Yash Manish Raichura

Seattle, WA, USA adczof@r.postjobfree.com +1-206-***-**** https://www.linkedin.com/in/yashraichura/ EDUCATION

University of Washington, Seattle, USA Expected - May 2021 Master of Science - Information Management – Specialization (Data Science, Business Intelligence) GPA – 3.85/4 Relevant Courses: Machine Learning, Statistical Modeling, Natural Language Processing, Business Intelligence (Data Warehousing), Visualization Design, Deep Learning, Big Data Analytics, Advanced Relational Database Management Systems, Social Network Analysis. University of Mumbai, India May 2017

Bachelor of Engineering GPA – 3.6/4

Relevant Courses: Computer Programming, Statistics, Applied Mathematics, Image Processing, Data Structures and Algorithms. SKILLS AND ACHIEVEMENTS

• Technical Skills: Python, R, SQL, JavaScript, NoSQL, Spark, Hadoop, AWS, Java, C++, HTML, CSS#, Bootstrap, XML

• BI Tools: Tableau, Power BI, SSMS, SSIS, Oracle Toad, Jira, Informatica PowerCenter, Talend, R Studio, AWS Lambda, AWS ML

• Winner of NASA International Space Apps Challenge Hackathon 2019 and Google TechStars Startup Event PROFESSIONAL EXPERIENCE

Accenture, India – Data Engineer Jul 2017 - Aug 2019

• Toolkit: Python, R, SQL, Tableau, Power BI, Informatica PowerCenter, Oracle Toad, Jira, Advanced Excel

• Implemented a data warehouse to enable generation of business reports to process more than 50 million records daily. Used ETL techniques such as dimensional modelling which resulted in a reduction of 50% for dimensions and 33% for fact tables.

• Developed over 500 ETLs and coded multiple complex SQL Queries for formatting and cleaning the data as per business requirements and performed SQL Query optimization to enhance data retrieving efficiency from 250 minutes to 2 minutes.

• Developed and deployed ‘Informatica Data Rejector’, an in-house tool using python to extract rejected records from Informatica Session log using Text Mining Principles, which was used for root cause analysis and saved the team 200 hours/week.

• Created automated notification alerts for missing data files on sFTP server using python (NumPy, pandas, seaborn) and displayed the results with an interactive GUI using python tkinter to reduce manual efforts by 30%.

• Designed, configured and developed an automation tool (using Python, Perl and JavaScript), using supervised machine learning algorithms which reduced production failures by 3000 incidents per year.

• Developed an automated email notification tool and analyzed underlying defects from the client website using web scraping principles and displayed the resulting reports using Tableau and Power BI, which reduced manual intervention by 40%. University of Washington, Green Dubs, USA – Data Scientist Jan 2020 - Present

• Toolkit: Python (Flask, Keras, Pandas, NumPy), SQL Server Management Studio, AWS Rekognition

• Developing a custom image recognition model (using unsupervised learning – Keras and Convolutional Neural Networks) to classify sightings of wildlife species and building a web application using Python Flask for users to upload images, segregate and collaborate data to engage with scientific researchers.

University of Washington, USA – Graduate Research Assistant Mar 2020- Present

• Toolkit: SQL Server Management Studio, Python, Flask, AWS

• Helping students understand principles of web development in software development using python Flask and connecting to a database and cloud using python. Conducting office hours and assisting students in the coursework. Electronics Corporation of India Limited, India – Data Science Intern Dec 2015 – Jan 2016

• Toolkit: NumPy, Pandas, matplotlib, seaborn, Beautiful Soap

• Developed a book recommendation system using Collaborative Filtering Method on user demographic details to recommend books. RELAVANT PROJECTS

DataForGood – NASA International Space Apps Hackathon – Winner, Google TechStars Hackathon - Winner

• Designed a web application, involving a database, using C# and SSMS that utilized NASA Earth Science Division’s data set and implements inference-based Machine Learning algorithms to help climate preservation to mitigate risk reduction challenges.

• Strategized a revenue model by factoring in customer validation, market size and explored partnerships a with local companies. Analysis of Amazon Reviews, Using Natural Language Processing, Text Mining and Clustering (Bag of Words)

• Analyzed amazon dataset consisting of user reviews of all the products, converted these reviews to a bag of words and removed stop words for precise analysis.

• Calculated TF-IDF Values for each word and performed K-Means Clustering to separate out reviews of different products. Predictive Analysis of Global Opinion, World Values dataset

• Performed classification using k-NN, logistic regression, Linear and Quadratic Discriminant Analysis and SVM by implementing k- fold cross validation to predict the opinion on abortion and evaluated model performance using accuracy and F-1 score. Job Portal Management System (RDBMS – SQL)

• Modelled a relational database schema using Entity Relationship (ER) Diagram and Normalization techniques (3NF) to store, retrieve and update data, implemented column data encryption, CHECK constraints and computed columns to fulfil business needs.

• Created a database in MS SQL server, generated views and created analytical reports and visualizations using Tableau.

Contact this candidate