Shabbir Anaswala

Data Scientist

FIGMD•  November 2018 - Present

• Created multiple scripts under GCP Dataproc Cluster (Using Pyspark, Pandas, Sklearn, etc) and connected its data source with Data Studio for Graphical Visualization • Using selenium and webscraping extracted data from practices EMR and EHRs • Using Google App script Created DQC (Data Quality Check) Tool for Data Exploration. Tool can interact with Bigquery and gets processed data as per user input. • For text data created sentiment Analysis which helped team in segregating "Positive, Negative and Neutral " text • Developed Tableau Dashboard for different sections of Practices and interlinked them. Connected Data Source with Big Query • Developed a Utility in Python to access AWS Bucket Data (Using BOTO 3 Client) to find the number of times particular Keyword appearing in different Text sections. • Created KNN algorithm for predicting performance of Provider. • Multi_Class Text Classification algorithm for predicting un mapped elements across 8 sections of 32 Registries • Poc on Tableau Dashboard for different sections of Practices and interlinked them. • Connected Data Source with Bigquery Developed Automation report in Python during MIPS submission for different Registries

Data Analyst

Tata Consultancy Services•  December 2013 - November 2018

METADATA INGESTION with 5/3rd Bank  To create data and business lineages on banking application using IBM IGC tool and to perform data mining using Global ID tool.  Comparing, transforming, traversing and combining huge data using SQL and SAS for commercial credit card application.  Build model using machine learning techniques for commercial credit card data provided by 5/3rd bank using Python and maintained 93% accuracy rate.  Setting up data base connections, data refreshment and performing certain validations using SQL Queries in IGC tool.  Using Tableau created the status dashboard for lineages, Global ID ingestion