data professional

NARAYANAN KRISHNAMURTHY

Coconut Creek FL, ******@*****.***, https://www.linkedin.com/in/NKrishnamurthy74

SKILLS: Portfolio - https://bit.ly/2yCFHUM Summary of Data work - https://bit.ly/2XUVsDe

* R (data.table, ggplot2, etc.), Python (Numpy, Pandas, NLP, etc.), Statistics, Matlab, SPSS

* Excel, PowerBI, Tableau, SSIS

* SQL (Teradata/Postgres/MS Sql Server/Sybase), NoSQL-MongoDB, Linux

* C, C++, C#, Embedded Systems, Parallel Programming

* Current Interests: Spark (Python Api), Ray/Dask, Shiny, etc.

Continuing Education: “Making Data-Driven Decisions by MIT IDSS” Schwarzman

College of Computing, Completed March 2025

Credential: https://www.mygreatlearning.com/certificate/KVYFRYEW

PROFESSIONAL EXPERIENCE

Mathematical Statistician MAR 2021 – till date

Internal Revenue Service, LB&I

Involved in different projects that entail data analytical work. I am a developer, facilitator and data product maintainer for different projects within product management of ADCCI.

Use SQL, R/Python and BI tools (Tableau & Power BI), and business objects for the following:

1) Candidate topic modeling. Topic categories identify different skillsets for specializations such as cross-border, transfer pricing, financial products etc. The topics can be utilized in ranking candidates, viz. revenue agents, economists and data scientists, for individual practice areas with specific needs

2) Natural Language Processing (NLP) of SEC 10K data. Different sections of 10K were parsed to show case NLP techniques: term frequency importance, key phrases with ranking, searching for specific terms, word clouds to highlight key risks. Sections 1a & 7a were used for risk identification and section 7 from management’s discussion analysis section were used to create a proof-of-concept search application using Microsoft Azure and Python NLP libraries.

3) Data product for workload, examinations and workforce to answer questions on workload inventory and exam history across different IRS locations. Corporate and partnership returns (11 million for tax year 2019) were pulled from the business master file and merged with closed cases along with HR payroll data to create this Tableau dashboard. Descriptive & prescriptive insights on number of returns, type of work, agent population across different locations, coverage ratio (revenue agents to returns), average yield ($/hr), history of entity’s filing etc. are presented in this interactive tool.

Data Science Analyst JUL 2020 – MAR 2021

Frontier Communications, FL

Contact Center Analytics - https://bit.ly/3Gs7c1m : Used R data.table library and Teradata SQL queries for analyzing, summarizing data from different sources, to deliver reports. Wrote Teradata SQL queries, to perform CRUD on tables that track customer calls. Customer Contact call records linked to customer accounts. Match percent for 2019-2020 with improvements were maintained as separate views.

1. Created tables, to analyze contact center call records avg 5 million per month with

total 160 million over 24 months

2. Created reproducible SQL Teradata code to link call records to customer accounts

3. Devised strategy to pick amongst multiple accounts

4. Tested the matching logic accuracy and devised ways to improve matching logic by identifying frequent callers

5. Code base transferred to IT for deployment via. Informatica

6.Used C# excel interoperability features to schedule daily forecast report & email to distribution list in Field Operations (wrote sql stored procedure, and modified C# automation project template to read excel report to update report, Microsoft task scheduler was used to automate emailing report on daily basis)

Software Engineer FEB 2019 – DEC 2019

Fabmatics - Magic leap, FL

LINUX PLC System

Manufacturing (Commissioning & production support): Along with 2 technicians, managed production of the AR version 1 glass handling system. The PLC and C++ system developed by Fabmatics; controlled and automated the lens manufacturing. Was the liaison between magic leap staff and German engineers, to sort out daily issues with manufacturing. Remote access to the system, & analysis of log files, via. terminal was used to correct errors in software, and/or errors due to the operator. System malfunction due to malfunction of sensors, due to changes in position or timing, and any other issues that arose with system or software were handled to facilitate production.

Data Science Analyst JUN 2018 - FEB 2019

Cognizant Software Technologies

Revenue protection - https://bit.ly/2A7wyE0, Florida Power & Light, Jupiter FL

R, Python, SPSS, SQL, Machine Learning, Issue Tracking

1. Wrote code and queries, to analyze customer usage data, and develop ML models for anomaly detection and time series classification.

2. Tsfresh time series (TS) features were extracted and dimension reduction techniques

and different ML classifiers (Random Forest, SVM, QDA & Neural Net) were used to classify anomalous time series.

3. Feature engineering: Significant features were obtained using CCA, PCA, TSNE & Baruta

methods.

4. Change point analysis was used to identify anomalous premises, and ggplot visualizations done for 2 million accounts.

5. Computations were implemented across threads in parallel to speed up computations using shared memory.

Data Science Analyst FEB 2016 - JUN 2018

ORAU DOE National Energy Technology Lab

Materials Discovery & Development - https://bit.ly/2zmgoGZ, Pittsburgh PA

R, Python, SPSS & Machine Learning

1. Different 9Cr Steel test data of in-house and those from Japan were analyzed to develop data analytic tools for rapid development of new alloys at NETL in collaboration with Case Western University.

2. Pairwise correlations were done as part of exploratory analysis. Variables of non-zero variance & frequent occurrences were used to predict strength, ductility, and other mechanical properties.

