Data Analyst, BI Analyst, Data Scientist

SHREE RAKSHA ARSIKERE PATTABHI RAMU

407-***-**** • *********@***.*** • linkedin.com/in/shreeraksha-ap • github.com/ShreeRaksha-98 • Milpitas, CA OBJECTIVE: Actively looking for Full-time opportunities in Data Science, Data Analytics and Computer Science EDUCATION

Master of Science, Computing & Information Sciences (Conc. In Data Science) Jan 23 - Aug 24 University of North Florida, Jacksonville, FL GPA: 3.87 Courses : Data Analytics, Data Visualization, Machine Learning, Design and Analysis of Algorithms, Data Structures, Programming for Data Science, Computer Networks, Information Assurance Certificate Course in Data Science ML & AI Sept 21 - May 22 Skillslash Academy, Bengaluru, India

Bachelor of Architecture Sept 16 – Aug 21

BMS College of Engineering, Bengaluru, India GPA: 3.90 TECHNICAL SKILLS

Tools: SQL, SSRS, Power BI, Tableau, Python, Power Automate, Power Apps, Excel, R, GitHub, HTML, Java,

Libraries: NumPy, Pandas, Matplot, Sklearn

Skills: Statistical Analysis, Machine Learning, ETL, Data Cleaning, Data Visualization, Natural Language Processing, Data Structures PROFESSIONAL EXPERIENCE

BI Reporting Analyst Intern, Bank of Montreal (BMO), San Francisco Jan 24 – Aug 24

• Enhanced Reporting Efficiency: Automated the generation of comprehensive Credit Card Fraud reports for both commercial and retail divisions. This eliminated repetitive manual processes, increasing efficiency by 80%.

• Data Integration and Analysis: Leveraged SQL queries to extract and consolidate data from multiple databases, creating insightful and actionable reports in Power BI. Developed various dashboards to track KPI metrics, providing the team with real-time performance monitoring and decision-making tools.

• Automation and Application Development: Utilized Power Automate to design and implement automated workflows, significantly streamlining team operations. Created custom apps using Power Apps to collect user information and store it in SharePoint lists, with automated email notifications sent to respective recipients, improving data management and communication processes.

Tech Intern, X-Era Realty, Jacksonville May 23 – Aug 23

• Automated email workflows using Google Apps Script for X Era Realty, a commercial real estate company.

• Assisted in CRM setup and optimization to enhance Data organization for X Era Realty. Research Assistant, University of North Florida, Jacksonville Feb 23 – May 23

• Developed a Computer Vision based iOS application to detect, measure the dimensions and classify various indoor 3D objects such as floors, walls, windows, etc., using ARKit.

• Deployed the application using Unity and Xcode for a Construction Project carried out by Prof. Vamsi Sai Kalasapudi. PROJECTS

Diabetes Prediction

• Conducted data analysis, cleaning, and feature engineering to develop a diabetes prediction model using a Random Forest Classifier, leveraging demographic and lifestyle features such as age, number of children, gender, smoking habits, and location to estimate diabetes probability.

• Deployed the model on Heroku, incorporating HTML and CSS within a Flask web framework for seamless accessibility. Image Classification

• Traditional ML Models: Utilized ensemble methods (LightGBM, Random Forest, Logistic Regression) on the CIFAR-10 dataset, achieving accuracies between 46-52%.

• Convolutional Neural Networks: Designed and trained CNNs with varying layers, filters, batch normalization, max pooling, dropout rates (0.3 and 0.5), and ReLU activation. Achieved an accuracy of 87%.

• Transfer Learning: Employed ResNet50 for transfer learning. Preprocessed data by resizing and one-hot encoding. Achieved a 97% accuracy after 3 epochs, using ReLU for intermediate layers and Softmax for the output layer. Car Price Prediction

• Conducted comprehensive analysis of car price data, addressing missing values and outliers through data cleaning techniques.

• Applied advanced feature engineering methods, including VIF calculation and PCA, to prepare data for linear regression modeling, resulting in a highly accurate predictive model. NLP Fake News Classifier

• Applied Natural Language Processing (NLP) to the news title, involving stemming and pre-processing to convert text into a bag of words representation using Count Vectorizer.

• Naïve Bayes’s MultinomialNB and Passive Aggressive classifier models are later used for training and predicting fake news.

Contact this candidate