PRATEEK GOYAL

Data Science Graduate

**x Certified Data Science Professional with 5+ years of

industrial experience in delivering data-driven decisions and insights to clients across the Automotive, Logistics, and Healthcare domain. Highly skilled in ETL data

pipelines, Data Visualization, and Machine/Deep

Learning. CGPA: 4/4

adg5f2@r.postjobfree.com

+1-906-***-****

Houghton, MI, USA

prateekgoyal.me/

linkedin.com/in/pgoyal-mlai

github.com/prtk1306

WORK EXPERIENCE

PLM IT Intern

Visteon Corporation

06/2020 - 08/2020, Van Buren, MI, USA

Legacy System: Reduced data synchronization time between systems by 95.8% (1 day to 1 hr) by automating ETL data pipelines with 80% code reusability; completely eliminating manpower dependency. Techniques Used: Python, SQL, SMTP, Batch Scripts US-based automotive electronics supplier: Integrated multiple logical data cubes into a single data model; developed various OnDemand Business Centric reports using a drag-drop feature. Techniques Used: Teamcenter Reporting & Analytics tool, Oracle Senior Associate Technical Consultant

SAS Institute, Inc.

06/2017 - 07/2019, Pune, MH, India

US-based major Healthcare: Developed ETL pipelines for processing terabytes of PHI data, performed data integration from varied sources, data pre-processing, and feature engineering; making data ready for downstream purposes. Techniques Used: SAS Macros, MapReduce, HDFS, Statistics, Linux US-based major Healthcare: Led the development and maintenance of visual analytic dashboards and reports to drive health science-related decisions and communicate real-time feeds to Doctors and Scientists; resulted in saving 300+ lives last year. Techniques Used: Tableau, SAS VA, SAS Cloud, Hadoop System Engineer

TATA Consultancy Services (TCS)

09/2014 - 06/2017, Gurugram, HR, India

Danish Logistic Company: Build a route optimization model for the transportation of empty containers; saved up to $4 million yearly. Techniques Used: SAS, Oracle, PL-SQL, Zabbix, Linux Danish Logistic Company: Reduced query execution time by 99.4%

(~36 hrs to under 10 mins) by redesigning the underlying data model and optimizing the SQL query using data profiler, enabled the client to get live updates of all in-transit containers on the fly. Techniques Used: SAP BusinessObjects, IDT, Data Warehousing, OLAP, Microsoft SQL Server, IoT Telemetry

PUBLICATIONS

A Comprehensive Guide to Regression Analysis - ML

Classification of MNIST dataset using Deep Learning A Data Preprocessing Guide for ML using Python

A Fast-track Hands-on Guide for Matlab/Octave

AWARDS

3X SPOT Award

SAS R&D and TCS

David House Family Fellowship.

Michigan Technological University, USA

SKILLS

Machine & Deep Learning AWS Tableau Statistics

Exploratory Data Analysis Feature Engineering Python ETL Pipelines Visualization Data Mining SAS R

SQL NLP Keras Regression Classification

Clustering SAP Big-Data Hadoop Optimization

DATA SCIENCE PROJECTS

Alzheimer's Disease: Diagnostic Classification and Prognostic Prediction Using Neuroimaging Data. Techniques Used: Logistic Regression, SVM, Tree-based models, Adaboost, CNN, DNN Stock Price Analysis & Prediction. Techniques Used: Exploratory Data Analysis, Feature Engineering, Time Series, Web Scraping, Tree-based model, XGBoost, ANN, Hyperparameter Tuning using Talos

Worldwide COVID-19 Dashboard and Storytelling using Tableau. Techniques Used: Union, Join, Blending, LOD, Table Calculations, Calculated Field, Parametric Filters

Multi-Label Image Classification using Keras and Deep Learning. Techniques Used: AWS Sagemaker, S3, EC2, Image Augmentation, Transfer Learning: VGG-16 & MobileNet, CNN, DNN, Dropout, Parameter Tuning using Grid-Search, KNN, Naive Bayes, Logistic Regression, L1-L2 Regularization, DCT

Text Prediction using Natural Language Modelling in NLP. Techniques Used: NLP, Stacked LSTM, RNN, Early Stopping House Price Prediction using SAS. Techniques Used: SAS Procedure, Data Curation, Forward Stepwise, Backward Elim. Exploratory Data Analysis of Superstore Dataset using Tableau. Techniques Used: Advanced Tableau, Tableau Prep Builder Data Science Projects on GitHub. Techniques Used:

Machine/Deep Learning, Python, Tableau, Data Str & Algo CERTIFICATION

5x SAS, 3x AWS, 2x Tableau, 1x Azure, 1x Oracle certified. EDUCATION

Masters of Science (Data Science)

Michigan Technological University, USA

09/2019 - 12/2020, CGPA 4/4

B. Technology (Computer Engineering)

Bharati Vidyapeeth Deemed University, India

07/2010 - 06/2014, First Class with Distinction

Contact this candidate