3. Multi-variate and stepwise regression were used to determine rank order of variables in explaining a mechanical property.

4. Random forest recursive partitioning technique was used to explore expanded composition space to predict property of new alloy from existing test data.

5. Different techniques i.e. ANOVA, and Tukey HSD tests on mean of samples, principle components, stochastic embedding (t-SNE), hierarchical and medoid, kNN clustering have been used to visualize different classes of alloys.

2007 - DEC 2009

University of Pittsburgh, Pittsburgh PA

* Designed and developed Lab VIEW based liquid reward system.

* Designed and developed a Wii based IR motion capture system.

* WiiMoCap - https://bit.ly/2X1fbhg

INTERNSHIPS JAN 2004 - DEC 2006

Bosch & University of Pittsburgh, Pittsburgh PA

* Bosch: CAN driver project: Designed and implemented a higher layer protocol viz. the driver and daemon on top of a Control Area Network (CAN). The daemon takes care of addressing, fragmentation and reassembly.

* Computer Science: Proposed a pub-sub architecture for emergency notification system using Linux socket programming on ARM PDA's, interconnected via. adhoc routing developed in-house.

* Information Science: MIMO Wireless system analysis: Studied MIMO aware MAC, for different PHY architecture, and identify mechanisms that would ultimately address QoS issues, service differentiation based on throughput and delay for Smart antenna based wireless LAN devices

Embedded Wireless Software Engineer JAN 1998 - JUL 2001

Indian Institute of Technology Startup, Chennai India

DSP C & ASSEMBLY - https://bit.ly/2M1Hw0A

1. Worked through multiple software lifecycles across DECT layers, from requirements, design, implementation and testing in C and Assembly language for ANALOG DEVICE’s DSP processors.

2. Projects Completed include 1) Auto ranging 2) Over the air FLASH programming 3) Memory management 4) Modified data link and network layers in the handset to handle dual voice and data connection in DECT wireless in local loop system.

Management Trainee - ITC Bhadrachalam, India JAN 1996 - MAY 1997

Recruited on graduation of BS in Mechanical Engineering, one of two selected in a class of 90. Did rotations in different engineering departments at the paper mill and involved with commissioning of new 21MW power plant in Sarapaka India.

EDUCATION

UNIVERSITY OF PITTSBURGH JAN 2010 - FEB 2016

Master of Science, Bioengineering

NIH Multimodal Imaging Fellow Award (2012-2013), RF simulation using threaded C code on

Linux and Matlab.

1. Designed and prototyped components used CAD (Solid works) and workshop for prototyping.

2. Model extraction from CAD models, and development of multiple anatomically detailed models and evaluation of MR coils simulations using full wave Maxwell's equations

3. Independent Transmit (Tx) & Receive (Rx) coil arrays are used to tackle (electric and magnetic) field in homogeneity that arise at ultra-high field MRI. An important part of my thesis work was bench marking of coil performance for efficient and safe use in-vivo.

4. The arrays were tested for reproducibility, reliability, and safe usage across multiple studies. EM/RF Finite Difference Time Domain simulations of the Tx and composite of five head models were used to optimize parameters, to obtain homogenize whole brain excitation with low RF absorption.

Thesis: https://bit.ly/3i7Ob71

Publication: https://doi.org/10.1371/journal.pone.0209663 - https://bit.ly/3c5EZgv

GEORGE WASHINGON UNIVERSITY SEP 2001 - MAY 2003

Master of Science, Computer Engineering

Teaching Fellow: Held weekly recitations and assisted professors with undergraduate and graduate ECE classes: Circuits Design, Signals and Systems, Digital and Analog Communication and Filter Design, Stochastic Processes, and Signal Processing.

CDAC Certificate in Computing – India JUL 1997 - JAN 1999 https://bit.ly/3doEbVm : Advanced C, Software Engineering, Object Oriented Programming, C++, Java and Business Computing.

REGIONAL ENGINEERING COLLEGE WARANGAL JAN 1992 - JAN 1996

Bachelor of Technology, Mechanical Engineering, Dean’s List 1992

PEER REVIEWED DATA SCIENCE WORK

1. KRISHNAMURTHY, N., MADDALI, S., HAWK, J. A. AND VYACHESLAV, R. N., “9CR STEEL VISUALIZATION AND PREDICTIVE MODELING”, COMPUTATIONAL-MATERIALS-SCIENCE; MARCH 2019, HTTPS://DOI.ORG/10.1016/J.COMMATSCI.2019.03.015

2. KRISHNAMURTHY, N., MADDALI, S., VERMA, A., BRUCKMAN, L., CARTER, J., FRENCH, R., VYACHESLAV, R., AND HAWK, J. A., “Technical Report: Data Analytics for Alloy Qualification”, https://www.osti.gov/biblio/1456238-data- analytics-alloy-qualification, DOI: 10.2172/1456238, 2018-03-20

3. ROMANOV, V. N., KRISHNAMURTHY, N., VERMA, A. K., BRUCKMAN, L. S., FRENCH, R. H., CARTER, J. L. W. AND HAWK, J. A., "MATERIALS DATA ANALYTICS FOR 9% CR FAMILY STEEL", STATISTICAL ANALYSIS AND DATA MINING JOURNAL, HTTPS://DOI.ORG/10.1002/SAM.11406, FEB 2019.

Contact this candidate