About Me

Hi, my name is Surabhi Chanchal. I'm a Master's Student at the Georgia State University majoring in Information Science (Big Data Analytics). Previously, I have worked as a Programmer Analyst (2018 - 2021) at Cognizant Technology Solutions after graduating from the BPUT University, Orrissa , India with a Bachelor's Degree in Electrical and Electronics Engineering. I have also worked as Senior Analyst in Nous Infosystem (2021 - 2023). I am a passionate techie who loves to learn and explore new things. I am intrigued about how technologies and its solutions are helping the world. I love dancing, reading, and video gaming. By the way, check out my awesome work My major fields of interests include Machine Learning, Natural Language Processing, Predictive Analysis and Data Visualization .

Skills

Programming Skills:

• Python
• C#
• JAVA
• HTML
• CSS

Databases:

• RDBMS
• MYSQL
• MongoDB

Domain Skills:

• STLC/SDLC
• Agile Methodology
• Machine Learning
• Cloud Deployment

Machine Learning:

• sckit-learn
• Numpy
• Matplot
• Pandas
• h2o
• keras
• NLP
• Neural Network
• Transformers
• TF/IDF
• Data Mining
• Data Cleaning
• Regression
• Classification
• Hypothesis testing
• A/B testing
• Boosting
• Data Visualisation
• Bagging
• Time series

Experience

Graduate Assistant @ Georgia State University (2023 - present)

Currently serving as GA for the online program at GSU. Working on a data cleaning task for the GAA project, I came across some fascinating insights within the survey report that added a meaningful and enjoyable aspect to the process.

Analyst @ Nous Infosystem (2021 - 2023)

leverage advanced analytical techniques and machine learning models to extract meaningful insights from complex datasets. Proficient in handling end-to-end data analysis

Programmer Analyst @ Cognizant (2018 - 2021)

Was responsible for extracting valuable insights from data to drive informed decision-making. Proficient in utilizing statistical methods and machine learning techniques

Projects

Fake News Prediction GitHub

Skills: Python, NLP, Git, Jupyter, SVM, Neural Network, Web Scrapping, Data Cleaning

Developed and implemented a machine learning model to accurately predict and classify news articles as fake or real, contributing to the fight against misinformation.

• Gathered diverse datasets from reputable news sources, ensuring comprehensive coverage
• Applied natural language processing (NLP) techniques and machine learning algorithms to analyze and classify textual data
• Performed data manipulation, feature engineering, and model implementation using python
• Extracted relevant features from textual data using advanced NLP techniques, such as TF-IDF, word embeddings, Stop words and sentiment analysis.
• Developed, trained, and fine-tuned machine learning models for accurate classification of news articles
• Implemented cross-validation techniques to ensure the robustness and reliability of the predictive model and evaluated Model performance using Confusion Matrix and ROC

Student Performance Prediction GitHub

Skills: Python, OneHotEncoder, Git, VSCode, ML Algorithm, Flask, StandaradScaler, AWS cloud (Elastic Beanstalk), HTML

Developed a web-based application for predicting student performance using Flask framework.

• Implemented a predictive model to forecast student outcomes based on various input features
• Designed and created a user-friendly interface for data input and result presentation
• Utilized machine learning techniques to analyze historical student data and generate predictions
• Integrated Flask APIs to handle user requests and deliver real-time predictions
• Developed, trained, and fine-tuned machine learning models for accurate classification of news articles
• Implemented data preprocessing , hyperparameter tuning and cleaning techniques to enhance model accuracy

Likes Prediction

Skills: R, HuggingFace, transformer, h2o, pytorch, Pytest, XAI, tidyverse, recipes, plotly, httr

Develop and implement an optimized machine learning model using h2o to predict likes based on comprehensive data fetched through Hugging Face API. The objective is to achieve accurate predictions, conduct algorithm comparisons, and enhance model interpretability through exploratory data analysis and visualization techniques

• Successfully retrieved diverse and relevant student performance data using the Hugging Face API
• Identified h2o.randomforest as the most suitable algorithm for accurate student performance prediction through systematic evaluation
• Compiled a comprehensive report comparing the performance of different algorithms, highlighting the strengths and weaknesses of each
• Fine-tuned model parameters to achieve optimal performance in predicting student outcomes
• Uncovered valuable insights from exploratory data analysis, contributing to a deeper understanding of patterns within the dataset
• Implemented Breakdown Plot XAI to enhance the interpretability of the predictive model for stakeholders and end-users.

Walmart Sales Analysis GitHub

Skills: Git, MYSQL Workbench, SQL query, Data Cleaning , Statistical Analysis, EDA, Optimization Techniques, Database Management

Conducted a comprehensive analysis of Walmart sales data to derive actionable insights and inform business strategies.

• Defined project objectives, including understanding sales trends, identifying top-performing products, and optimizing inventory management
• Gathered and integrated sales data from multiple sources, including transaction records, product details, and customer demographics
• Cleaned and preprocessed the dataset to handle missing values, outliers, and ensure data quality
• Analyzed sales trends over time to identify seasonal patterns, peak sales periods, and factors influencing fluctuations
• rovided actionable recommendations based on analysis findings.

Education

Elements

i = 0;

while (!deck.isInOrder()) {
    print 'Iteration ' + i;
    deck.shuffle();
    i++;
}

print 'It took ' + i + ' iterations to sort the deck.';