Koutam Srividhya

A strong passion for leveraging technology to drive impactful solutions in AI and software development is evident. With practical experience in Python and Java, coupled with a proven track record of successful project implementation, enthusiasm for contributing to a dynamic team focused on innovation in technology is demonstrated. The commitment to excellence is reflected through achievements in machine learning and task automation, aligning with the aspirations for meaningful development opportunities.

• Industrial Exposure, Completed 6 months of Certified Industrial Training at NSIC Hyderabad, gaining hands-on experience in real-world applications and industrial workflows.
• Technical Expertise, Demonstrated proficiency in programming languages such as C/C++, Python, and Java, and tools like Git, Docker, and Eclipse, strengthening my technical foundation.
• Loan Prediction, Successfully developed a Loan Eligibility Prediction System using machine learning techniques, enabling accurate and fair loan approvals by analyzing applicant data such as income, credit history, and loan amount.
• Academic, Consistently maintained strong academic performance, achieving a 7.55 GPA in Diploma - C.M.E and a 7.2 CGPA in B.Tech - C.S.M (in progress).

Loan Eligibility Prediction System, 10/2024, 12/2024, Developed a machine learning-based system to streamline and enhance loan eligibility assessments, ensuring financial inclusion. Leveraged algorithms such as Support Vector Machines (SVM) to predict loan approval based on applicant data, including income, credit history, and loan amount. The project incorporated real-time evaluation capabilities, a responsive web interface, and backend APIs built with Flask. The model achieved 89% accuracy while addressing challenges like class imbalance and bias, promoting transparency and fairness in credit assessments.

Heart Attack Using Retinal Eye Image,01/205,05/2025,Developed an AI-based system to predict the risk of heart attacks by analyzing retinal eye images. The project integrates medical imaging with machine learning to provide early warning signs of cardiovascular issues.

Key Contributions:

• Preprocessed and augmented retinal image datasets to improve model accuracy.
• Applied deep learning models (GoogLeNet and ResNet50) for image classification.
• Evaluated model performance using metrics such as accuracy, precision, recall, and F1-score.
• Conducted software testing and system validation to ensure reliability and usability.
• Collaborated in preparing test cases and final documentation.
• Managed cross-functional teams, fostering strong working relationships and enhancing overall productivity.
• Enhanced project efficiency by streamlining communication and collaboration among team members.