SUMMARY:

• Have 7 years of cumulative experience in solving problems related to pharma and Confidential domain and programming.
• Have 6 Years of Analytics Industry experience
• Have used data science - data acquisition from a multitude of sources, data validation, data visualization (created dashboards for visual analytics), implemented linear, logistic regression, clustering, machine learning algorithms and association rule mining - to spot and exploit new business opportunities, optimize business processes, and create solutions that help in decision making process.
• Expertise in data analysis, data modelling and presenting findings using R and visualization tool like PowerBI
• Expertise in packages like data. table, dplyr, tidyr, caret, mlr etc. to perform data analysis task.
• Strong experience working with R, R-Studio, SQLServer2008, R-Studio, Alteryx, PowerBI, Excel, VBA, Python.
• Worked on powerBI, Tableau to create dashboards and visualizations.
• Experienced in developing supervised Machine learning models like regression models, classification models like logistic regression, decision tree, random forest, SVM, KNN, LDA, QDA, Xgboost
• Experienced in developing unsupervised models like K-means, hierarchical clustering, PCA.
• Experienced in querying the relational database using SQL queries.
• Expertise in automating the repetitive work to improve upon operational efficiency.
• Experienced in working on large structured and unstructured data set.
• Have worked on data sources like Nielsen, IMS, Dunnhumby, Transactional data set, financial data.
• Ability to translate complex business problems into structured analytics and make recommendation.
• Experienced in developing automation routines to keep analytics systems regularly updated and refreshed with minimal manual intervention
• Exposure on big data technologies like mongodb, Hadoop, hive
• Develop and conduct testing of modules to ensure quality assurance of delivery.
• Expertise in integrating data from multiple sources and perform data transformation making it ready for analysis and modelling.
• Expertise in performing univariate, bi-variate and exploratory data analysis.
• Experienced in documenting system requirements including data flows and procedures
• Ability to understand and document standard operating procedures
• Excellent analytical, problem-solving, and root cause determination skills
• Highly competent at researching, visualizing and analyzing raw data to provide actionable insights and recommendations for meeting organizational objective.

WORK EXPERIENCE:

Confidential, Burlington, VT

Data Scientist

Responsibilities:

• Interacted with different stake holder for data understanding and acquisition, performed data integration and transformation.
• Conceptualized, developed analysis and provided insights, recommendation and implementation strategy for stores to realize 10% incremental growth.
• Used clustering algorithms like K-Means and Hierarchical clustering to identify similar behaving stores and then benchmarked stores with identified clusters to quantify additional growth opportunity.
• Utilized association rule mining, market basket analysis to propose bundled promotions and product placement enabling an estimated increase of 2% in the average basket size.
• Performed Assortment analysis to identify de-listing and listing of SKUs in store.
• Created dashboard using PowerBI and tableau facilitating market, cluster and store level review of sales, promotional activity, basket size, and assortment of SKUs. Automated monthly store scorecards generation that communicates store performance and actionable insights to store owners.
• Worked on high volume and velocity transactional data set.
• Designed scalable solution architecture catering the need of growing data volume.
• Delivered actionable insights and recommendations tailored as per business use and implementation.
• Wrote and optimized SQL queries to extract data from SQL database, coordinated with different stakeholder to improve the performance of database by indexing.
• Understanding of migrating the data to Hadoop clusters.
• Interacted with different business and technical stake holder to gather the data required to perform analysis.
• Performed data quality review, data integration and data transformation.
• Clustered various products based on different composition using K-Means and Hierarchical clustering.
• Used Principal Component Analysis to reduce data dimensionality.
• Used linear regression, logistic regression and machine learning algorithms to predict the value of variable influencing stability.
• Worked in liaison with subject matter experts to have model business relevant.
• Developed interactive dashboard for business stakeholder using Tableau.
• Presented the insights and findings to business stake holder.

