Summary
Overview
Education
Skills
Certification
UNIVERSITY PROJECTS
Timeline
Generic
SANTHOSH VADITAM

SANTHOSH VADITAM

Harrison,New Jersey

Summary

Organized and dependable candidate successful at managing multiple priorities with a positive attitude. Willingness to take on added responsibilities to meet team goals.

Overview

1
1
Certification

Education

Master of Science - Computer Science

University of Alabama At Birmingham
Birmingham, AL
12.2023

Bachelor of Science - Mechanical Engineering

Jawaharlal Nehru Technological University
05.2019

Skills

  • Python
  • C
  • SQL
  • HTML
  • CSS
  • JavaScript
  • AWS
  • Algorithms and data structures
  • Cloud Computing
  • Network security
  • Data Visualization
  • Machine Learning

Certification

  • AWS Cloud practitioner certificate
  • Graduate level certificate in Cybersecurity

UNIVERSITY PROJECTS

Breast Cancer Prediction using Machine Learning:

  • The goal of the project is to predict whether a customer has breast cancer or not.
  • Performed Data acquisition followed by pre-processing, Data cleaning, Attribute Selection, setting target Role and Features Extraction.
  • Applied various algorithms like Linear Regression, Logistic Regression, SVM, Random Forests, Decision trees, XGBoost and Evaluate candidate models based on the model performance metrics like Confusion matrix, Accuracy, Sensitivity, Precision, AUC to identify the Champion machine learning algorithm that are precise, reliable and find the higher accuracy.


File Upload Website using AWS Integration:

  • The goal of the project is to upload a file to web portal and send the SNS notifications to the shared users.
  • Front-end web pages were created using HTML and CSS.
  • Back-end functionality was developed using Python Flask.
  • Various AWS Services were used to make the website live such as EC2 instances for hosting the server, RDS service to store the user details, S3 bucket to store the uploaded files, SES service was used for Email Service, Lambda service is used to notify the users of file upload along with accessible link to file.


GENE Interaction Model:

  • Created 111929 variables by using 4-way interaction terms from 38 variables.
  • Reduced variable count to 238 variables by using Lasso regularization.
  • By using P-value less than 0.01% further decrease variable count to 9 variables.
  • Built several candidate models by using 9 variables and selected the champion model with highest adjusted R- square value of 82.6%.


Credit Card Fraud Detection Analysis:

  • Analyzed distributions of independent variables (features) against the credit card Fraud dependent variable.
  • Exploration and cleaning of the data is performed to balance the data.
  • Performed various statistical methods by comparing the accuracy of data with the statistical models Logistic Regression, Decision Tree, Random Forest classifier, Gradient Boosting Tree.

Timeline

Master of Science - Computer Science

University of Alabama At Birmingham

Bachelor of Science - Mechanical Engineering

Jawaharlal Nehru Technological University
SANTHOSH VADITAM