Sai Shivani Yojitha Pethakamsetty

Skilled in web design, cloud architecture, and application development, with a strong track record of delivering high-quality digital solutions. Proficient in building responsive websites, developing scalable cloud-based applications, and programming in multiple languages. Expertise includes front-end and back-end development, cloud platforms (AWS, Google Cloud, Azure), and data analytics for performance optimization. Adept at fostering client relationships and driving measurable results through innovative strategies and solutions.

• Passionate about reading works by influential leaders like Steve Jobs to gain insights into innovation and leadership. Actively participated in high school basketball competitions, showcasing teamwork and leadership skills. Regularly engaged in university technical fairs, contributing to and learning from various tech innovations.

Undergrad Champs: Technical | December 2020

Won first place in a competitive computer science event focused on Artificial Intelligence (AI) and the Internet of Things (IoT). This experience required in-depth research and practical application of AI and IoT concepts, including data analysis, machine learning algorithms, and smart device integration. The event not only allowed me to showcase my technical knowledge but also enabled me to engage in discussions with industry peers, exchanging ideas and perspectives that further deepened my understanding of these rapidly evolving technologies. The competition honed my presentation and communication skills, as I effectively conveyed complex technical topics to a diverse audience.

• Google IT Support Professional Certificate (Coursera) – Gained foundational knowledge in IT support, including troubleshooting, customer service, networking, and system administration.
• AWS Certified Cloud Practitioner (Amazon Web Services) – Learned the basics of cloud computing and AWS services, focusing on cloud infrastructure and security.
• Introduction to Machine Learning (Coursera) – Explored core concepts of machine learning algorithms, supervised and unsupervised learning, and data preprocessing.
• Web Development Bootcamp (Udemy) – Completed intensive training in HTML, CSS, JavaScript, and front-end frameworks, building

 ENC-Cloud Storage-Based Solution
During my final year of graduation, I developed a highly secure and adaptable cloud storage solution focused on enhancing data privacy and business resilience. The project involved implementing advanced encryption methodologies, where all data synchronized across cloud servers was stored in encrypted files with robust encryption keys. This approach ensured high levels of data security while enabling seamless data exchange across various formats. Additionally, the project demonstrated the critical role of cloud storage

Secure Transact- A Financial Fraud Detection System

Overview:
The Financial Fraud Detection System is a sophisticated machine learning-based application designed to detect and prevent fraudulent activities in real-time. It leverages advanced algorithms, behavioral analysis, and data-driven insights to identify suspicious transactions while ensuring minimal disruption to legitimate users. The system was developed to address challenges in financial fraud, including imbalanced datasets, evolving fraud techniques, and the need for high scalability and low latency improving automation, data synchronization, and disaster recovery, highlighting its potential to optimize business continuity in unpredictable environments. Delivered high precision (92%) and recall (88%) fraud detection capabilities, integrated Explainable AI for transparency, and ensured regulatory compliance (GDPR, PCI DSS). Deployed on AWS with Docker and Kubernetes, processing millions of transactions per second while maintaining sub-200ms latency."

Fraud Detection Datasets Overview:

Used Credit Card Fraud Detection Dataset (Kaggle) with 284,807 transactions and 492 fraud cases (~0.17%), featuring PCA-transformed components and labels. Leveraged PaySim simulated mobile money data with over 6 million transactions for anomaly detection. Incorporated E-commerce and Banking Data with user behaviors, transaction amounts, geolocation, and fraud labels. Addressed challenges like data imbalance using SMOTE and handled anonymized data with feature engineering for real-world applicability

Secure Transact: Key Features Across Datasets

• Transaction Amount: Numeric value of each transaction.
• Time: Timestamp or elapsed time for time-series analysis.
• Geolocation: Tracks transaction locations for anomaly detection.
• User Behavior: Frequency, average amount, and location trends.
• Fraud Labels: Binary indicators for supervised learning (1: Fraud, 0: Legitimate).

Dedicated and results-oriented computer science student with a strong foundation in programming, networking, and web development. Proven ability to combine technical expertise with leadership and teamwork skills, honed through active participation in group presentations, seminars, and collaborative projects. Passionate about applying knowledge to real-world challenges, such as developing solutions like Secure Transact, a fraud detection system leveraging machine learning and data analytics. Currently advancing academic and professional growth at Sacred Heart University, with a commitment to contributing to innovative technological communities.