SUMMARY

• Professional in the field of Data Science with 5+ years of experience in statistical analysis, data analytics, data modeling, and creation of custom algorithms.
• Analytically skilled professional with double masters (MBA and Master’s in business) with proven understanding of Business and using analytics to take decisions which help the Business.
• Application to the disciplines of machine learning and neural networks using a variety of systems and methods in training algorithms in different cloud platforms.
• More than 5 years of experience performing data transformations, data analysis and developing results for Business decisions using tools such as R, Tableau, Python and SAS
• Expert in creating interactive dashboards and reports using such as Tableau, R shiny and R
• Worked extensively with Advanced Advance Analysis Actions, created Calculations, Parameters, dynamic sets, groups, table calculations, LOD expressions and multiple table joins to create interactive dashboards in Tableau.
• Experience with Python Libraries like Numpy, Pandas, Matplotlib and Sci - kit learn
• Experienced in writing Python and R scripts to perform ad-hoc analysis and data manipulation.
• In depth understanding of statistics and machine learning.
• Built statistical models and predictive models in R and Python which helped Business solve critical issues and improve performance of success factors such as sales$, profit, customer retention, customer segmentation and selective promotions
• Industry experience includes predictive analytics in finance and marketing. Use of NLP and Computer Vision technologies.
• Familiarity with developing, deploying, and maintaining production models with scalability in mind.
• Experience with a variety of Natural Language Processing methods for information extraction, topic modeling, parsing, and relationship extraction.
• Worked on NLP with NLTK, Spacy, Gensim and other modules for application development for automated customer response.
• Utilized Docker to handle deployment on heterogeneous platforms such as Linux, Windows, and AWS.
• Scale analytics solutions to Big Data with Hadoop, Spark/PySpark, and other Big Data tools.
• Experience with knowledge databases and language ontologies.
• Quantitative training in probability, statistics and machine learning.
• Experience in the application of Neural Networks, Support Vector Machines (SVM), and Random Forest and other Machine Learning algorithms.
• Creative thinking and propose innovative ways to look at problems by using data mining approaches on the set of information available.
• Identify/create the appropriate algorithm to discover patterns, validate their findings using an experimental and iterative approach.
• Applied advanced statistical and predictive modeling techniques to build, maintain, and improve on multiple, real-time decision systems.
• Worked closely with product managers, service development managers, and product development team in productizing the algorithms developed.
• Experience in designing stunning visualizations using Tableau software and publishing and presenting dashboards, storyline on web and desktop platforms.
• Experience in working with relational databases (Teradata, Oracle) with advanced SQL programming skills.
• In-depth knowledge of statistical procedures that are applied in Supervised / Unsupervised problems.

TECHNICAL SKILLS

Programming: Python, R, SQL, Java, Unix, Hadoop, Spark, Hive, Oracle, MongoDB, GCP, Tableau

Machine Learning: Classification & Clustering learning methods, NLP, Ensemble methods, Neural Networks, Time Series Analysis, Feature Engineering, Optimization, Data Visualization, Statistics, EDA

Packages: Pandas, Numpy, Sklearn, Gensim, Spacy, NLTK, Keras, TensorFlow, PyTorch, Matplotlib, Seaborn, Regex, rpart, CARET, e1071, OpenCV, Forecast, ggplot2, Beautiful Soup

Other Skills: Problem Solving, Critical thinking, Innovative, Good Communication & Presentation skills

Version Control: GitHub, Git, SVN

Data Query: Google Big query, AWS, Airflow; HDFS, RDBMS, SQL, MongoDB, HBase, Cassandra and various SQL and NoSQL databases and data warehouses.

IDE: Jupyter Notebook, Intellij PyCharm, Spyder, Eclipse

PROFESSIONAL EXPERIENCE

Confidential, Nashville, Tennessee

Data Scientist - Consultant

Responsibilities:

:

• Deployed a multi-tiered text classification model to classify social media data, which helped our clients improve their customer service strategies. Used SVM and RNN methods for classification.
• Forecasting the Customer Headcount in Retail Stores: Developed a time series forecasting model to predict the Daily Customer headcount for 2200 Retail stores across the country using ARIMA Modelling, XGBOOST and Facebook Prophet in Python (Numpy, Pandas, Scikit-learn, matplotlib, fb prophet, xgbregressor) with an accuracy of 96%.
• Forecasting the Technician type based on the work in Retail Stores: Developed a time series forecasting model to predict the technician type required to do the jobs for 2200 stores across the country using ARIMA Modelling, XGBOOST and Facebook Prophet in Python (Numpy, Pandas, Scikit-learn, matplotlib, fb prophet, xgbregressor) with an accuracy of 84%.
• Development and Maintenance of Credit Card Application Models: Developed credit card application models that worked on 400k applications per month. Delinquency levels of the new portfolio decreased by 32%.
• Grand Openings: Developed a statistical model to analyze various kinds of promotions and their impact on sales when a new store is opened and devised a strategy to increase the sales for all the new stores.
• Experimental Design: Developed a statistical model to automate the selection of test and control stores at a market level for natural experiments.
• Brake Rotor Pricing: Designed and Analyzed multiple price variants to cope up with the Tariff increase in Brake Rotors - 7M$ increase in profit per year.
• Promotion Response: Designed various referral promos and analyzed the response of customers to promotional variants for a credit card online referral system using A/B testing., which increased the number of referrals by 40%.
• Digital Inspection: Worked on designing and analyzing the performance of vehicle inspections when carried out digitally, which increased the customer spend by 2M$.
• Grand Openings: Developed a statistical model to analyze various kinds of promotions and their impact on sales when a new store is opened and devised a strategy to increase the sales for all the new stores.
• TIMM: Designed and Analyzed the performance of statistical model which improved the sales and decreased the transfer costs, which generated a profit of 8M$.
• Improved the performance of Sales Personnel: Worked on strategies to improve the confidence of the sales personnel at the retail stores improving the recommended dollars and customer spend.
• Customer acquisition: Identified untapped customer segments to be targeted for Marketing campaigns. Designed and Analyzed the performance of the promotional strategy, which increased the profit by 25M$

