One Concern is a Data & Insights Risk Analytics Tech startup which brings disaster science with Machine Learning for better decision making. It quantifies Resilience from catastrophic perils, extreme weather & climate change into a Resiliency score and empowers business to measure, mitigate & transfer risk. As part of Research & Solutions team (reporting to CSO), we work with external clients (Insurance, Banking, Financial services, CRE, Asset management), Engineering, Go to Market & Sales team to build POC’s for clients and productize/scale data science solutions ● Evaluate hazard, exposure ML & Network models for various disasters: flood, hurricane, seismic & lifelines (highways, airports, ports, bridges, power & community) ● Proprietary vulnerability models predict downtime, recovery time, damage ratio in disaster events with 2035/2050 climate scenarios (RCP 4.5/8.5, SSP 245/585). Calculate Resilience score/grade and Business Interruption score of properties – delivered with API. ● DNA (Data & Analytics) product: Develop Exceedance probability & Downtime statistics pipeline (production code) across multiple hazards, planning horizons, return periods, build wireframe & scale Resilience metrics with Engg team for 20M properties in US/Japan ● Develop Resilience Adjusted Valuation & Financial Loss model pipeline (production code) using Discounted Cash Flow & Monte Carlo simulation, build wireframe. It quantifies a property’s resilience to climate risk/extreme events, pricing it into an asset’s appraisal. ● Develop model quantifying supply chain risk for Business Interruption (BI) using Graph networks and power simulation network model. ● Mentor & train fellow data scientists, new hires/interns; do code review (Github). Support pre-sales/post-sales efforts for clients Software : Python, Snowflake, Snowpark, GCP, Postgres SQL, Argo workflow

Duke Energy Corporation | Mar 2019 - Nov 2021

Data Scientist

Duke energy : one of the largest energy holding company in US; includes Piedmont natural gas (PNG), renewable energy assets. Part of Data Science Solutions team; I led various projects in electric and natural gas business verticals. Operations: Project Lead: Customer Analytics model for Disconnect Non-Pay work orders at PNG ● Develop Time series Forecasting models (LSTM, CNN1D, SARIMA) to predict weekly/daily generation of DNP orders, build framework for DNP customer journey ● Provide technical guidance, mentor junior data scientists for water heater failure prediction & sales conversion ● Develop Risk based Propensity model to predict/rank customers based on likelihood of delinquency. Financial impact: ~ $5.1 MM/yr Est. Marketing: Project Lead: Energy Efficiency program - Azure Databricks ● Develop Gaussian mixture model to find right target cluster; rank commercial properties to sell EE programs (Lighting, HVAC etc.) in non-native territories. Managed & coached two data scientists in this project. Financial impact : $8-10MM (2021) ● Address normalization: Azure maps geospatial API, Data imputation algorithms: MICE, KNN, Soft impute Grid Analytics : Customer Mapping Engine – iGrid ● iGrid utility platform – digitally driven energy ecosystem. Algorithm layer – CME analytics, CLIE Powerflow, Image analytics ● Develop & improve Meter to Phase algorithm (Accuracy: 96% - K-Means, Fast Fourier Transform) & Meter to Transformer algorithm (Accuracy: 91% - Geospatial clustering HDBSCAN) with SCADA/AMI edge data to predict & fix inaccuracies in GIS database Renewable Energy Analytics: AI/ML in Asset health monitoring & Risk management (using NLP) ● Nuclear: Condition based maintenance- Failure modes, Remaining life prediction for pumps/motors using work order documents. ● Entity Recognition, Information extraction with Elastic Search engine, AWS Textract, Text summarization: Seq2Seq model

Great Learning | Jul 2020 - Mar 2021

Mentor

Mentor for Great Learning EdTech startup (partnership with UT Austin); teach Post Graduate AI/ML program for a cohort of 20 experienced working professionals who want to up skill in the field of AI/ML : https:// www.mygreatlearning.com/us/

