Data Analyst · Open to Opportunities

Hritika
Dev

I turn complex, messy data into decisions that move the needle — through scalable pipelines, sharp dashboards, and ML models that actually get used.

2+
Years of Production Experience
Ayna.ai · Saint Louis University
41%
Surplus Inventory Reduced
via KPI-driven dashboards freeing working capital
10–12h
Weekly Manual Work Eliminated
through Python & Power BI automation
Background

About Me

I'm a B.Tech graduate from NIT Delhi with a focus on data analytics and machine learning. Over the last two years, I've worked across fast-moving startups where data had real, immediate stakes — from pricing engines for competitive tenders to inventory systems that freed up working capital.

My background spans the full data lifecycle: designing ETL pipelines, building KPI frameworks from scratch, and delivering BI dashboards that actually change how teams make decisions. I care about the numbers being right, the code being clean, and the output being usable.

Outside of work, I've applied ML to scientific problems — detecting bearing faults in motor vibration data using Discrete Wavelet Transform, achieving 98.6% classification accuracy. I'm equally comfortable in rigorous, research-driven environments as in product analytics roles.

Currently Data Analyst at Ayna.ai, Bengaluru
Education B.Tech · NIT Delhi · CGPA 7.6 · 2024
Interests Distributed computing, ML for scientific data, dashboard design, causal inference
Status Open to Data Analyst / Scientist roles globally
Technical Toolkit

Skills & Stack

⚙️
Languages & Query
Python SQL PySpark Pandas NumPy
📊
BI & Visualisation
Power BI Tableau Matplotlib Seaborn Google Analytics
🤖
Machine Learning
Scikit-learn Random Forest SVM XGBoost SMOTE KNN
🔧
Data Engineering
ETL Pipelines Spark Data Cleaning KPI Frameworks Feature Engineering
🛠
Tools & Workflow
Advanced Excel JIRA Git Jupyter Agile
📐
Core Competencies
A/B Testing Statistical Analysis Storytelling Stakeholder Comms
Career

Experience

Aug 2024 – Present · Full-time
Data Analyst
Ayna.ai · Bengaluru, IN
  • Architected an AI-powered quotation platform unifying engineering specs, product configuration logic, and real-time pricing models — cutting bid turnaround from 1–2 days to hours and enabling live margin optimisation across competitive tenders.
  • Built an automated end-to-end inventory reporting pipeline in Python and Power BI, eliminating 10–12 hours of manual processing per week and reallocating capacity toward strategic analysis.
Mar 2024 – Jul 2024 · Internship
Data / Systems Intern
Ayna.ai · Chennai, IN
  • Diagnosed fulfillment bottlenecks via shipment data analysis; achieved a 15% uplift in operational throughput, creating headroom for higher order volumes.
  • Designed KPI-driven inventory dashboards for Finance and Operations; reduced surplus inventory by 41%, directly freeing working capital for strategic reinvestment.
Aug – Sep 2023 · Internship
Data Analyst Intern
Saint Louis University · Remote
  • Built campaign performance dashboards tracking digital KPIs; surfaced spend inefficiencies that cut ad budget by 47% while preserving campaign reach.
  • Delivered ROI and attribution insights to marketing leadership, directly shaping budget reallocation and go-forward strategy.
Work & Research

Project Highlights

01 · Featured
Credit Card Fraud Detection on Highly Imbalanced Data
86% Precision · 85% Recall on unbalanced dataset
0.18% minority class prevalence
SMOTE + threshold optimisation + class weighting

Built a multi-model classification pipeline on a severely imbalanced fraud dataset. Benchmarked SVM, Logistic Regression, Gradient Boost, and Neural Networks. Applied SMOTE oversampling and threshold tuning to achieve strong recall without sacrificing precision — critical in fraud contexts where false negatives are costly.

Python Scikit-learn SMOTE XGBoost Jupyter
02
Amazon Sales Analysis

Analyzed Amazon sales data to extract seasonal trends, top-performing SKUs, and regional demand patterns using Python. Built visual reports for decision-maker consumption.

End-to-end EDA pipeline
Actionable visual storytelling
Python Pandas Matplotlib Seaborn
03
HR Analytics — Employee Attrition

Analyzed employee demographics and attrition drivers across departments. Identified key retention risk factors and built dashboards tracking workforce trends for HR leadership.

Multi-factor attrition modelling
Interactive HR dashboards
Python Power BI Statistical Analysis
04
COVID-19 Global Data Analysis

Analysed worldwide COVID-19 progression data — case growth rates, mortality trends, and regional comparisons — and built an interactive Tableau visualisation for public insight.

Global dataset · time-series analysis
Interactive Tableau dashboard
Tableau Python Pandas
Research · NIT Delhi
Bearing Fault Detection via DWT & ML

Pre-processed 9 sets of motor vibration data; applied Discrete Wavelet Transform to extract 10+ statistical features. Trained and benchmarked Weighted KNN and SVM — achieving 98.6% classification accuracy. Mentored by Dr. Sachin Kumar Singh, Asst. Professor.

Python DWT Scikit-learn SVM KNN Signal Processing
98.6%
Classification Accuracy

Get In Touch

I'm open to full-time Data Analyst and Data Scientist roles — especially in product analytics, scientific computing, or anything that rewards rigorous thinking. Reach out and let's talk.