SUMMARY:

• Highly focused Data Science/Engineering professional with close to 8 years of experience out of which 4 years in putting mathematics and BigData to business use in the form of data collection, analysis, and interpretation.
• Able to play a key role in analyzing problems and come up with solutions using statistical and machine learning techniques.
• Engineered data for custom data solutions.
• Attention to details, as well as supervisory skills to lead and manage projects, as an individual or as part of a team.
• Design and Implemented Predictive models using different statistical and machine learning techniques to derive valuable business insights from diverse sources of data.
• Analyzed large dataset using methods including principle component analysis, random forest, K - NN, K-mean clustering etc.,
• Utilize various technologies such R, Knime, Python etc., to identify trends and relationship between different pieces of data
• Ability to work as data engineer in performing ETL tasks using Hive, Sql, PySpark, and R.
• Ability to design and schedule data and model pipelines.
• Design appropriate solutions using Tableau, excel and other frameworks to give life to data insights through colorful visualization.
• Hands on experience on Big data platforms (Hadoop, hive, pig, oozie, python, spark)
• Sound knowledge in analysis of functional issues.
• Thorough familiarity with the manufacturing, ecommerce and retail domain.

SKILLS PROFILE:

Knowledge Domains: Retail analytics, Mining, Manufacturing & consumersPlatform/Technologies Python, Java, Big Data Hadoop, Python Django, Flask, Bottle, Microsoft SQL Server 2000/2005/2008/2012 , Linux (Ubuntu 12.02 LTS), MongoDB

Packages: R, Shinny App(R), Python Web, PySpark, Hadoop, Hive, Pig, Spark, Knime, Rapid Miner(Basic), Tableau, D3 Charts, Microsoft PowerBI.

PROFESSIONAL EXPERIENCE:

Confidential, Phoenix, AZ

BigData Analytics Engineer

Responsibilities:

• Manipulating, cleansing & processing machine sensor data using Hive, Python and Pig in Bigdata environment.
• Collecting and analyzing data and identifying areas and methods for improvement.
• Perform statistical analysis on mining truck’s sensor data to recommend maintenance schedules to avoid production lag.
• Developed and implemented operator scorecard method to rate truck driver’s performance on daily basis.
• Develop statistical and machine learning models to identify and solve complex business issues.
• Design and Develop MapReduce codes using Python or Java to process complex data structures and transform them into model usable format.
• Develop automated workflow using Hive & Python and schedule them using Oozie in BigData Cluster.
• Generate 3D Model of mining sites to identify the critical truck route within the mine.
• Use Excel, R Shiny and D3 charts to visualize findings of the analysis to business users.
• Perform quality check and monitor existing statistical model’s performances.

Confidential

Environment: s: R, Python, Excel VBA, Tableau, Mongodb

Principal Analyst (Statistical Modeling)

Responsibilities:

• Processed the raw data and preformed Exploratory Data Analysis.
• Mapped online stores sales to offline stores using Geospatial Mapping technique with Python and Mongodb.
• Used web scrawling to generate economic indices value for all US city to correlate consumer buying power with stores demand.
• Design and Developed hybrid approach to estimate the local demand based on consumer behavior and past sales history. (Multiple Linear Regression, Multinomial Logistic Regression, Spectral Clustering).
• Responsible for leading team of four statistical analysts and managing the project.
• Visualized the findings using Tableau and presented them to the client.

Confidential

Environment: s: Apache Spark, Hadoop, Tableau, R, Knime

Principal Analyst (Statistical Modeling)

Responsibilities:

• Collected project related data from various industrial backgrounds.
• Preform Exploratory Data Analysis to understand the correlation between different data across industries.
• Designed and Developed algorithm to mine Frequent Buying Pattern of customers to provide cross sell and upsell recommendation.
• Designed and Developed algorithm to predict customer service experience and propensity to churn.
• Developed dashboard using Tableau to visualize the results of the algorithm.
• Documented the design and approach of the algorithm.
• Assist BigData Development to port the solution into product.
• Tested and validated the model performance
• Update the model based on its performance.

