0%
About Experience Projects Blog Publications Skills Certificates Contact

Atharva
Bakde

I help companies, brands and entrepreneurs develop data-driven solutions and achieve their business goals

Aspiring
Data
Analyst

Get to
know me

Atharva Bakde
Download CV LinkedIn GitHub Instagram Medium
Digital Analytics Intern · Real Fashion Index

I'm Atharva Bakde — a data analytics master's student at UMass Amherst, Isenberg, graduating May 2026. I build ML pipelines, NLP systems, and dashboards that turn messy data into clear decisions. My background spans Information Technology, DevOps, and cybersecurity — I bring the engineering rigour that most analysts don't.

5
Projects
shipped
2+
Years
experience
3
Research
papers
May
2026
Available
full-time
Education — 01
M.Sc. Business Analytics
UMass Amherst · Isenberg
Class of May 2026
Education — 02
B.Tech Information Technology
Vishwakarma Institute
of Technology · 2024
Currently
Digital Analytics Intern
Real Fashion Index
Jan 2026 – Present
Based in
Amherst, MA
Open to remote, on-site
& relocation

My
Experience

Jan 2026 — Present
Real Fashion Index
Digital Analytics Intern · South Carolina, USA · Hybrid
  • Analyzed website performance using GA4 and Google Search Console to surface SEO gaps and user behavior trends, contributing to a 23% increase in organic traffic within the first month
  • Built Looker Studio dashboards and set up Google Tag Manager event tracking to give stakeholders clear, real-time visibility into site KPIs and user interactions
  • Worked closely with product, design, and marketing teams to translate data findings into UX improvements, reducing bounce rates on high-traffic landing pages
Oct 2023 — Mar 2024
SpryIQ Technologies
Business Analyst · Pune, India · On-site
  • Built automated data pipelines using Python and SQL that eliminated 12+ hours of manual preparation per week and significantly improved the reliability of downstream reporting
  • Developed Power BI dashboards to track KPIs and flag data quality issues, giving Finance and Operations teams faster access to the information they needed
  • Worked with cross-functional stakeholders to consolidate reporting processes and align data outputs with business goals, improving consistency across teams
  • Coordinated Agile sprint planning for analytics deliverables, cutting report delivery time by 22%
Jul 2022 — Dec 2022
Onsolve LLC, CRISIS24
Research Analyst Intern · Bangalore, India · On-site
  • Queried and analyzed over 1 million records in SQL to uncover data quality issues and reporting gaps, directly improving the accuracy of compliance reports
  • Built Grafana dashboards to monitor real-time financial and operational KPIs, helping leadership spot and respond to compliance issues before they escalated
  • Collaborated with cross-functional Agile teams through requirements gathering, solution design, and UAT to ship monitoring systems that met compliance standards
Sep 2021 — Dec 2021
Vedanta Resource Limited
Information Technology Analyst Intern · India · On-site
  • Worked on networking using Cisco Packet Tracer and Cisco Network Assistant
  • Configured routers and switches with communication protocols for secure connectivity
  • Gained hands-on experience with DHCP, DNS, and network security fundamentals

Recent
Projects

01/05
Ongoing · Samsung Health API
6 yrsPersonal health data
108Engineered features
K-meansLife-phase clustering
Sleep, steps, heart rate & nutrition → unsupervised clustering → behavioral drivers of fat loss
Personal Health Analytics & ML Python · Scikit-learn · Samsung Health
02/05
Seattle · Inside Airbnb dataset
541KGuest reviews processed
6,800Listings analyzed
~10mFull pipeline runtime
BERTopic semantic clustering + VADER sentiment → interactive Flask app to surface top stays by experience type
Airbnb Listing Recommender NLP · BERTopic · VADER · Flask
03/05
Random Forest · Kaggle · 1,025 patients
96.1%Model accuracy
0.996AUC–ROC score
2Missed diagnoses / 158
13 clinical features · StandardScaler + outlier removal · 98.7% recall — near-zero false negatives
Heart Disease Prediction Random Forest · Scikit-learn · EDA
04/05
Random Forest · SMOTE · Apr 2025
86.7%RF test accuracy
+35ptAbove LR baseline
90%Class imbalance handled
Temporal & weather features · SMOTE balancing · 4 models benchmarked · week-of-year top predictor at 18.9%
Global Traffic Accident Analysis Random Forest · SMOTE · Feature Engineering
05/05
Upcoming
6Years of listening history
NLPMood & energy analysis
×Cross-correlated with health data
Genre shifts · late-night vs morning listening · mood mapped to life phases
Spotify Listening Analytics Python · Spotipy · NLP · Pandas

Latest
Writing

Featured · Data Science
From Steps to Self-Awareness: A Data-Driven Analysis of My 6-Year Health Journey

Building a full ML pipeline on 6 years of personal Samsung Health data — cleaning 64 raw files, engineering 108 features, and finding patterns I never noticed while living them.

Read on Medium →
Engineering
Dynamic Programming Strategy for Real-World Problem Solving

Breaking down DP patterns with practical examples beyond textbook problems.

Read on Medium →
AI · Opinion
Artificial Intelligence in Social Media

How AI shapes what we see, share, and believe across social platforms.

Read on Medium →

Research
Publications

# Title Conference Link
01 Detection and Categorization of Patients Having Alzheimer's Disease: Machine Learning Algorithms ICAPSM 2022 Paper →
02 Effective Mid-Day Meal Analysis Depending on Children's Needs Using Machine Learning Grenze International Journal of Engineering and Technology, Vol. 9, Issue 1 · Jan 2023 Paper →
03 Brain Tumor Classification Using Machine Learning JPRI 2021 Paper →

What
I do

A full toolkit spanning data science, analytics, and engineering

Programming
& Databases
Python R SQL PostgreSQL Snowflake Google BigQuery MongoDB HTML/CSS
Analytics
& Machine Learning
Scikit-learn TensorFlow Statistical Modeling Predictive Modeling A/B Testing Feature Engineering ETL Data Wrangling GA4 Google Tag Manager Alteryx Advanced Excel Pandas NumPy
Visualization
& BI Tools
Power BI Tableau Looker Studio Grafana Matplotlib Seaborn Agile / Scrum JIRA ClickUp
DevOps
& Tools
Git GitLab Docker Kubernetes Ansible Terraform FortiSOAR Fortinet Figma Claude Chatbase

Certificates

01
Google Data Analytics
Google · Coursera
02
AWS Cloud Technical Essentials
AWS · Coursera
03
Power BI Data Modeling with DAX
LinkedIn Learning
04
Power BI Essential Training
LinkedIn Learning
05
Learning Power BI Desktop
LinkedIn Learning
06
Machine Learning: Hands-On Python & R in Data Science
Udemy
07
Python & Django Full Stack Web Developer Bootcamp
Udemy
08
The Complete Android N Developer Course
Udemy
09
Basic AutoCAD for Engineering Students
Udemy
10
Introduction to Python
DataCamp
11
Data Manipulation with Pandas
DataCamp
12
Supervised Learning with scikit-Learn
DataCamp
13
Ensemble Methods in Python
DataCamp
14
Data Visualization in Power BI
DataCamp
15
Case Study: Analyzing Customer Churn in Power BI
DataCamp
1/3

What's
your name?

What's
your email?

Tell me about
your project

Thank you!
I'll be in touch soon