SAI KAUSHIK PEESARI

- Aspiring Data Engineer and Front-End Developer with a Bachelor's in Computer Science Engineering from the University of Central Missouri, graduated in December 2023 with a GPA of 3.49.
- Proficient in programming languages and frameworks: Java, C, C++, JavaScript, Python, Bootstrap, CSS, HTML5, Spark, Py Spark, Hadoop (HDFS, Hive, Sqoop), Angular, React.
- Experienced with cloud technologies:
- AWS: RDS, Glue, Redshift, IAM, S3
- Azure: ADF, Synapse Analytics, Blob Storage
- Skilled in databases: Oracle, MySQL, Snowflake.
- Notable projects:
- Fake News Detection using Machine Learning
- Zube Analysis with Python and Flask
- Certified in:
- React Basics
- Programming With JavaScript
- React Advanced
- Python for Machine Learning
- SQL Relational Database
- Strong analytical, problem-solving, and project management skills.
- Commitment to continuous learning and professional development.
- Adept at building responsive and user-friendly front-end applications, ensuring seamless user experiences and efficient data integration.

• React Basics, Coursera, https://coursera.org/share/ebc679eec34497db8a74908a6dfe148f
• Programming With JavaScript, Coursera, https://coursera.org/share/48b11c9b00ffd9339f07b50e19537a55
• React Advanced, Coursera, https://www.coursera.org/api/certificate.v1/pdf/F6CHW76G3AYY
• Python for Machine Learning, Great Learn, https://olympus.mygreatlearning.com/courses/10899/certificate
• SQL Relational Database, Cognizant

• Introduction to Machine Learning
• Project management
• Senior Project
• Object-oriented programming through Java
• Cyber Security
• Database Management Systems
• Computer Networking
• Network Security
• Big Data
• Python development
• Business Management

❖ Fake News Detection Using Machine Learning

Roles:

➢ Created a machine learning model for detecting fake news in a dataset of news articles.

➢ Text vectorization was accomplished using TF-IDF, while classification was accomplished using Decision Trees, Random Forests, KNN, SGD, and SVMs.

➢ Accuracy, precision, recall, and F1 score were among the evaluation parameters, with a significant F1 score of 0.864.

➢ The project's goal was to automate fake news detection to increase the overall dependability of the client's news platform.

❖ Zube Analysis with Python and Flask

Roles:

➢ Using Python and Flask, I created a user interface (UI) model for detecting bogus news.

➢ A dataset of news articles was gathered and prepared for training and testing the machine learning model.

➢ For classification, I used a variety of algorithms, including Decision Trees, Random Forests, KNN, SDG, and SVMs.

➢ The model's performance was evaluated using accuracy, precision, recall, and F1-score measures, yielding an impressive F1-score of 0.864.

➢ The project's goal was to create a user-friendly interface that people could engage with and assess articles