PROFESSIONAL SUMMARY:

• Data scientist with experience in data collection, data manipulation, visualization, building statistical and machine learning models.
• Participated in various phases including data collection, data mining, data cleaning, data visualization, developing models, improvising models and presenting results.
• Over 7+ years of experience in the field of data science, data analytics, data visualization, business intelligence and data mining.
• Excellent hands on experience in building time series models like ARMA , ARIMA for predictive analytics and forecasting.
• Proficient with statistical technique’s like linear regression , multiple regression and ANOVA .
• Experience in developing machine learning models using decision trees, deep learning, support vector machines, clustering, Bayesian networks and reinforcement learning.
• Experienced in SSIS for ETL processes to ensure implementation of event handlers, checkpoints and handlers.
• Experience working with RDBMS systems such as oracle and MySQL .
• Expertise in python, R and respective libraries.
• Experienced in Natural Language processing and its related concepts.
• Designed and developed dashboards in tableau .
• Certified supply chain professional from IIT Delhi.
• Hands on experience working a DBA, User Administration, maintenance using Oracle 10g and 11g.
• Analyzed slot machine data and user data in WEKA to provide a useful insight on slot machine complexity vs usability.

TECHNICAL SKILLS:

Primary Languages: Python, R

Database: MySQL, Microsoft SQL Server, Oracle DB

ETL Tool: SSIS

BI Tools: Tableau, Oracle BI

Data analysis tools: WEKA, MATLAB

Python/R libraries: Numpy, Scipy, Shiny, Pandas, SQLAlchemy, matplotlib, scikit - learn, TensorFlow, Scrapy, Seaborn, Basemap

ML and Statistical Algorithms: Decision trees, ANN, Deep learning, Bayesian networks, reinforcement learning, support vector machines, logistic regression, data mining methods and cluster analysis.

Other: Natural Language processing (NLP), Hidden Markov Models, Map Reduce, Data Structures and algorithms, git, Jupyter Notebook and MS Excel

PROFESSIONAL EXPERIENCE:

Confidential, Omaha, NE

Data Scientist

Responsibilities

• Build time series predictive models for solar and load forecast using geospatial and energy data.
• Applied Moran’s Index to spatial autocorrelation for a multi variate or multi-dimensional GIS data.
• Applied Hidden Markov Model in reinforcement learning and spatial pattern recognition.
• Test for stationarity of the data set by visualizing rolling statistics and applying Dickey-Fuller test using python statistical package stats models.
• Develop forecast models using statistical methods like Auto Regressive Integrated Moving Averages (ARIMA) and Auto-correlation function (ACF).
• Evaluated time series forecast models using statistical evaluation metrics like Mean absolute percentage error (MAPE) and Root Mean squared error (RMSE).
• Applied stochastic process to model observed time series data.
• Worked on many statistical methods like correlation (Pearson, Spearman), data distributions and descriptive statistics.
• Build linear regression models for predictions and used linear methods for statistical significance tests and correlations in R.
• Build machine learning model for market segmentation using k-means clustering analysis in python with a 95.5% accuracy.
• Build a predictive model to improve sales hit ratio using decision trees (ID3) using Weka.
• Predicted target variable on test data and created confusion matrices, AUROC curves.
• Worked on relational, graph and document stories.
• In-depth knowledge in SQL databases, tables, stored procedures, triggers, views, user defined data types and functions.
• Experience with querying relationship using graph database neo4j.
• Design and visualize interactive results using tableau to publish dashboards.

Confidential, Las Vegas, NV

Data Scientist

Responsibilities

• Define the problem, evaluate available data to develop and implement descriptive, predictive and prescriptive solutions using statistical and machine learning models.
• Build hypothesis and strategically participate in accurate data collection from various sources to support analytical needs.
• Summarize, aggregate and group data using Python Pandas to find the data structure and data distributions.
• Decide sampling using Numpy and remove features with low variance using scikit-learn
• Visualize data using matplotlib, seaborn, ggplot and geoplotlib to generate different graph types like attribute histograms, pairwise scatter plots, bubble charts and combination plots.
• Worked on text parsing, NLP and stemming using python package NLTK.
• Handle all Preprocessing tasks like data cleaning, integration, transformation, reduction and discretization using data mining tools like Rapid miner, WEKA, R-Programming tool, NTLK, Knime, pandas.
• Assisted ETL team with mapping, sessions and workflows using SSIS.
• Experience in developing time series, regression, decision trees, artificial neural networks, Bayesian networks, deep learning, support vector machines and rule-based machine learning algorithms using Python and R.
• Evaluate, test statistical model and machine learning models using residual graphical analysis, test harness and k-fold cross validation techniques.
• Design and visualize interactive results using tableau to publish dashboards

Confidential, Las Vegas, NV

Security Data Scientist

Responsibilities

• Developed a security model based on cyber-security analytics .
• Collected and modeled data to detect malware, their root causes and security incidences
• Proposed statistical analysis and visualizations using R
• Visualization of network behavior and patterns to understand source of the threats
• Interpret data, analyze results using statistical techniques , provide ongoing reports and provide feedback to the data.
• Worked on ETL package that included data conversions, dynamic variable expressions, sequence containers, conditional data flow using SSIS.
• Hands-on experience PL-SQL , SSIS , Business Intelligence in an SQL Server environment
• Designed and shared code using R and SQL extractions from relational database, data cleaning, data analysis, predictive analytics and graphic visualization.
• Developed a shiny app using information security data with in depth analytics to visualize intensity of a hack
• Data analytics on security using R language to predict cyber-attacks with respect to location and visualization using Tableau .
• Effectively used data blending feature and worked on Server installation and administration in tableau
• Experience with preparing dashboards using calculations, parameters, calculated fields and sets in Tableau.

Confidential

Senior Sourcing Engineer

Responsibilities

• Analyzed historical cost, service, material and other data to provide key insights to review financial goals, identify cost variances, save on opportunities and report on initiatives
• Used oracle tools and applications to develop and present metrics/reports to leaders and stakeholders of varying levels of technical and business knowledge
• Implemented six-sigma to optimize supply chain processes
• Developed cross functional expertise by working in the areas of purchase planning, contracts and procurement, sourcing and product life cycle management.
• Excellent working knowledge on Microsoft excel and use of functions like VLOOKUP , concatenate , lower, upper, proper and if functions.
• Performed data cleaning by removing duplicates, text columns and using mark check box in spread sheets.
• Performed various data analysis by drawing inference from data using pivot table and creating charts in Microsoft excel .
• In depth knowledge on oracle database and oracle e-business suite .