Neha Khetawat

I turn raw, messy data into clear decisions you can act on.

Python SQL Power BI Pandas Scikit-learn

↳ the moving dots are a live PCA of 211 shoppers, split into two segments — one of my projects below.

Detail-oriented, statistics-rooted, decision-focused.

Data Analyst with hands-on experience turning raw data into clear, actionable insights. Proficient in SQL, Python, Excel and Power BI, with a solid foundation in statistics and exploratory data analysis.

Adept at cleaning, modeling and visualizing data to support confident, data-driven decisions in fast-paced, collaborative teams.

0%

SPAM CLASSIFIER ACCURACY

0

BSc STATISTICS CGPA / 10

0

ML PROJECTS SHIPPED

0

HOURS DS INTERNSHIP

The toolkit

[ 01 ] LANGUAGES

Python SQL

[ 02 ] VISUALIZATION

Power BI Advanced Excel Matplotlib Seaborn

[ 03 ] DATA TOOLS

Pandas NumPy Scikit-learn

[ 04 ] ANALYTICAL

Data Cleaning EDA Insight Generation Descriptive Stats

[ 05 ] CORE CONCEPTS

Machine Learning Deep Learning NLP Computer Vision Generative AI Feature Engineering Model Deployment

Where I've been

2026 · REMOTE

Data Science Intern

Algonive · 120-hour program

Algorithm design & optimization for data-driven applications.
ML approaches for pattern detection and predictive modeling.
Computational problem solving and algorithmic thinking on real datasets.

JAN–FEB 2026 · REMOTE

Data Science Intern

SyntecxHub · 120-hour program

Data preprocessing & EDA with Python, Pandas and NumPy.
Built and evaluated models in Scikit-learn — accuracy, precision, recall.
Designed structured ML workflows with mentors to improve reliability.

// 04—— SELECTED WORK

Projects, as data unfolds

Scroll into each — the result renders live, the way it did in the notebook.

PROJECT 01 / 2026

Consumer Shopping
Behavior Analysis · PCA

Applied Principal Component Analysis to 211 customer records, reducing dimensionality to surface two clean segments — value-seeking impulse buyers and price-conscious rational buyers. Verified with Bartlett's & KMO tests.

0

RECORDS

0

SEGMENTS

Python Pandas Scikit-learn

pca_scatter.ipynb● live

            Impulse
            Rational
          

PROJECT 02 / 2026

Employee Attrition
Prediction System

Built and compared Random Forest, XGBoost and Logistic Regression to flag attrition risk from HR analytics. Feature engineering surfaced the strongest drivers of turnover for proactive retention.

XGBoost Random Forest Logistic Regression

feature_importance● live

RELATIVE DRIVERS OF TURNOVER

OverTime

Monthly Income

Age

Job Satisfaction

Years At Company

PROJECT 03 / 2025

SMS Spam Detection

An NLP classifier reaching 97% accuracy with TF-IDF features and Multinomial Naive Bayes — deployed as a live Streamlit app for real-time text classification.

NLP TF-IDF Naive Bayes Streamlit

classifier.eval()● live

0%

TEST ACCURACY

Let's read the
data together.

Open to data analyst & data science roles. Reach out — I reply fast.

Neha Khetawat

Detail-oriented, statistics-rooted, decision-focused.

The toolkit

Where I've been

Data Science Intern

Data Science Intern

Projects, as data unfolds

Consumer Shopping
Behavior Analysis · PCA

Employee Attrition
Prediction System

SMS Spam Detection

Education

MSc in Data Science

BSc in Statistics

Certifications

Leadership & Research

Let's read the
data together.

Neha Khetawat

Detail-oriented, statistics-rooted, decision-focused.

The toolkit

Where I've been

Data Science Intern

Data Science Intern

Projects, as data unfolds

Consumer ShoppingBehavior Analysis · PCA

Employee AttritionPrediction System

SMS Spam Detection

Education

MSc in Data Science

BSc in Statistics

Certifications

Leadership & Research

Let's read thedata together.

Consumer Shopping
Behavior Analysis · PCA

Employee Attrition
Prediction System

Let's read the
data together.