Confidential

Environment: Microsoft SQL server 2005, R, Excel VBA, Java.

Sr Product Analyst

Responsibilities:

• Understand existing virtual number allocation process.
• Collected and Processed historical virtual call logs and performed Exploratory Data Analysis.
• Identified and cluster business listing based on the popularity.
• Designed and Developed Machine Learning Model using Random Forest to identity business listing which would reach the minimum virtual call requirement.
• Tested and validated the results of the model.
• Deployed the model as R shiny application for business users.
• Worked with vendors to understand the format of their Rest API.
• Developed java application to automate allocation of virtual number to business using Rest API, which would update the virtual number’s vendors databased and Confidential database.

Confidential

Environment: Microsoft SQL server 2005, R Shiny App, Excel VBA.

Sr. Product Analyst

Responsibilities:

• Collected and processed customer data such as Package details, payments, complaints etc.
• Worked with customer relationship managers to understand Package details, payment schedules and complaint redressal system.
• Performed Exploratory Data Analysis on the processed customer data to identify the anomalies.
• Developed and Designed Statistical Model to predict customer service experience and probability to churn.
• Tested and validate model results with statistical approaches.
• Identified key factors which increased churn rate.
• Visualized and present the findings to Management
• Deployed algorithm as R shiny application for future use.

Confidential

Environment: Google BigQuery, Perl, Excel, Microsoft Sql Server.

Sr. Product Analyst

Responsibilities:

• Worked with sales and SEO team to understand the team’s requirement.
• Collected and Processed Keyword and Business listing data to identify the important keywords to be tracked.
• Formulated approach to identify current position of a particular in a city using web scrawling methods.
• Used Time Series techniques to forecast the near future search result position of a keyword.
• Worked with Perl Developer team to design web scrawling system and to deploy them in AWS EC2 Instances.
• Designed the Database Tables and Queries to process the raw data to transform it into a final format.
• Worked with developers in development of the Application.
• Tested and validated the results.
• Visualized the data using D3 charts.

Confidential

Environment: R, Rshiny, Microsoft Sql Server.

Sr. Product Analyst

Responsibilities:

• Collecting various users from the database.
• Processed the users comment with text mining approaches such as stop word and punctuation removal, stemming etc.,
• Created Term Document Matrix and Inverse Term Document Matrix from the process user comments.
• Development scoring method to score each keyword from the document.
• Design and Developed text classifier models using Naïve Bayes techniques to classify keywords.
• Validated the Models performance.
• Visualized the results using Rshiny app.
• Suggested the listings team with relevant business categories and subcategories.

Confidential

Consultant Business Development

Responsibilities:

• Organize all client related issues/items and proactively provide client follow up, status updates as directed by the Director.
• Manage non-strategic partner firms, respond to email and phone inquiries, furnish fact sheets, dashboards and business planning documents.
• Ensure effective and impactful weekly communication to sales force via Relationship Management email.
• Work closely with Corporate Marketing to design and execute pre-agreed strategies built around developing new business growth.
• Open business development dialogs with strategic customers. Particular interest is to build a few large strategic accounts.
• Interface with existing strategic customers to solidify mutual expectations of performance and growth.
• Writing up concise, value-based sales proposals.
• Replying to all customer enquiries in a timely and accurate manner
• Developing and maintaining a database of all contacts.

Confidential

Environment: Php, HTML, Css, MySql.

Jr. Web Programmer

Responsibilities:

• Co-developed a vibrant, secure website using interactive features and SEO best practices to optimize traffic, page views and the user experience (UX).
• Helping the senior programmers in preparing the basic layout of a site in the building process.
• Moving sites from one domain to another for better performance.
• Constantly working towards reducing Site Opening Time (SOT)
• Reporting daily to the Senior Web Programmer