| | | 20,000+ Fresh Resumes Monthly | |
|
|
| |
Click here or scroll down to respond to this candidateCandidate's Name
Data Science Machine Learning R & Python Programming CloudEMAIL AVAILABLE PHONE NUMBER AVAILABLECareer-oriented and a hard working professional with over 6 years of IT experience in data science (machine learning, text mining), data management, data visualization, data warehousing, and data/business analytics, and operations.EDUCATION:The University of Texas at San Antonio (UTSA) Jan 2020 - May 2023M.S. in Computer Science (Concentration in Data Science) GPA: 3.93Coursework: Data science, Database Management Systems, Machine Learning, Cloud Computing.Muffakham Jah College of Engineering and Technology Oct 2005 May 2009B.E. in Information Technology Percentage: 84%SUMMARY:Expertise in data mining, text analytics, statistical machine learning and creating data visualizations with Tableau, R, and Python for a range of business issues.Proficiency in converting corporate needs into analytical models, creating models, algorithms, and data mining solutions that can handle enormous amounts of both organized and unstructured data.Identifying data that is accessible, utilizing both external and internal data sources, by utilizing innovative data collection techniques such as geolocation data.Competent in researching new and existing processes and technologies that require data inputs and outputs, analytical metrics, and user interface requirementsProficiency in developing Supervised and Unsupervised Machine Learning projects with Amazon & Azure, employing various algorithms to conduct in-depth predictive analysis and constructing Web Services models for any kind of data, including continuous, nominal, and ordinal.Good Knowledge of Hadoop MapReduce and Amazon EMR or any big data framework.Good Knowledge of REST API's and experience working with gRPC.Experience working with Machine learning models and distributed systems.Mitigating risk factors through careful analysis of financial and statistical data. The raw data is transformed and processed for further analysis, visualization and modeling.Having expertise in using data mining and modeling approaches utilizing decision trees, k-mean clustering, clustering, linear and logistic regression, correlation, hypothesis modeling, and inferential statistics.Organizing new data in documents to support the mapping of sources to targets. Additionally, maintaining data validity and cleanliness through data profiling and updating the documentation for already-existing data.Proficiency in utilizing machine learning platforms such as R & Python Data Science Packages (Scikit-Learn, Pandas, NumPy) to develop scalable Statistical & Predictive Decision Science Models.Team builder with excellent communication, time and resource management skills and the ability to consistently develop client relationshipsCertifications:Microsoft Certification in Essentials of Data ScienceAmazon Web Services Solution Architect Associate LevelProgramming, Frameworks & Scripting:SQLPythonR Programming & R StudioJava ScriptDjangoApache HadoopHTMLCSSXMLReact JSC/C++ScalaGolangFlaskT-SQLBackend:C/C++Node JSDevelopment Tools:Notepad++Jupyter, Spyder, Google CollabGoogle, Elastic Search AnalyticsHDFS, Hive, SparkRedshiftAzure & Amazon Machine LearningTalend, Tableau, Snowflake, Power BI, Tensor FlowMemSQL NetezzasnowflakeTableauTechniques & Algorithms:Machine LearningRegressionClassificationData Mining & CleaningStatisticsDecision TreesRandom ForestDatabases:SQL/MySQLCassandraMongoDBProject Life Cycle:Data AnalysisBusiness Analysis & MonitoringProject SchedulingDeploymentOperationalizationOthers:DockerJIRAPyTorchScikit LearnTensorflowREST API'sgPRCMachine LearningBig DataACADEMIC PROJECTS:An e-commerce interface website for an online bookstoreTech Stack: Python - Django Framework Jan 2023 May 2023Designed an e-commerce website for a bookstore along with admin interface using Python - Django Framework. Our team size is 5.Built a user-friendly website by following all the principles of a user interface design.Design a new ML model for Classification of images using an existing CNN ML model.Tech Stack: Python, Py torch Aug 2022 Dec 2022Built an ML model for classification on top of existing Densenet161 for categorizing the images of a dataset into autistic and non-autistic children.Analysis of the NYC Uber Trips dataset from April to September in 2014.Tech Stack: Hive, Chameleon cloud, Hadoop Aug 2021 Dec 2021 Have Setup Hadoop on chameleon cloud and performed all queries for processing the dataset and analyzing the traffic trends. Team size is 5.A website for facilitating online booking of domestic gas.Tech Stack: JavaScript, SQL, HTML, CSS Aug 2022 