Jun 2024 – Jun 2025 · 1 yr · Noida, Uttar Pradesh, India

Jun 2022 – Jun 2025 · 3 yrs · Noida, Uttar Pradesh, India

Dec 2023 – Jan 2024 · 1 mo · Remote

• Machine Learning Training | Skill India & N.S.D.C
• Successfully completed a comprehensive course in machine learning with an A grade, covering topics from Python basics to advanced techniques like ensemble models and clustering, under the organization Scholiverse Educare Private Limited.

Nov 2023 – Jan 2024 · 2 mos · Noida, Uttar Pradesh, India · On-site

• At JSSATE Noida, I worked on a project titled "SPAM FILTERING USING SVM" under the faculty of IT Department. I focused on SVM fundamentals, including hyperplanes and support vectors. I managed data collection and preprocessing, feature extraction, SVM model implementation, and testing the classifier on emails, ensuring systematic data handling and thorough model evaluation.

Oct 2023 – Dec 2023 · 2 mos · Noida, Uttar Pradesh, India · Remote

• Machine Learning Training Internshala
• Successfully completed comprehensive training in machine learning, mastering topics from Python basics to advanced techniques like ensemble models and clustering. Achieved 100% in the final assessment and was recognized as a top performer.

Oct 2023 – Dec 2023 · 2 mos · Noida, Uttar Pradesh, India · Remote

• Admission Prediction Using Logistic Regression:
• I've spearheaded a project focused on predicting admission probabilities using logistic regression, fine-tuned with gradient descent, to analyze exam performance data. Employing Python alongside Pandas, NumPy, and Matplotlib, the project aims to enhance fairness and efficiency in educational admissions through rigorous data analysis and modeling techniques.

Jul 2023 – Sep 2023 · 2 mos · Noida, Uttar Pradesh, India · On-site

• Handwritten Digit Recognition Project at JSSATE Noida under Aparna Srivastava ma'am faculty of Data Analytics of IT Department.
• Worked on the Handwritten Digit Recognition (HDR) project, utilizing a Convolutional Neural Network (CNN) with TensorFlow and Keras to classify handwritten digits. Achieved a 95.2% validation accuracy using the MNIST dataset, demonstrating significant potential for OCR and document processing applications.