncover trends and correlations.

The project employs machine learning algorithms to predict ridership during different times of the day and week, facilitating informed decisions on resource allocation and service frequency. Visualization tools present findings, allowing stakeholders to grasp key insights easily.

Ultimately, the goal is to minimize wait times, improve passenger satisfaction, and enhance overall operational efficiency for the Delhi Metro. This project not only demonstrates the power of data analytics in public transport but also showcases the potential for future app

Project Details

In my Credit Risk Modeling project using Python, I focused on predicting the probability of borrower default based on historical financial and demographic data. The process began with data collection and preprocessing, including handling missing values, outlier detection, and scaling numerical features. I conducted feature engineering to enhance model performance by creating new variables, such as debt-to-income ratio and credit utilization.

I employed machine learning algorithms like Logistic Regression, Random Forest, and Gradient Boosting to classify borrowers as risky or safe. Hyperparameter tuning was done using GridSearchCV to optimize model accuracy. I also used techniques like cross-validation to reduce overfitting and ensure robust model performance.

Project Details

In my SQL project for Faasos, I worked on analyzing customer orders and sales performance to provide actionable insights. The project began by querying large datasets containing customer information, order history, and delivery data. I used SQL to perform data cleaning, join multiple tables, and extract meaningful patterns.

I wrote complex SQL queries to analyze key performance indicators (KPIs) such as order frequency, average delivery time, and customer retention rates. Aggregation functions, window functions, and subqueries were employed to generate detailed reports. I also optimized queries to enhance database performance by indexing and normalizing tables.

The project provided valuable insights into customer behavior, sales trends, and areas for improving delivery efficiency. These findings were used to recommend strategies to boost customer satisfaction, streamline delivery operations, and increase repeat orders.

Project Details

In my Personal Finance project using Power BI, I aimed to create an interactive dashboard to help users manage their finances effectively. The project began by importing financial data from various sources, including spreadsheets and databases, to consolidate income, expenses, and savings information.

Using Power Query, I transformed the data by cleaning, filtering, and structuring it for analysis. I created calculated measures for key performance indicators, such as total income, total expenses, and net savings, using DAX functions.

The dashboard features various visualizations, including bar charts, pie charts, and line graphs, to present spending patterns, monthly trends, and budget allocations. Interactive slicers allow users to filter data by categories, timeframes, and income sources. This project not only enhances financial awareness but also assists users in making informed budgeting and spending decisions.

Live Interactive Dashboard

Project Details

In my IPL 2024 data analysis project, I aimed to provide valuable insights into the Indian Premier League matches through comprehensive data exploration. The project began with data collection from various sources, including match statistics, player performances, and team rankings. Using Python libraries such as Pandas, I imported and cleaned the dataset, handling missing values and ensuring data consistency.

I conducted Exploratory Data Analysis (EDA) to identify trends and patterns in match outcomes, player performances, and team strategies. Visualizations created with Matplotlib and Seaborn highlighted key findings, such as the impact of player form on match results and the performance of different teams across various venues.

Project Details

In this project, I comprehensively analyzed Human Resources data to uncover key workforce trends. Using Python for data preprocessing and Power BI for visualization, I examined employee demographics, turnover rates, and performance metrics. The project aimed to identify critical factors contributing to employee attrition, workforce diversity, and overall productivity. I employed correlation analysis and machine learning models to predict employee turnover and retention rates. Key insights included identifying departments with the highest attrition risk and recommending targeted strategies for improving employee satisfaction and retention. The project’s outcomes provided HR teams with actionable data-driven strategies to optimize workforce planning, improve employee engagement, and enhance operational efficiency.

Live Interactive Dashboard