Senior Data Engineer

• Oct 2021 - Present

Business Intelligence Developer

• Jan 2019 - Sep 2021

• Validate all new data assets for KPI development, quality assessment and usage considerations (new vendors, sources and additions to existing deliverables). • Designed and developed dashboards in QlikSense by extracting data from sources like Oracle, Snowflake and QVDs. • Lead data quality initiatives, including strategic guidance on quality monitoring framework, integration of new source data and development/implementation of imputations to maintain accuracy and reliability of data sets. • Manage various secondary data vendors, including ongoing deliverable quality, ad hoc requests, budget tracking and contracting. • Liaise extensively across CIM, IT and analytics teams across the organization. Represent CIM on various analytics and insights core teams. • Develop and maintain SAP Business Objects reports to track brand health across multiple divisions used by leadership. • Develop and execute SQL script against the existing Qlik Sense apps to verify data consistency on a weekly basis. • Extensively created views and written complex SQL scripts in SQL Developer and Snowflake database used by various reporting systems.

Data Scientist

• Oct 2017 - Dec 2018

● Being the first technical employee in a startup, single handedly developed Supervised Machine Learning models (Ensemble Learning) on Python to predict underground water pipe failures yearly using geospatial data. ● Created proprietary features that helped model to achieve ~ 70% accuracy with 2% false positive rate for a utility client (where the best accuracy so far has been around 25%). ● Built the pipeline using Pandas and Arcpy library of Python 3 for data cleaning, validation, preprocess, QA, build model and in the end analytics on results (Recall and Precision). ● Optimized automation process in python that augmented processing time from 50 mins to 16 mins (68% optimization). ● Used publicly available data (soil, weather, land use and seismic data) to enrich dataset that produced better forecast. ● Gained experience in Azure Machine Learning Studio and DataRobot by building ML models to compare preliminary results . ● The ML model I built helped the company raise $1.4M investment in Round A

Student

• Sep 2015 - Aug 2017

Predictive Analyst Intern

• Sep 2016 - Dec 2016

- Continually updated knowledge of industry data sources that could be used to improve analysis. - Utilised analytical tools such as Microsoft Azure Studio and R Studio to track, report, and analysed marketing and sales information. - Consulted and performed ad-hoc, data-mined analysis solutions for brand teams, sales, and business development. - Designed, built and ran promotion response models providing insights and recommendations that optimised targeting and sampling for different customer segments. - Constructed customer segmentation model using predictive analytics to support brand strategy, including patient profile and other behavioural analysis. - Developed and presented statistical and data mining models that explain the utility of marketing and sales programs and help forecast future outcomes. - Developed predictive models using various algorithms to uncover actionable insights and business opportunities.

Business Intelligence Analyst

• Mar 2013 - May 2015

Began my professional career as a Data Quality Analyst at Accenture, India involved in Data Governance mechanism. Adhering to my roles and responsibilities I found my interest in tracking the data flow throughout the project and rectify the non-standard ways of handling data using metadata management methodologies. Unified the results of Data Quality reports with metadata to provide statistics of invalid data ingesting enterprise wide servers and data marts. Roles and Responsibilities: - Expertise in many Software Development Life Cycle (SDLC) implementations, performing process planning, documentation, functional and system design, implementation, unit, integration, regression testing, and system maintenance. - Experienced in writing and debugging complex SQL queries to perform end-to- end ETL validations and support Ad-hoc business requests. - Excellent experience in developing Stored Procedures, Triggers, Functions,Packages,Inner Joins & Outer Joins, views using TSQL/PLSQL. - Creating and oversight of data warehouse, data quality assessments and reporting, data modeling and integration, and data profiling. - Worked closely with Business Analyst and business users to identify source data, source validation rules, and process calculations; finalize the Granularity and Documented the Business Rules. - Co-ordinate all teams to centralize Meta-data management updates and follow the standard Naming Standards and Attributes Standards for DATA & ETL Jobs. - Import Metadata from various data sources like Teradata, Erwin, Microstrategy, Cognos to form end to end lineage in SQL server database. - Cleansed, extracted and analyzed business data on daily basis and prepared ad-hoc analytical reports using Excel and SQL - Experience of creating dashboards on share point to analyze daily data entry for data quality reports that helped development teams to improve logics in transformation code to reduce data discrepancies.