Environment: R, SQL, Tableau, Python, Excel, PCA, Clustering, Supervised Learning

Confidential, Piscataway, NJ

Consultant Analytics

Responsibilities:

• Data extraction and understanding of Confidential data for multiple geography.
• SET-UP, implementation, execution and institutionalization of data processing process at global scale reducing man-hours by 50%.
• Analysis of State of business and Competitor’s performance for Confidential client. Study and standardization of business review decks across all countries (80+) where a top Confidential client has its presence.
• Extraction of data from databases and its manipulation for calculation of facts and KPI’s used for analysis.
• Automation of PPT generation for presentation purpose from calculated data using VBA.
• Lead the initiative to make process iteration free and to improve accuracy
• Created developer account with twitter to access the public data for our client.
• Performed sentiment analysis for promotional campaigns of pet food company to identify areas of improvement upon based on tweets.
• Identified Key customers following twitter handle and profiled consumers to have strategy for targeted promotions and offers.
• Used naïve Bayes classifier to classify the positive and negative tweets.
• Used SVM and Random Forest to classify tweets.

Environment: R, SQL, Excel, VBA, Machine learning

Confidential, New Brunswick, NJ

Senior Analyst

Responsibilities:

• Understanding of IMS data at physician level for Confidential .
• Provided actionable insights in the form of excel dashboard that helped in making business decisions and improve overall Sales Force Effectiveness.
• Segmentation of Territory to perform Pay-out performance analysis that determined the effectiveness of Incentive Plan.
• Sales Crediting and Quota Setting of medical representatives for Confidential that brought efficiency in budget planning of client.
• Designing contest plan and administering it to motivate the medical reps for aggressive marketing pitch and drive effort of achieving the organization objective
• Designed and created tool based on Excel VBA to automatically generate medical representative scorecards.
• Investigated market sizing, competitive analysis and positioning for new drug feasibility.
• Use Correlation analysis to identify relation between variables, patterns, outliers and causal factors.

Environment: R, SQL, Excel, VBA, Machine learning

Confidential, Austin, TX

Analyst Analytics

Responsibilities:

• Used R and python to perform exploratory data analysis, visualization and model building.
• Identified pattern in data and segmentation of credit card clients
• Done feature engineering and performed variable transformation to design better models
• Build Logistic, Random Forest, SVM and Xgboost model to predict the default status
• Evaluated model performance and selected best performing model.

Environment: R, Python, Excel, Tableau, Logistic, SVM, RF, Xgboost

Confidential

Analyst

Responsibilities:

• Designed and developed VBA based tool to bring in efficiency and accuracy to existing process.
• Gather & Review Customer Information Requirements for OLAP and building the data mart.
• Performed document analysis involving creation of Use Cases and Use Case narrations using Microsoft Visio, to present the efficiency of the gathered requirements.
• Calculated and analyzed claims data for provider incentive and supplemental benefit analysis using Microsoft Access and Oracle SQL.
• Analyzed business process workflows and assisted in the development of ETL procedures for mapping data from source to target systems.
• Worked with BTEQ to submit SQL statements, import and export data, and generate reports in Terra-data.
• Responsible for defining the key identifiers for each mapping/interface
• Responsible for defining the functional requirement documents for each source to target interface.
• Coordinated meetings with vendors to define requirements and system interaction agreement documentation between client and vendor system.
• Enterprise Metadata Library with any changes or updates.
• Document data quality and traceability documents for each source interface.
• Establish standards of procedures.
• Generate weekly and monthly asset inventory reports.
• Managed the project requirements, documents and use cases by IBM Rational RequisitePro.
• Assisted in building an Integrated LogicalDataDesign, propose physical database design for building the data mart.
• Document all data mapping and transformation processes in the Functional Design documents based on the business requirements.

Environment: SQL Server 2008R2/2005 Enterprise, SSRS, SSIS, Crystal Reports, Windows Enterprise Server 2000, DTS, SQL Profiler, and Query Analyzer.