Divya Srinivasan
adikhk@r.postjobfree.com
Data scien>st
SUMMARY
• 3+ years of IT experience in Machine Learning, Data mining with large datasets of Structured and Un- structured data, Data AcquisiCon, Data ValidaCon, PredicCve Modelling, Data VisualizaCon.
• UClized analyCcal tools like R- Programming to idenCfy trends and relaConships between different pieces of data, draw appropriate conclusions and translate analyCcal findings into risk management and markeCng strategies that drive value.
• Extensive database experience using BigData, Hadoop, mysql, Oracle, Sql server, mongodb.
• Worked with large and complex banking data on Hadoop mulC node cluster.
• Extensive experience in Data Mining using SQL to deep dive into structured, semi-structured & unstruc- tured datasets for acConable business insights
• Generated visually appealing and interacCve graphs to idenCfy trends and paVerns.
• Experienced in Machine Learning techniques ForecasCng, Time Series Regression, Linear/Nonlinear Re- gression, LogisCcs Regression, Clustering and Tree based models.
• Deep knowledge with Hadoop, Spark, and experience with Big Data tools such as PySpark, Pig and Hive.
• Proficient in SAS, R and Python for data wrangling, data analysis, model development and deployment.
• Created machine learning models for paVern recogniCon, anomaly detecCon.
• Hands on experience with RStudio for doing data pre-processing and building machine learning algo- rithms on different datasets.
• Worked on large datasets by using structured /unstructured data.
• Extensive experience in Data Mining using SQL to deep dive into structured, semi-structured & unstruc- tured datasets for acConable business insights.
• ExperCse and knowledge of design & execuCon of complex analyCcal soluCons by analyzing business problems, generaCng business insights using data, developing predicCve models, interpreCng results, and recommending strategies
Work Experience
Data scien>st
freelancer
August 2019-August 2020
ResponsibiliCes:
• Design and develop state-of-the-art deep-learning / machine-learning algorithms for Self-Healing.
• Developed the innovaCve and creaCve AI / ML /DS soluCons.
• Developed complex SAS Macros to simplify SAS code and effecCvely reduce coding Cme
• IdenCficaCon of new Use Cases and successfully created the predicCon model for cases (Out of Memory)
& (Disk Full).3
• Extensively Performed Data Mining on the Splunk log datasets.
• Involved with Data Analysis and, created the data dicConaries for the new datasets.
• Created the Data landscape and create a data roadmap for each pla^orm.
• Develop and maintain high quality Python code under Linux for general purpose PCs. Test and debug so_ware on mulCple technologies.
• working with large data sets using staCsCcal analysis and programming tools like Python and R.
• Worked on condiCon monitoring and predicCve failures.
• Develop/Edit SQL and Hive scripts to pull clean datasets.
• Worked on data preparaCon, data condiConing and data exploraCon.
• Analyze, interpret, and communicated the results of experiments by using exploratory data analysis techniques like histograms, scaVer plots, box plot etc.
• Deliver business value by translaCng complex data into meaningful insights.
• Strong foundaCon in probability, staCsCcs, and algorithm development.
• Worked on model buildings by using linear regression, logisCc regression, classificaCon problems and measured efficiency of models via various metrics.
• Developed algorithms for associaCon rules like Market Basket Theorem, Apriori algorithm.
• Created and developed algorithms for Decision trees, Random forest, Naïve Bayes classifiers.
• Created the deep neural network topologies such as convoluConal nets, recurrent nets, RBMs, causal reasoning, probabilisCc programming for log datasets. Data scien>st/ Data Analyst
SoOcell Technologies - Pune
April 2016 – November 2017
ResponsibiliCes
• Collected, collated, and carried out complex data analysis in support of management & bank requests and shared staCsCcal findings across teams.
• Ran SQL code to assess, clean, validate and analyze large datasets
• Analyzed and processed complex data sets using advanced querying, visualizaCon, and analyCcs tools.
• Designed and developed interacCve and user-friendly applicaCons using R- shiny.
• Explored and Implemented various algorithms like kmean, Apriori, PageRank and kNN using R.
• Automated reporCng process by fetching data from many data sources like excel, Hadoop, mongodb, Oracle, SqlServer and generaCng reports and plots using R and Python.
• Explored and compared various Data Mining tools like Weka, RaVle, Rapid Miner.
• Developed Tableau visualizaCons and dashboards using Tableau desktop.
• Hands on experience with imporCng and exporCng data from RelaConal databases to HDFS, Hive using Spark.
• Knowledge on Hadoop ecosystems such as HDFS, Job Tracker, Task Tracker, Name Node, Data Node
• Analyzed and understood the ETL workflows developed Data scien>st
Advanced Risk Analy>cs Pvt ltd-Pune
July 2015 - March 2016
ResponsibiliCes
• OpCmized data collecCons procedures and generated reports on weekly, monthly, and quarterly basis.
• Coordinated with banks and customers to validate and invesCgate suspicious transacCons.
• Extracted and analyzed variables importance on Fraud transacCons
• Developed SQL Reports using advanced queries in OLTP
• Wrote several stored procedures, funcCons, and cursors to build consistent reports for the sales
• Assisted in designing and developing technical architecture, requirements, and staCsCcal models.
• Worked on Data Analysis & VisualizaCon using R packages like Cdyverse, dplyr, ggplot2, ggvis, shiny, shinydashboard), Adv. Excel, PivotTables & Charts, Solver, Complex formulas, Data Analysis, Python, Lookups, SAS, Tableau (integraCon with R).
• Integrated R with Mongodb, Hadoop, .Net, Java.
• Responsible for creaCng Test Data based on test cases for Unit and IntegraCon TesCng and document- ing the results for future reference.
• Did black box tesCng to find out Invalid data, Boundary CondiCon, Decision Table Data Set, No data.
• Worked on Data VerificaCons and ValidaCons to evaluate the data generated according to the re- quirements is appropriate and consistent.
• Have used AWS, Jenkins/CI-CD infrastructure.
Technical Skills:
• Business Intelligence/BigData/Data Science-SQL, Hadoop (Hive/Impala), R, Python and SAS
• ETL/RDBMS-Teradata, SQLServer, Oracle.
• DataVisualizaCon/ReporCng- Tableau, Looker, Spo^ire, RShiny, Excel (Advanced)
• Version Control Agile/Others- Git, BitBucket, JIRA.
• MachineLearning/StaCsCcalModeling: LinearRegression, LogisCcRegression, DecisionTrees, Random- Forests, GradientBoosCngMachines, SVM, ClusterAnalysis, TextMining
• SpecialCes: DataAnalyCcs, Product AnalyCcs, Growth Strategy, Business Development, and Insights Educa>on:
Master of Science (Computer Applica>on)
Symbiosis InsCtute of Computer Studies and Research Pune India 2013-2015
Bachelor of Computer Science (Bcs)
Babasaheb Ambedkar university Aurangabad India
2010-2013