Data Engineer, Python SQL Developer, Aspiring Data Scientist

<p>Sanket Chobe <br />Data Engineer, Python, SQL Developer, Aspiring Data Scientist <br />XXXX@XXXX.XXX | (XXX) XXX-XXXX |LinkedIn: sanketchobe | Chicago, IL <br />Experience Summary <br />&bull; 6 years of experience in Software (backend) development for banking and finance domain. <br />&bull; Proficiency in Python, SQL, Data Analysis and problem-solving using data structure and algorithms. <br />&bull; Research journal publications in Machine learning (Association rule mining and Graph Analytics/Clustering). <br />Academic Qualification <br />&bull; 2016 - 2018: MS in CS University of Nevada, Las Vegas, USA <br />GPA - 4.0/4.0 <br />&bull; 2007 - 2011: B. Tech in IT <br />Government College of Engineering, Amravati, India GPA - 8.72/10.0 Data Mining Research Journals and Projects <br />Mining Association Rules for Low Frequency Itemsets &ndash; PLOS ONE (Published) 2018. DOI <br />&bull; Published a novel association rule mining algorithm for low frequency and low-utility itemsets, achieved same <br />run time efficiency as FP-growth algorithm. <br />&bull; Generated new priority-based rules to provide effective discount offers or online recommendations. Advancing Community Detection Using Keyword Attribute Search &ndash; Journal of Big Data (Published) 2019. DOI <br />&bull; Developed a novel clustering algorithm for personalized community detection by creating a new classification <br />and keyword search method for attributed graphs. Python, NetworkX, Gephi <br />&bull; Data preprocessing - feature selection of ground-truth network datasets (10,000 nodes) with random attributes <br />on nodes and (&gt;=30%) probability of edge creation. <br />&bull; Achieved a scholar position in the Data Scientist fellowship challenge of The Data Incubator. Correction of Spelling Errors and Sentiment Analysis NLP - Python, NLTK, Scikit-learn, Numpy, and Pandas. <br />&bull; Implemented HMM with 85% accuracy of correction of spelling errors in a document with 44000 characters. <br />&bull; Naive Bayes Classifier model for the sentiment analysis of movie reviews with 95% accuracy of classification of <br />the review as positive or negative. <br />&bull; Neural Network, Decision Trees, and Random Forest algorithms for movie reviews with around 90% accuracy. Industry Experience <br />Data Engineer - Capital One/ Wipro Limited, Chicago, USA: 03/2019 &ndash; Present <br />&bull; Developer of Scala, Spark SQL and Snowflake modules for ETL on the partner data into AWS cloud environment. Software Developer Intern- Caesars Entertainment, Las Vegas, USA: 05/2017 &ndash; 01/2019 <br />&bull; Developed Golang modules, and complex PostgreSQL queries to visualize the sports betting summary on the <br />leaderboards at The Book - LINQ Casino (Leaderboard as a Service). <br />&bull; Developed a POC for Quiz, Tone, and Personality analysis chatbots using IBM Watson and Microsoft Azure. <br />&bull; Developed a POC on DOTA2 with 70% accuracy of winner prediction using logistic regression and SVM models. Analyst - Principal Financial Group, Pune, India: 12/2014 &ndash; 07/2016 <br />&bull; Developed scalable COBOL DB2 SQL modules for billing and specialty benefits modules using Agile SCRUM/XP. System Engineer - Tata Consultancy Services, Pune, India: 09/2011 &ndash; 12/2014 <br />&bull; Developed scalable DB2 SQL Stored Procedures for New Account Opening application of Morgan Stanley. Technical Skills <br />Programing: Python, SQL, T-SQL, PostgreSQL, Golang, Scala, Spark SQL, C++, HTML, NodeJS. <br />Algorithms: Community Detection, Logistic Regression, Neural Networks, Decision Tree, Random Forest. <br />Packages: Pandas, NumPy, Scikit-learn, Matplotlib, NetworkX. <br />Databases: DB2, MS SQL Server, Neo4J, Snowflake, Apache Spark, AWS basics, Hadoop Map-reduce. <br />Data Tools: Spyder, Jupyter Notebook, Azure ML, R-Studio, Visual Studio code, Tableau, Git, Docker, IBM Z-os.</p> How We Protect Your Privacy


Profile Views: 237
Member since: 2019