Data Analyst Engineer

DIVYANK GARG

**** ********* ****** ***.********.com/in/divyank-garg-19381678 979-***-****

San Jose, CA, 95134 https://www.kaggle.com/divyank10 *************@****.*** EDUCATION

Texas A&M University, College Station, Texas, US Aug 2017 – Aug 2019 Master of Science (Major: Engineering Data Analyst), CGPA 3.5/4.0 Relevant Courses: Engineering data analysis, applied analytics, Applied informatic science, Regression Analysis, Statistic, DOE National Institute of Technology, Raipur, India May 2012 – May 2016 Bachelor of Technology, GPA 3.7/4.0

TECHNICAL SKILLS:

Proficient: R-studio, Python, MYSQL, Tableau, Power BI, VBA Excel, Alteryx, GitHub, Outlook, UNIX, Smartsheet, SPCD, DBMS Data Analysis/ Science: Data mining, Data preprocessing, Machine learning, Data visualization, Hypothesis testing, AI PROFESSIONAL EXPERIENCE

Juniper Networks, Sunnyvale, USA (Software Engineer/Data Analyst) Sep 2019- Present

• Used Tableau Prep to create pipeline for PR data source and used SQL query for customizing big data and cleaning it

• Published Tableau dashboard to keep track of PR related issues and analyzed trend and count of PR for individual team

• Used shell and python script in LINUX to automate the voltage marginal calculation value during hardware testing Juniper Networks, Sunnyvale, USA (Data Analyst Intern) May 2019 – Aug 2019

• Extracted data from server MYSQL RDBMS using python and combined it with scrapped data from smart sheet using API

• Created ER diagrams and Relational schema to learn relation between tables and executed SQL queries to get desired table

• Pre-processed data in python and built python scripts that converted unstructured table to meaningful table for analysis

• Delivered an automatic interactive dashboard in Power BI which pulled live data from server using python script as back- end and displayed total amount spent quarterly wise for NPI programs and further categorized spent into subcategories

• Made Tableau Dashboard to show labor allocation and quarterly amount spent for projects like infra, NPI, sustaining, VE.

• Forecasted actual amount against planned amount for next quarter using different model like- Moving Average, Exponential Smoothing, Holt’s Linear Trend and ARIMA in python to analyze under-spend vs overspend quarterly Juniper Networks, Sunnyvale, USA (Data Analyst Intern) May 2018 - Aug 2018

● Optimized the functional yield six-sigma target value by validating complex yield data on 2017 yield data sets

● Extracted 12 datasets from Oracle Agile system to combine and blend them in Alteryx software to get unique dataset

● Removed outliers and grouped product into 3 cluster based on complexity index value using K-means clustering in R studio

● Fitted linear regression line between yield and complexity index of product to get complexity factor for 3 cluster group

● Built new target yield model in R based on complexity grouping with improved accuracy of 45% compared to current model Vedanta Resources, Chhattisgarh, India (Process Improvement & Analyst Engineer) May 2016 - July 2017

● Applied advanced predictive analytics techniques through sensors output data to identify areas which needs maintenance on priority basis to increase efficiency & reduce the time required for the crane to be in maintenance mode

● Used SQL to design the database & checked for spare inventory by cross-linking multiple projects resources ACADEMIC PROJECTS Oct 2017 - Nov 2018

Built a predictive classification model of accuracy 88% by using R studio for analyzing semiconductor manufacturing dataset

● Analyzed dataset with 1567 observation & 590 parameters and imputed missing values using techniques- KNN, Mean, MICE

● Feature selection of 127 important predictors was done using technique like- PCA, MARS, BORUTO and LASSO

● Unbiased training dataset in the ratio 1:14 was balanced to 9:10 by using case boosting techniques SMOTE & ROSE

● Built a best predictive classification model of accuracy 87% using technique like- LDA, LR, Decision Tree, SVM, C5.0 Created dashboard and story using Tableau to analyze different salaries in different state in US for data related job

● Found highest median salary of $130000 for attorney job title throughout US in 2017 year using histogram

● Featured companies like- IBM, Google which paid less wage then prevailing wage in 2017 throughout US using tree plot

● Compared the wages of data science engineers within states with respect to living cost using blending and calculation field Expanded operation of Metro Bike plan in LA by predicting bikes per station and recommending new station using Python

• Preprocessed data of 4 regions of LA bike for 3 years and used SQL queries to merge station details and bike details data

• Calculated distance using google distance API and time duration using datetime function and grouped them along with trip id on month wise for each station to perform linear regression and found R-square of 85% for some station

• Used time series algorithm to check seasonality in data and applied ARIMA for forecasting demand of bike for next quarter

• Applied Linear and Quadratic optimization to maximize total revenue based on pricing structure and number of rides

Contact this candidate