A computer science engineer with 5.8 years experience in application
development, machine learning.
Fluent in Python and Java.
Enthusiastic about building innovative, intelligent data products.
• Leading technology front for internal analytics product, AMP.
Consult with stakeholders, design and develop vertical solutions
/ automate - fraud, acquisition business processes and deploy as
a use case on AMP product.
• Designed, Built a unique user dashboard view for all analytics
reports in place to reduce the time spent by business users in
navigating through multiple reports.
• Built a Fraud strategy developer assistant using flask,
celery, rabbitMQ, and SAS to pull data for a specific period of
time and generate rules using machine learning.
• Lead backend and data engineering for internal analytics
platform AMP. Lead, implemented product integrations with
Protegrity for data security, IBM ACM for fraud investigation
case filing.
• Worked as a consultant with stakeholders on credit, merchant
fraud detection analytics areas to innovate and revamp legacy
processes with automation and ML.
• Creating synthetic data using data mining and machine learning
algorithms and data lineage with pattern mining problems
• Architected and developed backend for a web-based machine
learning platform, developed machine learning, data analysis,
data visualization as reusable use cases with Python - Django,
Spark, Angular, Java - Spring in the technology stack
• Reduced the manual effort for TDM teams in masking sensitive
customer data to 40% by creating a sensitive data identification
model using Natural Language Processing combined with Machine
Learning
• Worked with large banking clients to develop machine learning
solutions to problems like credit risk, credit stage leveraging
open source technologies like caret in R, Scipy, Scikit-Learn in
Python
80%
Increase the campaign effectiveness by identifying significant characteristics that affect the success (such as, the deposit subscribed by the client) based on a handful of algorithms
Given an image of a dog, my algorithm will identify an estimate of the canine’s breed
Design an agent that can fly a quadcopter, and then trained it using reinforcement learning algorithms
Best describe the variation in the different types of customers that a wholesale distributor interacts with.
Built an optimal machine learning model to estimate the best selling price for a house in the Boston metropolitan area based on a statistical analysis of the historical data
Evaluate and optimize several different supervised learners to determine which algorithm will provide the highest donation yield while also reducing the total number of letters being sent to ask for donations