Open to opportunities

Vedant Ghaisas

@vedantghaisas

Statistics professional delivering data-driven insights through predictive modeling, survey research, and consumer-behavior analytics.

India

Message

What I'm looking for

I’m looking for a role where I can apply statistical analysis and predictive modeling to real business questions, especially survey and consumer-behavior data. I want a collaborative team that values clear, evidence-based recommendations and rigorous methods.

I’m a statistics professional (M.Sc., The Maharaja Sayajirao University of Baroda) with hands-on experience turning complex data into clear, actionable insights. I focus on survey research, consumer behavior analysis, and predictive modeling to support better decisions.

In my M.Sc. work, I led a statistical study on Q-commerce consumer adoption, using multi-stage stratified sampling and techniques like EFA, PCA, correspondence analysis, clustering (K-Medoids), and regression models. I compared Decision Tree, Random Forest, and Logistic Regression models and translated results into business recommendations, with my findings featured in Gujarat Samachar.

I also analyze sentiments and research outcomes through structured survey design and hypothesis testing, including sentiment analysis of student opinions on trending topics. My goal is to keep building rigorous statistical workflows—clear methodology, strong model evaluation, and insights people can actually use.

Experience

Work history, roles, and key accomplishments

Q-Commerce Adoption Study

The Maharaja Sayajirao University of Baroda

Jan 2025 - Jan 2026 (1 year)

Designed a multi-stage stratified sampling framework (n=341) and ran full statistical + machine learning modeling to predict Q-commerce adoption likelihood. Compared Decision Tree (AUC=0.823, Accuracy=81.4%), Random Forest (Sensitivity=94.1%), and Logistic Regression (AUC=0.817), and identified two adoption dimensions (Convenience & Lifestyle, Price Sensitivity) via EFA.

Cochran'S Formula K Medoids Clustering Logistic Regression Decision Trees Random Forest Chi Square Test

Student Sentiment Analysis

The Maharaja Sayajirao University of Baroda

Jan 2024 - Jan 2025 (1 year)

Collected and analyzed MSU student survey responses to classify sentiment toward trending topics and interpret sentiment patterns across respondent groups. Applied hypothesis testing to assess relationships between sentiment outcomes, age, and social media usage frequency.

Survey Design Sentiment Analysis Hypothesis Testing Likert Scale Analysis Python

Academic Dishonesty Study

The Maharaja Sayajirao University of Baroda

Jan 2023 - Jan 2024 (1 year)

Conducted a stratified survey study (n=305) on prevalence and demographic determinants of academic dishonesty across MSU departments. Used G-square tests, non-parametric methods, and logistic regression to quantify effects of age, gender, and academic level for policy-oriented reporting.

Stratified Survey Sampling G Square Tests Non Parametric Methods Logistic Regression Questionnaire Design Statistical Modeling Data Analysis

Education

Degrees, certifications, and relevant coursework

The Maharaja Sayajirao University of Baroda

M.Sc., Statistics

2024 - 2026

Activities and societies: Dissertation (2025–26): multi-stage stratified sampling + EFA + K-Medoids + PCA + logistic regression/decision tree/random forest; plus related sentiment analysis project (2024–25).

M.Sc. in Statistics focused on statistical study design, predictive modeling, and survey-based analysis. Completed a final-year dissertation on Q-commerce consumer adoption using sampling, EFA, clustering, and classification models.

The Maharaja Sayajirao University of Baroda

B.Sc. (Hons.) Statistics, Statistics

2021 - 2024

Activities and societies: Final-year study (2023–24): stratified survey (n=305), G-square tests, non-parametric methods, and logistic regression across age, gender, and academic level.

B.Sc. (Hons.) in Statistics with work applying survey research methods and statistical hypothesis testing. Completed a final-year study on academic dishonesty prevalence and demographic determinants using stratified survey design and logistic regression.