Vignesh Arvind

[email protected] +61403576304

PROFESSIONAL SUMMARY

Aspiring data scientist currently pursuing a master's degree with a strong passion for data analysis, machine learning, and statistical modeling. Skilled in leveraging programming languages such as Python and R to extract actionable insights from complex datasets. Eager to apply academic knowledge and hands-on project experience to solve real-world business challenges and drive data-driven decision-making. Committed to continuous learning and growth in the dynamic field of data science.

WORK EXPERIENCE

No work experience added yet.

EDUCATION

Masters of Data Science
07/2023 - 11/2025
Macquaire University , Sydney, Australia
bachelor of computer science
11/2022
M S Ramaiah College Of Arts, Science and Commerce , Bengaluru GPA: 8.8

SKILLS

Technical Skills: sql, c++, java, python, database management system, Matplotlib, Tableau, Pandas, NumPy
Soft Skills: Critical Thinking & Problem Solving, Communication & Storytelling with Data

PROJECTS

Stock market trend prediction
Technologies: Python, Pandas, NumPy, scikit-learn, TensorFlow, LSTM neural networks, Matplotlib, Jupyter Notebook
Developed a predictive model to analyze and forecast stock market trends using historical financial data and machine learning algorithms
Implemented data preprocessing, feature engineering, and time series analysis to improve prediction accuracy and model robustness
Collaborated in the full project lifecycle from data collection to model validation, achieving a proof-of-concept with potential to assist investment decision-making
Grammatical Metaphor Detection
Technologies: Python, TensorFlow, Keras, Natural Language Processing (NLP), Deep Learning, Data Annotation, Literature Review
Conducted comprehensive literature review to analyze existing approaches for detecting Grammatical Metaphor (GM), identifying limitations in current methods
Designed and implemented deep learning models using Python and TensorFlow to accurately detect GM instances in natural language text, improving detection precision and recall
Collaborated in data collection and preprocessing to build a high-quality annotated dataset, enabling effective model training and evaluation
Delivered detailed survey report and performance analysis demonstrating model effectiveness, contributing to advancing automated linguistic phenomenon detection
drivers of unemployment in Canada
Technologies: R, Survey Package in R, Logistic Regression, Weighted Descriptive Statistics, Chi-square Tests, Statistics Canada Labour Force Survey Data
Conducted comprehensive analysis of unemployment drivers in Canada using Statistics Canada’s Labour Force Survey data, addressing key demographic and economic factors impacting employment outcomes
Applied design-based statistical methods including weighted descriptive analysis, logistic regression modeling, and chi-square hypothesis testing to ensure accurate representation and robust inference
Implemented survey weighting, sampling design considerations, and nonresponse adjustments to improve estimate precision and support evidence-based policy recommendations on labour market equity and participation