Machine Learning Data Analyst

KARISHMA KAMBLE

Open to Relocate • Chicago, IL • ******************@*****.*** • 312-***-**** • LinkedIn • GitHub

EDUCATION

UNIVERSITY OF ILLINOIS CHICAGO Chicago, IL

Master of Science in Business Analytics, GPA:3.78 Dec 2024

●Relevant Coursework: Data Mining, Machine Learning, Database Management (DBMS), Big Data Analytics, Data Visualization

INSTITUTE OF CHEMICAL TECHNOLOGY Mumbai, IN

Bachelor’s in Chemical Technology May 2018

TECHNICAL SKILLS

Programming: Python, SQL, R

Data Processing: Pandas, NumPy, SciPy, PySpark, Data Wrangling, Feature Engineering

Machine Learning & AI: Scikit-learn, TensorFlow, PyTorch, NLP, LLMs, Predictive Analytics, Time Series Forecasting

Big Data & ETL: Spark, Hadoop, MapReduce, AWS Glue, Data Pipelines, Governance & Compliance

Data Visualization: Tableau, Power BI, Looker, Excel (VBA, Pivot Tables), Alteryx

Cloud & Databases: AWS (S3, EC2, Lambda, RDS, Redshift), Snowflake, MySQL, SQL Server, PostgreSQL

Project Management: JIRA, Confluence, MS Project, Agile, Stakeholder Communication

PROFESSIONAL EXPERIENCE

KPMG India

Data Analyst Aug 2022 – Jul 2023

●Developed data governance frameworks that ensured compliance with KPMG’s risk and audit policies, reducing regulatory audit discrepancies by 30% and improving data accuracy across 500+ audit reports annually.

●Conducted exploratory data analysis (EDA) using Python (Pandas, NumPy) to identify fraud patterns, leading to a 25% improvement in risk detection efficiency and a 40% reduction in manual audit reviews.

●Built AWS-based data pipelines (S3, Redshift, AWS Glue) to centralize and automate audit data processing, reducing data retrieval time from 12 hours to 3 hours for audit teams handling terabytes of financial data.

●Designed risk assessment models using SQL, improving anomaly detection and enabling auditors to proactively identify 60% more high-risk transactions before regulatory reviews.

●Created Power BI dashboards to automate financial audit reporting, eliminating 20+ manual hours per week and accelerating decision-making for 15+ senior auditors and compliance officers.

●Standardized ETL workflows to integrate data from 7+ ERP systems, ensuring 98% accuracy in financial reporting for audit engagements.

Adani Group India

Data Analyst Mar 2020 – Jul 2022

●Automated SCADA data extraction and transformation using Python and PySpark, reducing manual logging efforts by 70%, saving 25+ engineer hours per week, and ensuring real-time energy monitoring across 10+ renewable power plants.

●Developed predictive maintenance models (Scikit-learn) for 500+ wind turbines and solar panels, reducing unexpected failures by 35%, cutting maintenance costs by $1.2M annually, and improving asset uptime by 20%.

●Built Power BI dashboards to track key energy performance indicators (KPIs), improving energy output forecasting accuracy by 15%, leading to an annual energy generation increase of 50 MW.

●Strengthened data security by implementing AWS KMS-based encryption, reducing potential security risks by 40%, ensuring full compliance with energy data regulations.

●Optimized SQL-based data warehousing, improving query performance by 45% and reducing report generation time from 2 hours to 30 minutes for operations managers across 5 energy sites.

●Conducted EDA on operational inefficiencies, leading to a 10% improvement in energy output and a 15% reduction in energy wastage, optimizing overall power distribution.

Trigent Software Pvt. Ltd. India

Data Analyst Feb 2019 – Mar 2020

●Optimized SQL-based ETL workflows, increasing data processing efficiency by 50%, reducing query response time from 5 minutes to under 1 minute, supporting real-time analytics for 20+ clients.

●Automated SharePoint-based workflows, reducing data retrieval time by 60% and cutting manual documentation hours by 15+ hours per week.

●Developed Python-based automation scripts, reducing data preparation time by 40% and enabling teams to generate daily reports in under 5 minutes.

●Built Tableau dashboards for real-time tracking of IT service performance, decreasing incident resolution time by 35% and improving resource utilization efficiency by 25%.

●Partnered with development teams to implement custom data analytics solutions, improving data accessibility for 10+ enterprise clients and enhancing internal reporting accuracy by 30%.

Data Analyst Intern Aug 2018 – Jan 2019

●Developed SQL queries to extract and validate 1M+ records from multiple enterprise systems, ensuring 99% data accuracy in IT service monitoring.

●Automated data preprocessing using Python, reducing data ingestion time by 50%, allowing faster updates to analytical dashboards.

●Designed dashboard visualizations for real-time IT service tracking, leading to a 20% improvement in service issue resolution rates.

PROJECTS

Graduate Capstone Project – LLM based AI Agent Chicago

CCC Intelligent Solutions Aug 2024 – Dec 2024

●Developed an AI-powered vehicle valuation agent using Lang Chain, Lang Graph, and LLM frameworks, automating real-time market data retrieval for accurate pricing insights.

●Designed a modular and scalable AI architecture, improving system adaptability and reducing query processing time from 10 seconds to under 3 seconds.

●Collaborated with CCC’s technical team, presenting AI-driven optimizations to senior stakeholders, enhancing valuation accuracy and decision-making for insurance and automotive clients.

CERTIFICATIONS

AWS Academy Data Engineering (AWS Academy Graduate) Apr 2024

Contact this candidate