Dec 2022Developed a website for online booking of domestic gas with JavaScript, html and CSS for frontend and MySQL as database. Incorporated two step authentication. Team size is 4.A compiler for Decaf 22 Programming languageTech Stack: C/C++, Flex, Bison, shell scripts, bash, Linux Jan 2023 May 2023Designed a 4-step compiler. The first step is scanner implemented using C++ & flex that scans the input and tokenizes keywords, data types, identifiers.Developed a syntax analyzer using C, C++, and bison for parsing phase of the compiler in step2.Implemented a semantic analyzer for type checking, label checking, flow control check and reporting semantic errors in step3.Lastly in step4 the compiler generates the assembly code, using C++ and SPIM.PROFESSIONAL EXPERIENCE:Data Scientist:Jan 2019 - Nov 2019Lucid Infosystems, Sunnyvale, CA.Roles & Responsibilities:Developed Machine learning, Statistical Analysis and Data visualizations applications with challenging problems that involved large data processing.Designed the mapping specifications for converting the legacy building and warehouse datasets.Expertise in working with different databases like Oracle and SQL. Have performed the log transformations, feature engineering, computations and Data exploration to identify the insights and provided conclusions from complex data using R- programming in R-studio.Have implemented predictive machine learning algorithms models like linear regression and linear boosting algorithms and performed in- depth analysis on the structure of models. Have compared the performance of all the models as part of analysis. Identified that tree boosting algorithm is the best for the prediction for the existing problem.Experience with using the in-memory computing capabilities of Spark to perform advanced procedures like text analytics and processing.Expertise with Spark in Memory capabilities, Broadcasts in Spark, Effective & efficient Joins, Transformations and other during ingestion process itself. Proficient in handling large datasets using Partitions.Have utilized the concepts of R-squared, R.M.S.E, P-value in the evaluation process to extract interesting findings through comparisons.Experience in using Cluster analysis, Logistic Regression, and boosting models to perform an in-depth statistical analysis. Applied data mining methods using R for these models.Have actively involved in all the phases of project life cycle including data acquisition, data cleaning, data engineering. Proficient in the whole CRISP-DM life cycle.Proficient in desgining Web services for the predictive analytics. Extensively used Azure Machine Learning to set up the experiments.Ability to write complex SQL queries in performing Data analysis using window functions, joins and ehanching the performance by using partitioned tables.Have built SQL procedures to synchronize the dynamic data with the Azure SQL Server.Expertise working with Golang and Scala languages.Have used Tableau to design multiple dashboards that shows the data behavior. Analyzed and worked well with all of regression models (OLS etc).Actively worked with stakeholders and played a key role in resolving any techincal challanges in the applications and to communicate to team members. Took leadership to ensure the models are well desgined and optimized.Merged SAS datasets into Excel using Dynamic Data Exchange. Used SAS to analyze data, statistical tables, listings and graphs for reports.Data Scientist:APR 2014 - Feb 2015WIPRO technologies, Pune, IN.Roles & Responsibilities:Have performed the Setup of storage and data analysis tools in Amazon Web Services cloud computing infrastructure.Developed numerous machine learning algorithms by using pandas, numpy, Seaborn, scipy, sci-kit-learn libraries in Python.Have experience in using NoSQL databases, such as MongoDB, Cassandra, HBase. Have also used SQL, NoSQL databases and Python programing and API interaction.Have imported the data from different data sources, performed transformations using Hive, MapReduce, and have also loaded data into HDFS.Defined the source to target data mappings, business rules.Experience in automation engineering tasks and performed the ELK stack (Elasticsearch, Kibana) for AWS EC2 hosts.Utilized Reference Data Management (RDM) to Define the list codes and code transformations between the source systems and the data mart.Hands on experience in designing and deploying AWS services: VPCs, EC2s, S3, RedShift, MySQL DBs, Snowball, ELB, Auto-scaling, IAM policies/roles and Security and Networking Services on Linux and Windows OS.Involved in an end to end Informatica ETL Testing for the custom tables and wrote complex SQL queries on the source database to compare the results against