Yash Bajaj Email & Phone Number

New York City Metropolitan Area

New York City Metropolitan Area

● Cloud Lake Data Optimization :- Converted SQL queries to PySpark queries which reduced the query execution time from 6hrs to 30 minutes and saved compute cost on CDP by $40k annually.● Claims Audit Process :- Compressed the Audit file records to 10% using Classification and MultiLayer Perceptron algorithms which automated manual process and economized 320 human hours quarterly.

Outlier Detection Model - ● Used Docker Image to load the dependencies and created a JSON file to create a dictionary of features to automate data wrangling and data cleaning.● Applied AutoEncoders, Isolation Forest, Local Outlier Factor and One Class SVM using PYOD to check new quotes and compare with historic business for building the Pricing model .● Took advantage of H2O AutoML to generate feature importance and SHAP Outlier Detection plots and tSNE’s dimension reduction capabilities to visualize the train and test set outliers.● Used the top 3 features to analyze the output and highlighted underwriting of policies for new users which helped saving $300k in a US state which was under loss.

Champaign, Illinois, United States

● Identified issues with Accessibility on ACE editor to make it more accessible for people who are visually impaired so that they can code in any programming language and applied ARIA tags on respective components.● Used AInspector to generate reports on accessibility of the National Centre for Supercomputing Applications website based on WCAG guidelines.

Maharashtra, India

Mumbai, Maharashtra, India

● Developed a Distributed Employee Management System using NetBeans as a front-end and Oracle SQL to store the data in the back-end● Written efficient Java code and SQL queries to achieve the desired result of distributed concurrency● Designed the distributed database to achieve Replication and Fragmentation to store data

Masters In, Statistics Analytics

Bachelor Of Engineering, Computer Engineering