SUMMARY

• IT professional with over 5 years of diverse experience in data - driven analytics
• Proficient in Transforming large, complex datasets into pragmatic, actionable insights as well as leverage data to identify, quantify and influence tangible business gain.
• Experience in using Statistical Model Building and Machine Learning Algorithms such as Hypothesis Tests, ANOVA, Clustering and Regression, Time Series Analysis, PCA analysis to analyze data for further Model Building.
• Well versed in machine learning algorithms such as Linear and Logistic Regression, Decision Trees, Random Forest, Support Vector Machines, Neural Networks, K nearest neighbors.
• Extensive programming skills in programming languages such as R, Python, SQL, Weka and Java.
• Experience in Data Modeling and Designing Value Added Datasets using SAS, R, Python, SPARK, SQL to analyze the hidden insights within the data to effectively implement Analytical Project Objectives.
• Hands on experience in manipulation, wrangling, model building and visualization with large data sets in R and Python.
• Expert in Visualization and dashboards using Shiny, ggplot2 and seaborn.
• Proficient in establishing scalable, efficient, automated processes for large scale data analyses, model development, model validation and model implementation.
• Extensively worked on all phases of data warehousing and business intelligence projects like data mining, data cleansing, data modeling for data staging & data mart, ETL, Indexing, Quality Assurance, data updating plan, data presentation to business users, auditing, backup and recovery.
• Experience in MapReduce, HIVE and Spark, Hadoop,
• Experience in dealing with different data sources ranging from Flat files, SQL server, Oracle, My SQL, MS Access and Excel
• Industry experience and expertise in Business Requirement gathering, Business Process flow, Business Process Modeling and Business Analysis.
• Strong presentation skills and ability to tailor presentations towards different functional areas of business.

TECHNICAL SKILLS

Programming Languages: Java SE, Java EE, R, Python

Web Development: HTML5, JS, CSS 3.0 Analytics tools SAS, R, Python

Platforms: UNIX, LINUX (shell scripting), Microsoft Windows, MacOS

Databases & Big Data: SQL, Teradata, MySQL, Oracle, Hadoop 2.0, YARN, Pig, Hive, Spark, Sqoop, Kafka

BI Tools: R Shiny, R, Python, Spark, Excel-VBA, Tableau, dashboarding, Spotfire (Basic), QlikView (Basic), TensorFlow

PROFESSIONAL EXPERIENCE

Confidential, Bloomington

Data Scientist

Responsibilites:

• Derived the deviation of the scheduled arrival/departure time from the actual, for major bus stops across all routes. Results showed a route could take anywhere from 21 to 35 minutes, which in theory is scheduled to take 27 minutes. R, Python, D3, Highcharts .
• Performed data extraction, Data mining, exploratory data analysis, data manipulation and prepared various production and ad hoc reports using Quantitative Analysis to support risk adjustment initiatives and strategies using R, Python and highcharts
• Built a Spark Standalone application using Kafka to read messages from the message system -Logs and detect whether the IP address is part of the DDOS attack. Integrated with Spark Producer and Consumer API’s to perform read from HDFS as streaming data.
• Implemented a decision tree in Python to explore its applicability to predict the presence of breast cancer in the preliminary stages.
• Implemented ensemble methods to reduce bias and variance and obtain better predictive performance. Built a model suitable for recommending hashtags for tweets Java- Lucene Framework, LDA and Word2Vec
• Predicted the scoring pattern to an accuracy of 61%, from a perfectly unbiased training set SkLearn, Python .
• Analysed and compared the performance of conventional supervised learning algorithms viz. SVM, Naive Bayes and KNN. Python R, Python, Spark, D3, Highchart

Confidential, New York

Data Scientist

Responsibilites:

• Derived interesting insights into running a logistic operation in countries, which presents cultural, economic and regulatory challenges among the very few.
• Extracted data from one or more source files and Databases using R and Python.
• Participated in continuous interaction with Marketing and Finance teams for obtaining the data and data quality and obtaining Metadata.
• Accomplished multiple tasks from collecting data to organizing data and interpreting statistical information.
• Unearthed the raw data by doing the Exploratory Data Analysis.
• Converted raw data to processed data by merging, finding outliers, errors, trends, missing values and distributions in the data.
• Conducted data exploration to look for trends, patterns, grouping, and deviations in the data to understand the data diagnostics.
• Designed various reports using Pivot - tables, and different charts like Bar, Pie, Line etc.
• Developed segmentation trees (CHAID) to find out high risk segment of the population.
• Developed multiple MapReduce jobs in Java for data cleaning and pre-processing and finally derive distributions of time taken by shipments inside a facility as well as in transit.
• Handled importing of data from various data sources, performed transformations using Hive, MapReduce, and loaded data into HDFS.
• Analyzed datasets using ClickView and used statistical analysis to make effective project decisions
• Analyzed large data sets in HDF - Python to build models for data analysis using Question-Model-Validation technique.
• Installed and configured Hadoop MapReduce, HDFS and developed multiple MapReduce jobs in Java for data cleansing and preprocessing.
• Designed and implemented web applications and customized data visualization using R-Shiny (GUI)and helped end users to visualize data in real-time.
• Involved in loading data from UNIX file system to HDFS and programmed scripts using R, Perl, UNIX for processing large datasets and resolved technical setbacks on the data analysis
• Analyzed large amounts of data sets to determine optimal way to aggregate and report on it.
• Responsible for building scalable distributed data solutions using Hadoop.
• Responsible for cluster maintenance, adding and removing cluster nodes, cluster monitoring and troubleshooting, manage and review data backups, manage and review Hadoop log files.

Environment: R, Python 3, sklearn, SQL, Logistic Regression, K Neighbors Classifier, Jupyter notebooks, Anaconda, Weka

Confidential

Data Scientist

Responsibilites:

• Monitor their production lines for waste generation and perform root cause analyses.
• Developed a customer segmentation analysis system using the K-means algorithm to generate a customer
• Analytical record which can be used to profile new or returning customers.
• Extesnively worked on R, responsible for data analysis and analytics.
• Processed huge datasets (over billion data points, over 1 TB of datasets for data association pairing and provided insights into meaningful data association and trends., done data analysis and statistical modeling
• Developed cross-validation pipelines for testing the accuracy of predictions
• Enhanced statistical models (linear mixed models) for predicting the best products for commercialization using Machine Learning Linear regression models, KNN and K-means clustering algorithms
• Automated Quality Control reporting tools (using R) for product commercialization based on biotechnology industry standards
• Designed and implemented analysis pipelines for data summarization, variation, aggregation and reporting analysis.
• Worked for Ministry of Finance, Belgium to build a module in automating their trade processes.
• Developed specialized web application of assigning risk associated with every item.
• Demonstrated good levels of enthusiasm and interest in knowledge management, value innovation, defect prevention activities.

Environment: R, Pyton, DPR, data.table, reshape, caret, dplyr, randomForest, ctree, rpart, Hadoop, Hive, HBase, lm, glm, nnet, xgboost, ksvm, lda, qda, adabag, adaboost, lars & lasso, roxygen2.