Atharva Chaskar

Background

Experience

Associate Application Developer

Accenture · Data & Analytics · Pune, India

Apr 2023 – Jul 2024

Engineered and optimized Azure Data Factory (ADF) ELT pipelines across 5+ heterogeneous data sources, improving data ingestion reliability by 15% through rigorous validation and profiling checks
Refactored legacy SQL transformation scripts in Snowflake, reducing query execution latency by 10% and delivering KPI-ready datasets for executive-level automated dashboards
Developed reproducible automated reporting workflows and new ADF components based on sprint requirements, cutting recurring data quality anomalies by ~15%
Coordinated bi-weekly production releases utilizing Git-based version control and CI/CD pipelines, collaborating on code reviews, providing UAT support, and maintaining technical SOPs

Education

M.S. Management Information Systems

University of Illinois Springfield

GPA 3.9 / 4.0 · May 2026 · Beta Gamma Sigma

B.E. Mechanical Engineering

JSPM's Rajarshi Shahu College of Engineering, Pune

May 2022

Work

Projects

Data Engineering

CTA Performance Analytics Platform

End-to-end pipeline ingesting 25 years of Chicago Transit Authority ridership data from a public REST API, loaded into Snowflake, and surfaced through an interactive live dashboard.

Analyzed 11.1 billion total rides spanning 25 years of Chicago Transit Authority ridership data using Pandas and SQL to identify key macro patterns, including a 57% post-2020 drop and system recovery trajectories
Built a Python-based ETL pipeline to ingest data from the Chicago Data Portal API, migrating data from local SQLite storage to a Snowflake cloud data warehouse for live application performance
Designed and launched an interactive Plotly Dash web application featuring 4 dynamic visualizations evaluating bus vs. rail distribution and year-over-year growth trends

Python Pandas Snowflake Plotly Dash REST API Render

Live Dashboard ↗ GitHub ↗

Spatial Analytics

Transit–Walkability Gap Research

Applied unsupervised machine learning to 3,322 census block groups to identify mobility misalignment patterns across the Chicago metro area.

Conducted spatial segmentation analysis on 3,322 census block groups from the EPA, applying K-means clustering to discover a critical walkability gap impacting 53% of the Chicago metropolitan area
Built an end-to-end Python pipeline incorporating feature selection, z-score standardization, and one-way ANOVA validation, optimizing model stability by identifying and removing multicollinear variables
Generated publication-quality spatial maps using GeoPandas and Matplotlib, visualizing cluster distributions across the Chicago–Naperville–Elgin CBSA
Co-authored a peer-reviewed research paper accepted to the MWAIS 2026 Proceedings, winning the Best Research-in-Progress Paper Award over faculty and doctoral submissions

Python scikit-learn GeoPandas Matplotlib K-means ANOVA

Analytics Engineering

Olist E-Commerce Analytics Pipeline

End-to-end analytics pipeline ingesting 9 Brazilian e-commerce CSVs (~1.5M rows) into Snowflake, transformed with dbt Core, and surfaced through 3 Looker Studio dashboards.

Developed 3 Looker Studio dashboards surfacing critical business KPIs, including $13.7M in platform revenue and a 91.9% on-time delivery rate across 74 product categories
Engineered a Python ingestion pipeline to bulk-load ~1.5M rows of raw transaction data across 9 CSV datasets into Snowflake using snowflake-connector-python and Pandas write_pandas
Modeled the data warehouse using a structured 3-layer Medallion Architecture (Raw, Staging, Marts) by building 8 dbt Core staging models and 3 data marts focused on seller performance segmentation and delivery logistics
Implemented 15 dbt data quality tests covering primary key constraints and engineered custom schema macros to standardize environment and naming architecture

Python Snowflake dbt Core Looker Studio SQL

GitHub ↗

Data Mining

Chicago Crime Data Engineering & Mining Pipeline

Large-scale preprocessing and analysis of 750K+ Chicago crime records with Tableau dashboards and machine learning models for pattern detection.

Transformed 750K+ raw Chicago crime records into analytics-ready datasets using Python and Pandas, resolving missing values, type conversions, and structural inconsistencies across a large-scale public safety dataset
Designed 3 Tableau dashboards (executive overview, time/arrest insights, geographic hotspot analysis) visualizing patterns across 262K+ incidents for operational decision-support
Developed predictive analytical models including hierarchical clustering and Decision Tree classification achieving 88% accuracy for arrest outcome prediction, validated with 90% sub-sample stability testing

Python Pandas Tableau SAS Enterprise Miner Hierarchical Clustering