Research Data Scientist
New York University Abu Dhabi
Total years of experience :16 years, 7 Months
Working on various top-notch research projects with several departments in the university in collaboration/support.
Scaling and executing the heavy computing requirements on the DALMA (NYUAD Super Computer), HPC environment.
Providing the extended support over the lifecycle of a research project by embedding a data science in research requirements. Design and implement a data analysis pipeline for many stages of research project, and/or develop a prototype of research focused software tool. Specifically, helping with the following:
• Writing reproducible, version-controlled code
• Data organization and cleaning
• Model estimation and post-estimation
• Visualization of raw data and model output
• Interpretation of results
• Writing methods and results sections of papers
• Responding to peer-reviews of our analyses
• Developing tool prototypes in R / Python
Advanced Algorithms Design and implementation.
Parallelization and optimizing of code.
State of Art advanced Model implementation like Image Recognition, Social Network Analysis, Recommendation engine, Speech and Text mining using Deep learning frameworks.
Leading the Data science and Data Engineering team for development of real time Analytics in the organisation from scratch with hybrid computing (cloud AWS and in-house), starting from infrastructure setup, data science tools assessment and team build-up.
•Leading and supporting for the legacy applications migration to new big data environment, from impact analysis, source to TDM mapping, ETL development and testing.
•Migrating the Enterprise data mining models from SAS to Big Data Environment.
•Created the new predictive models for churns, repeated customer prediction, fraud detection, scoring, and recommendation models (including the deep learning like NN, CNN, RNN, and HNN).
•Created the ETL framework in Hadoop to load the sources in the Telecom Data Model and built the various business marts.
•Real time data processing using the Spark Streaming for various Analytics
•Perform quantitative analysis of product sales trends to recommend pricing decisions.
•Design Thinking Hackathon Winner in Maxis for 2018 edition.
•Built the Query Bot using NLP and Real Time Recommendation engine using the knowledge graph.
•Developed the various useful models like Area of Interest, Collaborative filtering, Clustering, Speech to text & text to speech for customer service incident categorisation, Cell Tower Revenue attribution.
Developed SAS predictive models to Client for the effective product sale.
Developed SAS risk models for loans and AML & fraud detection for Italian banks.
Analyse large datasets to provide strategic direction to the company.
Load the data in to the Hadoop system for Batch processing using MapReduce.
Real time sensor data will be processed using the Spark Streaming for air quality prediction using Spark MLlib.
Perform quantitative analysis of product sales trends to recommend pricing decisions.
Conduct cost and benefits analysis on new ideas.
Scrutinize and track customer behaviour to identify trends and unmet needs.
Develop statistical models to forecast inventory and procurement cycles.
Assist in developing internal tools for data analysis.
Working on Smart City Project for Air Quality Prediction and for various applications
Design of new Interface System for the Product Migration to New Core Banking Product Temenos T24.
Involved in the legacy application data migration design from STAR to T24 using ETL.
Point of contact for parameter configuration for T24 and Legacy applications entity transformations via Application-ESB to T24.
Build POC real time analytics for Customer 360 views using Spark in Hadoop Ecosystems.
Migration data quality check and data management using Informatica IDQ and Profiling.
Produce the migration reports by entity wise to analyse the data using the SAS Enterprise data miner.
Team leader for new data warehouse project for the Single customer view, Data profiling and migration data analysis.
Used R, SAS and Python for predicting the fraud detection of Cards, AML and credit defaulters List.
Used Tableau and Power BI for Data Visualisation and SQL server to generating various reports.
This project involves Support and enhancement of Critical warranty Analysis system for JD. Here we are using SAS as an ETL tool to load data in to the warranty warehouse. My role is here to do data analysis dealing with critical data issues and regular enhancements. And development of some new warranty systems for various reporting purposes to the business. Also Project has various Warranty Analysis applications, which are used by customers for various reporting purpose like creating metrics, legal, accounting and future forecast reports.
This project involved migration of critical modules of Sales and marketing reporting applications of a Pharmaceutical Client from MVS-COBOL and MVS-SAS to Informatica, Linux. My role has started from the estimation phases of the project and continued until the stabilization phase. I had the opportunity to design and develop most of the modules in various applications due to an unexpected resource crunch, which was widely appreciated by one and all after the successful completion of the project.
Data science research projects
Electrical and electronics engineering.
URL removed due to policy violation. Please contact support for further information.