Brighthouse Financial | Jun 2017 - Jan 2019

Data Scientist II

Brighthouse Financial (former MetLife division) provides Annuity & Life insurance products. As part of centralized Data Science team, we worked with different business clients – Marketing, Distribution, Product, Risk, Underwriting, HR to provide end to end delivery of Machine Learning solutions. Marketing: Third Party Distribution Propensity Model ● Built Propensity model combining various data sources to score Financial Advisors most likely to sell Flex/Shield annuity product ● Used Logistic regression, Lasso, Random forest etc, combine seven models in 3 layers (stacked ensemble model) - Face to Face, Active, Inactive advisors and Product models. Measure success of email campaigns, used for lead generation ● Impact: 60MM in incremental quarterly sales revenue, score model quarterly with new data ● Built Classification models (SVM, Naive Bayes, GBM) to score Advisors for Financial firms : Wells Fargo, etc Product: Guaranteed Minimum Income Benefit (GMIB) annuity utilization & withdrawals ● Analyzed how GMIB has been utilized by consumers based on demographics, geography; examine withdrawal rates & surrenders ● Build Survival (cox ph) model to predict customer churn (policy surrenders) & find statistically significant drivers of policy lapse SAP Cloud - Big Data Services(BDS), Interim Big Data Admin ● Provided leadership and led the migration of ML models to SAP cloud with architects. Deployment of Propensity models to dev/prod cluster in SAP Big Data Services; automate production models (Python), built ML & ETL data pipeline (PySpark) & onboard team to SAP Cloud ● Transition to cloud helped BHF exit current service agreements with MetLife, hence cost savings ~ $10MM Distribution: Wholesaler Effectiveness Analysis ● Collaboration with experts from Univ of Missouri to (a) find optimal number of wholesalers (b) territory alignment (c) design wholesaler incentive plan.

R+L Carriers | Mar 2013 - Jun 2017

Data Scientist

R+L Carriers is a Global Transportation and Logistics Company serving North America. As a Decision Expert, I used Predictive Analytics and Machine Learning algorithms to derive meaningful insights. Sales: Project - Forecasting ● Built Time Series Forecasting models (Holt Winter, ETS, ARIMA) using VBA, R to predict various metrics- revenue, shipment, etc ● Automated models with SQL and R; Data Visualization with Tableau ● Recommended to business; Reduced Forecasting time to < 1 hour, reducing man-hours and leading up to $800K annual savings Operations: Project - Truck Terminal Efficiency and Optimization ● Built a business framework, Identified factors and defined metrics/KPIs affecting the terminal capacity, performance & potential growth rate of LTL industry. Methods– Clustering (K-means), Customer segmentation, Random Forest, SVM. Used Shiny to build a visualization tool ● Managed and mentored two employees and identified potential areas to increase efficiency thus saving thousands of dollars/month

University of Florida | Aug 2012 - Dec 2012

Business Case Design

Business Case Design for the coursework ‘Entrepreneurship for Engineers’ 1) Case study on marketability of heated clothing. Analysis included secondary research of apparel industry, competitive analysis (SWOT, PEST) and market opportunity sizing. 2) Delivered results based on financial projections and modeling. MS Excel, MS Power Point were widely used for presentations, reports.

University of Florida | Aug 2011 - Dec 2012

Graduate student

Specialized in the area of Statistical Data Analysis, Optimization and Design of Experiments, electronic materials, electrical and optical characterization methods, thin film deposition and Entrepreneurship

Helmholtz-Zentrum Berlin | May 2012 - Aug 2012

Intern

Study and Analysis of Hydrogen evolution reaction as future Renewable Energy source 1) Deposited MoS2 and WS2 thin films undoped and doped with Ni on Ti and Si/SiO2 by reactive Magnetron Sputtering (PVD) at different power rates, temperature, annealing conditions. 2) Cyclic Voltammetry and Potentiostatic measurements on these thin films prepared at different parameters (power etc.) in H2SO4 electrolyte 3) Data acquisition, Analyses of electrochemistry curves by IGOR Pro software to understand the most effective material for hydrogen evolution reaction

University of Florida | Jan 2012 - Apr 2012

Graduate Research Project on Design of Experiments(DoE) and Statistical Data Analysis

1) Designed a Randomized Block experiment with Two Factors Two Levels. Metric - conductivity of copper film, analyzed effects of Single Factors and their interactions. 2) Techniques used - Hypothesis Testing, Blocking, ANOVA, Regression, residual analysis

