Subrahmanya Hegde

Machine Learning Model for Movie Genre Prediction

Developed a machine learning model using techniques like TF-IDF and classifiers such as Naive Bayes, Logistic Regression, or Support Vector Machines to predict the genre of a movie based on its plot summary.
Utilized Python libraries such as scikit-learn, pandas, and numpy for data preprocessing, feature extraction, and model training.
Achieved an accuracy of 90% on the validation dataset, demonstrating the effectiveness of the model in genre prediction.

Credit Card Fraud Detection Model:

Engineered a fraud detection model using algorithms like Logistic Regression, Decision Trees, or Random Forests to classify credit card transactions as fraudulent or legitimate.
Employed feature engineering techniques to extract relevant information from the dataset, enhancing the model's ability to detect fraudulent transactions.
Attained an F1 score of 0.91 on the test dataset, showcasing the model's efficacy in identifying fraudulent activity and mitigating financial risks.

Customer Churn Prediction Model:

Designed and implemented a churn prediction model using algorithms like Logistic Regression, Random Forests, or Gradient Boosting to forecast customer churn for a subscription-based service.
Incorporated historical customer data and demographic features to train the model, enabling proactive retention strategies to reduce churn rate.
Achieved an AUC-ROC score of 90 on the validation set, demonstrating the model's capability to predict customer churn and optimize business performance.

Spam SMS Detection Model:

Developed an AI model using techniques like TF-IDF or word embeddings with classifiers like Naive Bayes, Logistic Regression, or Support Vector Machines to classify SMS messages as spam or legitimate.
Implemented feature extraction methods to transform text data into numerical representations, facilitating effective spam detection.
Validated the model's performance with on a holdout dataset, showcasing its effectiveness in filtering out spam messages and improving user experience.

Handwritten Text Generation Model:

Created a character-level recurrent neural network (RNN) to generate handwritten-like text based on a dataset of handwritten text examples.
Utilized deep learning frameworks such as TensorFlow or PyTorch for model implementation and training, leveraging RNN architecture to capture sequential patterns in the data.
Generated coherent and realistic handwritten text samples, demonstrating the model's ability to learn and replicate complex patterns in handwriting.

• Developed professional skills through hands-on experiences, including time management and effective communication.
• Improved internship experience by efficiently managing assigned tasks and meeting deadlines.
• Sorted, organized, and maintained files.
• Received positive feedback from supervisors, reflecting a strong commitment to personal growth and development throughout the internship program.
• In my role as a Python with AWS Developer, a significant portion of my time, approximately 25% , was dedicated to Python script development. Crafting these scripts allowed me to tailor solutions to meet various project requirements, demonstrating my proficiency in leveraging Python's capabilities to streamline processes and boost productivity.
• Moreover, about 20% of my focus was directed towards utilizing key Amazon Web Services (AWS) offerings such as EC2, S3, Lambda, and RDS. Leveraging these services enabled me to deploy scalable applications, manage data storage effectively, and execute serverless functions, thereby contributing substantially to the project's infrastructure and functionality
• Additionally, another 20% of my efforts were devoted to developing automation scripts. By conceptualizing and implementing automated workflows, I played a crucial role in optimizing operational efficiencies, reducing manual efforts, and fostering agility within our development process.