DIMPLE BAPNA
adh2ym@r.postjobfree.com GitHub LinkedIn Portfolio Seattle, WA 425-***-**** SUMMARY
Data Analyst with a growth mindset and a passion to dive deep into data to tackle ambiguity and tell compelling stories using quantitative analysis. Excellent communication skills and a hands-on practice of solving real-world problems to cater to customer needs and deliver business value.
EDUCATION
Northeastern University, Master of Science, Data Analytics Engineering GPA: 3.8 Aug 2019 - Jan 2021 Courses: Data Mining, Neural Nets and Deep Learning, Data Warehouse and Business Intelligence, Database Management & Design, Data Visualization, Probability & Statistics, Deterministic Operations Research, Statistical Methods in Engineering University of Mumbai, Bachelor of Engineering, Computer Engineering GPA: 3.8 Aug 2008 - Jun 2012 Relevant courses: Data Structures and Algorithms, Object Oriented Programming, Mathematics, AI EXPERIENCE
Data Scientist - Consultant Costco Wholesale, Seattle Jun 2020 - Aug 2020 Tech stack: Python, pandas, scikit-learn, matplotlib, seaborn, neural network (LSTM), Tableau
Implemented LSTM model to forecast demand of goods sold by Costco.com, reducing revenue loss by 20%
Developed comprehensive data presentations reporting forecasted demand at depot-level using Tableau dashboard
Leveraged data exploration on large data sets to identify limitations and recommended improvements in data quality Data Scientist - Consultant Tignis, Seattle Feb 2020 - Jun 2020 Tech stack: Python, pandas, scikit-learn, matplotlib, neural network, statistics
Implemented anomaly detection for real-time sensor data with neural networks (Feed forward) by utilizing historical data
Performed statistical modeling on sensor data for data manipulation and missing value treatment
Reduced the overall time taken for fault investigation by 60%, resulting in direct cost savings of more than $300k Senior Software Developer Duck Creek technologies, India Aug 2016 - Jun 2018 Tech stack: C#, SQL, Duckcreek tools
Led a team to create and manage an end to end billing system resulting in a 35% faster billing process
Collaborated with multiple teams to articulate a data driven strategy to improve billing platform; reducing customer attrition rate by 20% and enhancing customer experience.
Developed an automated payment records system compatible with 50+ banks, saving 160 man-hours per month Software Developer Accenture Services Pvt Ltd, India Feb 2013 - Jul 2016 Tech stack: C#, SQL
Automated medical billing application for incident analysis, increasing productivity of the healthcare system by 70%
Developed a single input application which eliminated manual interventions reducing engineering costs by over 60%
Delivered a tool to eliminate duplicates and highlight pending invoices saving $2M+ in interest penalties for the client DATA SCIENCE PROJECTS
Automated grocery list generator Apr 2020
Tech stack: R Shiny, Python, ML- Apriori
Developed and deployed R Shiny web app to break down recipe and generate grocery list
Extracted data using APIs and performed data transformation and data wrangling
Applied Apriori algorithm to generate 27,000 association rules and provided recommendation based on grocery list items Machine learning based SMS message filter Dec 2019 Tech stack: Python, Sklearn, NLP, Multinomial Naive Bayes algorithm
Processed dataset of raw SMS messages using data analysis and data wrangling and performing feature selection
Applied Natural Language Processing and Multinomial Naive Bayes machine learning algorithm to create a spam detection filter to screen out unwanted and abusive messages for a user
Used precision metric to validate the performance of the model. Achieved a precision of 99% on the test data Statistical analysis on healthcare dataset from Kaggle Dec 2019 Tech stack: R, Statistics
Performed numerical and analytical programming on Kaggle healthcare dataset to extract insights and attributes leading to heart strokes in humans using data mining and analytical techniques
Conducted various statistical tests including null hypothesis testing, z-test, t-test, Chi-square goodness-of-fit test Foodbank Inventory Management System Dec 2019
Tech Stack: RDBMS, SQL Relational Databases, Power BI
Created an end to end management and tracking system on transaction-based model for Food Bank inventory database
Implemented Relational Database Management System along with features such as views, table-level and column-level constraints, column-based encryption, stored procedures, triggers and generated PowerBI reports by SSMS integration TECHNICAL SKILLS
Programming Skills: Python (Pandas, NumPy, SciKit-learn, matplotlib, TensorFlow, Keras, PyTorch, Postgres), Java, C++ Machine Learning Algorithms : Linear Regression, Logistic Regression, Decision Trees and Random Forests, KNN classifier, K-Mean Clustering, SVM, Apriori, Neural Nets and Deep Learning Data Science / Analytics: R, SQL, Tableau, Statistics, SSIS, Talend Other Applications: Version Control Systems (Git, Bitbucket), GitHub, Jupyter Notebook, IntelliJ, JIRA, Confluence, Lingo