the target database.Created the source data from MS SQL Server, sequential files and excel sheets.Maintained the data dictionary to create metadata reports for technical and business needs.Experience using the ETL tools and data visualization tools.Implemented supervised algorithms like Logistic Regression, Decision trees for classification.Modified the Python scripts to match our training data with our database stored in AWS Cloud Search and assigned each document a response label for further classification.Performed data transformations from different resources, have done data organization, and features extraction from raw and stored data.Built and maintained dashboard, reports using the statistical models to identify and track key metrics and risk indicators.Have parsed and cleaned the data streams to load it into an analytical tool.Participated in updating code modules and patches.Data Analyst:Jan 2012 Jan 2014CAP GEMINI (Formerly known as iGATE Global Solutions), HYDERABAD, INRoles & Responsibilities:Developed R/Python programs to prepare transform and harmonize data sets in preparation for modeling.Utilized REST API's for the application.Created large data sets from structured and unstructured data and Performed data mining.Collaborated with data modelers to develop data frame requirements for projects.Developed Python/R programs for Ad-hoc reporting/customer profiling, segmentation.Followed and tracked various campaigns, generating data required for customer profiling analysis and data manipulation.Provided maintenance to the testing team for System testing/Integration/UAT.Participated in Design reviews and Technical reviews with the project stakeholders.Have involved in the complete life cycle of the project right from the requirements gathering to the production support.Have used Linux environment for project implementation.Have worked on loading data from RDBMS and web logs into HDFS. Also on loading the data from MySQL to HBase using Sqoop.Executed Hive queries for Analysis across a variety of banners.Have set up Amazon EC2 Cloud Instances using Amazon Images (Linux/ Ubuntu) and Configured the launched instances for the specific applications.Developed a R/SQL program, with a list of detail steps for the execution of data analysis as a part of final project deliverables. Performed data mining.Performed detailed analysis on large datasets and generated reports and outcome to answer business queries.Collaborated with a team of programmers and data analysts to develop insightful results that support data-driven marketing strategies.Utlized Microsoft Visio and Rational Rose for designing the Use Case Diagrams, Class model, Sequence diagrams, and Activity diagrams as part of the SDLC process of the application.Experience in exporting the results set from Hive to MySQL using Sqoop.Increased the efficiency of the existing system by improving the performance of the existing Data warehouse applications.Jr Data Analyst:Feb 2010 Jan 2012CAP GEMINI (Formerly known as iGATE Global Solutions), HYDERABAD, INRoles & Responsibilities:Analyzed and profiled data using sophisticated SQL on multiple systems including Teradata and SQL Server.Created logical data models & physical data models that restrict existing condition / potential status data basics and data flows with ER Studio.Assists in analyzing Business needs, designing and developing high level and low level designs, unit and integration testing.Implementing Metadata Repository. Involving in maintenance of Data Quality, Data Cleanup procedures, Transformations, Data Standards, Data Governance program, Scripts, Stored Procedures, triggers and execution of test plans.Implemented the naming standards for the entities, attributes, alternate keys, and primary keys for the logical model. Have also involved in Peer reviewing the logical model.Utilizing Web crawling and text mining techniques to score referral domains and to generate keyword taxonomies, and assess commercial value of bid keywords.Coordinated to set up meetings with vendors for requirements gathering and prepared the system interaction agreement documentation between client and vendor system.Created lists of multimillion bid keyword using extensive web crawling. Identifying the metrics to measure the quality of each list (yield or coverage, volume, and keyword average financial value).Involved in integrity check of data used in analysis,reviewed the data Processing, cleansing.Updating the Enterprise Metadata Library.Documented data quality and traceability documents for each source interface.Dealt with DTS Packages, DTS Import/Export for transferring data between SQL Server 2000 to 2005.Generated asstet inventory reports on a weekly and monthly basis. |