Environment: Python (PyCharm, Jupyter Notebook), SQL, Google BigQuery, Airflow, Docker

Confidential, Austin, TX

Data Scientist

Responsibilities:

• Provided Configuration Management and Build support for more than 5 different applications, built and deployed to the production and lower environments.
• Implemented public segmentation using unsupervised machine learning algorithms by implementing k-means algorithm using Pyspark.
• Using Airflow to keep track of job statuses in repositories like MySQL and Postgre databases.
• Explored and Extracted data from source XML in HDFS, used ETL for preparing data for exploratory analysis using data munging.
• Handled importing data from various data sources, performed transformations using Hive, Map Reduce, and loaded data into HDFS
• Used R and python for Exploratory Data Analysis, A/B testing, HQL, VQL, Data Lake, AWS Redshift, oozie, PySpark, Enova test and Hypothesis test to compare and identify the effectiveness of Creative Campaigns.
• Computing A/B testing frameworks, clickstream and time spent databases using Airflow
• Created clusters to Control and test groups and conducted group campaigns using Text Analytics.
• Created positive and negative clusters from merchant’s transaction using Sentiment Analysis to test the authenticity of transactions and resolve any chargebacks.
• Analyzed and calculated the lifetime cost of everyone in the welfare system using 20 years of historical data.
• Developed Linux Shell scripts by using NZSQL/NZLOAD utilities to load data from flat files to Netezza database.
• Used Python, R, SQL to create Statistical algorithms involving Multivariate Regression, Linear Regression, Logistic Regression, PCA, Random forest models, Decision trees, Support Vector Machine for estimating the risks of welfare dependency.
• Identified and targeted welfare high-risk groups with Machine learning/deep learning algorithms.
• Conducted campaigns and run real-time trials to determine what works fast and track the impact of different initiatives.
• Developed Tableau visualizations and dashboards using Tableau Desktop.
• Used Graphical Entity-Relationship Diagramming to create new database design via easy to use, graphical interface.
• Created multiple custom SQL queries in Teradata SQL Workbench to prepare the right data sets for Tableau dashboards
• Perform analyses such as regression analysis, logistic regression, discriminant analysis, cluster analysis using SAS programming.

Environment: R 3.x, HDFS, C#, Hadoop 2.3, Pig, Hive, Linux, R-Studio, Tableau 10, SQL Server, Ms Excel, PySpark.

Confidential

Data Scientist

Responsibilities:

• Customer Attrition Model: Worked on developing a Customer Attrition Model using XGBOOST to predict the customer churn and on designing proactive and reactive retention campaigns, which increased the customer spend by 5M$ per month.
• Youngest employee to be a part of analytics strategies team responsible for Credit Cards collections.
• Engaged with multiple business teams & clients for projects on Segmentation, Business development, Customer acquisition & Customer churn by developing strategies and statistical models using R & SQL.
• Developed loss reduction strategies for credit cards portfolio - 6M$ savings by loss rates reduction & cost efficiency.
• Rule management using statistical models to score suspicious transactions- 1M$ loss savings per quarter.
• Customer Segmentation Model: Modified existing segmentation model to increase pre-qualified customer base for cross sell of bank’s products to credit card customers. Identified 300K additional customer base with a conversion rate of 45%.
• Statistical Models Monitoring: Monitored customer behavior, delinquency & attrition models for performance deterioration, population shift & feature wise stability compared to the development period.
• Decision Tree Model on Merchant Chargeback Frauds: Identified fraud merchant segment using chargeback data on point of sale (POS) terminals by classification tree model leading to fraud reduction of 0.5M$ per quarter.
• Identified high propensity customers to be targeted for marketing campaigns by analyzing transaction level data.
• Created visualizations and dashboards using shiny, tableau and R.

Environment: Python 3.3, Jupiter Notebook 3.0, Rstudio, Git 1.7, SQL Server 2008, Apache Spark

Confidential, Dayton, Ohio

Student Consultant

Responsibilities:

• Worked as a student consultant with Vocalink team to work on strategies to increase its customer base and visibility. The analysis included Identifying potential threats and providing recommendations to mitigate them.