University of Florida | Jan 2012 - Apr 2012

Research Assistant

Fabrication of an AC Thin Film Electroluminescent device (PEN/SiO2/ITO/ BTO/ZnS: ErF3/BTO/Al) which will be applied in Phototherapy Bandage project. A bandage that continuously bathes a wound in low level infrared light has been shown to speed wound healing. • Deposited SiO2 thin film on PEN by E-beam evaporation, Magnetron & RF sputtering (PVD) of oxide layer (ITO, BTO) on the thin film • Optimized process parameters (pressure, process time) to get desired thickness and conductivity (using Profilometer / Four point probe)

Anand Automotive - Mando Corporation Korea | Jul 2010 - Jul 2011

Quality Engineer - Supply Quality Assurance

Anand Automotives in collaboration with Mando corporation Korea manufactures state-of-the-art brake systems. Meeting all Hydraulic Brake requirements of Hyundai Motors, it supplies automotive parts to Ford, Renault and General Motors. As part of my work with the Quality Assurance division, I ensured that quality of products supplied by multiple suppliers is met and certified internally before subsequent manufacturing, assembly and delivery to Hyundai and other companies. 1) Conducted Statistical Analysis (pareto) of rejection levels of various parts, managed reports, took actions to reduce rejections. Pattern modification of brake castings of a Ford model reduced rejections from 35% to 8%; leading to savings of $50K 2) Audited suppliers using Quality control methodologies like 5S, Process Control plan, Failure Mode and Effects Analysis, Poka Yoke, PPAP, Statistical Process Control etc. 3) Undertook training for lean manufacturing and six sigma and implemented its principles in the machining lines 4) Identified and improved process conditions in the Machining lines at the shop floor to reduce downtime and implemented Total Productive Maintenance (TPM) principles, thus making work flow more efficient 5) Analysed and solved technical issues by working in cross functional teams across suppliers and experts to improve quality of products.

Ohio University | May 2009 - Jul 2009

Research Intern

Analysis and Temperature measurement of Quantum Dots(QDs) on AlGaN thin film 1) Data Analyses of various images and time, emission spectra obtained from Raman Imaging using Near Field Scanning Optical Microscope 2) Qualitative models were built with GRAMS software. Calculation of temperature measurement algorithm, Peak fitting operations done to find out the temperature change of the Quantum Dots

Indian Institute of Science | Nov 2008 - Jan 2009

Research Intern

Analysis and Study of temperature dependent properties of a nano composite thin film on a Silicon substrate 1) Synthesis of ODT capped gold nanoparticles in PMMA solution done on a silicon substrate and characterized by UV-Visible spectrometer 2) Ellipsometric Data Analysis on this thin film to find out its thickness, volume fraction of Au in PMMA and refractive index

Indian Institute of Technology, Madras | May 2008 - Jul 2008

Research Intern

Memory Alloy(SMA) wire 1) Collected load and displacement data of a Shape Memory Alloy (NiTi) wire subjected to different cyclic loading and unloading experiments at different strain rates in the wire testing equipment to evaluate its suitability as a damping material. 2) Constructed different Data Charts and compared various stress and strain curves. Extensive Data Analyses was conducted using MS Excel. 3) “Effects of cycling on the pseudoelastic properties of CuAlMnNi and TiNi based pseudoelastic alloys”, published in the International Journal of Structural Changes in Solids, Volume 1. No.1 December 2009, page 171-185

Indian Oil Corporation Limited | Dec 2007 - Jan 2008

Process Engineering Intern

1) Worked with various Non-Destructive Evaluation techniques like Thermography, Ultrasonic testing, etc. in Oil industry and welding methods 2) Gained experience in the functioning of the refining industry from import of crude oil to various treatments, fractional distillation and refining to final packing. Inspection of a Hydrogen storage bullet was done using Ultrasonic and Dye Penetrant test

My Education

Take a look at my formal education

Masters of Science, Materials Science and EngineeringUniversity of Florida | 2012

Bachelor of Technology, Metallurgical and Materials EngineeringNational Institute of Technology, Trichy | 2010

About Me

Experience of 10+ years, problem solver, storyteller, end-to-end solution provider in AI/Data Science & Analytics, worked in startup and Fortune 150 industries – Software, Energy/Utilities, Financial Services, Insurance, Logistics, Automotive

Create Your Data Portfolio for Free