Varun B's repositories
Churn-Modelling
In this project, I developed a machine learning model to predict customer churn. Using a dataset with features such as age, gender, credit score, and account balance, I preprocessed the data and trained the model to identify patterns that indicate whether a customer is likely to leave. This helps businesses understand and reduce customer attrition.
Heart-Disease-Prediction
In this project, I performed data analysis and machine learning to predict heart disease. Using a dataset with features such as age, sex, chest pain type, and more, I trained and evaluated models to identify patterns and predict the likelihood of heart disease, demonstrating the utility of machine learning in healthcare applications.
Social-Media-Data-Analysis
In this project, I performed a social media data analysis using Python. The analysis involved cleaning and visualizing data from platforms like Twitter to uncover trends in user engagement and likes across different categories. This helped identify the most popular categories and provided insights into overall engagement patterns on social media.
EDA-on-Retail-Data
In this project, I performed exploratory data analysis (EDA) on retail data using Python. The analysis involved loading the data, cleaning it, and conducting various descriptive and visual analyses to uncover patterns and insights. This EDA provides a foundation for deeper data analysis and informed business decisions in retail.
Flight-Booking-Prediction
In this project, I developed a machine learning model to predict flight booking prices. The dataset included features such as airline, source city, departure time, stops, and days left until the flight. By training and evaluating the model, I aimed to forecast flight prices, helping travelers make cost-effective booking decisions.
Potato-Disease-Classification
In this project, I developed a deep learning model using TensorFlow and Keras to classify potato diseases from images. The dataset included 2152 images across three classes. Training involved a batch size of 32 and an image size of 256x256 over 50 epochs. The model accurately identifies and classifies potato diseases.
Churn-Prediction-using-ANN
In this project, I developed an artificial neural network (ANN) to predict customer churn in the telecom industry. The model was trained on customer demographics and service details, and its performance was evaluated using precision, recall, and F1-score. This helps in identifying customers likely to leave, enabling targeted retention efforts.
F1-2024-Predictor
F1 2024 Predictor: Analyzed data from the last 10 Formula 1 races to predict team rankings and points for the 2024 season. Cleaned and processed race data, calculated points using historical scoring systems, and visualized predicted outcomes using Matplotlib.
Orders-Data-Analysis
Analyzed a dataset of 9994 orders using Python, SQL, and Jupyter Notebook. Performed data cleaning, handled missing values. Utilized Pandas, Matplotlib and Seaborn. Extracted insights on cost price, list price, quantity, and discount patterns. Applied SQL queries to extract and analyze data from a relational database.