Resume

Sign in

Data Manager

Location:
Fullerton, California, United States
Posted:
January 21, 2019

Contact this candidate

Resume:

Ashwin Gour

https://github.com/ashwingour ac79a4@r.postjobfree.com 657-***-**** https://www.linkedin.com/in/ashwingour

Summary

I am a Proactive Data Scientist with an Experience of 3 years in both Python & SQL, proficient in Machine Learning Algorithms and Apache Spark prepared me for enhanced Business Solutions and Advanced Data-Driven Methods.

EXPERIENCE

mTAB LLC Anaheim, CA-92801

Data Science Intern May 2018 – December 2018

Framed different Classification and Regression models with MAE, MSE and R2 metrics via Apache Spark (MLib)

Performed Text mining, stemming, tokenization, lemmatization, and frequency distribution via spaCy and NLTK

Managed & created mTAB’s workflow for blending and extraction of data from large datasets with Alteryx

Implemented Mapping and Text Analysis of JSON files through Elasticsearch for Text Analysis and Text Mining

Conducted Optimization, Time Series Analysis & Communicated insights, business metrics to cross-functional groups

California State University, Fullerton Fullerton, CA-92831

Operations Specialist (Data), Mihaylo College of Business and Economics November 2017 – August 2018

Extracted, Aggregated and Manipulated data from multiple student databases with SQL Server

Analysed under Assistant Dean in distinct projects, transformed data & visualized its reports in Tableau, Excel

Carried out patterns in datasets through Statistics and visualized it via distinct suitable graphs, bars, charts with Tableau

Employed Excel’s Pivot Table, Pivot Reporting Data Visualization via Tableau

Virtual Globe Technology Nagpur, Maharashtra, India

Data Scientist January 2015 – December 2016

Applied Descriptive & Inference Statistics, Naïve Bayes, Random Forest, SVM, Clustering, PCA models to business problems

Web Scraping and Price Prediction of various websites by deploying Python Libraries such as urllib and BeautifulSoup

Managed Data Munging, Data Cleaning, Missing Data through Exploratory Data Analysis via Jupyter Notebook as IDE

Performed Log analysis to support application monitoring on real-time data via Elasticsearch, Logstash, and Kibana

Technical Skills

Languages: Python, C

Data Analytic Tools: Tableau (Desktop, Prep), Alteryx, Excel

Databases: SQL, PL SQL, SQLite, MongoBD

AWS: VPC, EC2, S3, Redshift, Elastic MapReduce

Libraries: Pyspark, Pandas, Numpy, scikit-learn, sklearn, spaCy, NLTK, Keras, Tensorflow, XGBoost, Seaborn, Matplotlib

Hadoop: Apache Spark (Spark Streaming, MLib), MapReduce, Hive, Pig, Airflow

Tools & Framework: Elasticsearch, Logstash, Kibana, Git, SVN

Familiar with: RNN, CNN, ANN, MatLab, SPSS, SaaS, Optimisations ML Techniques

Education

California State University, Fullerton Graduation

Master of Science, Computer Engineering December 2018

Rajiv Gandhi College of Engineering and Research Graduation

Bachelor’s Degree, Electronics and Telecommunication May 2015

Projects

Movie Recommendation System:

Implemented Collaborative Filtering on MovieLens Dataset to create the entire system

Applied Exploratory Data Analysis techniques and implemented Seaborn & Matplotlib for Visualization purpose

Credit Card Fraud Detection:

Implemented Logistic Regression Classifier as a probabilistic approach on Card Fraud dataset from Kaggle.com

Resampled data to an approx. 50-50 ratio and attained 92.7% Accuracy by employing Seaborn and sklearn

Web Scraping and Data Extraction:

Imported get, urllib & webbrowser module for the identification of the URL structure

Introduced BeautifulSoup library from the bs4 module for parsing and sorting of the HTML content

Applied Web Scraping data pre-processing techniques, extracted data of products such name, size, & category from Nike.com

House Price Prediction:

Employed Decision Tree Regressor to anticipate house prices & Adaptive Boosting technique to boost accuracy

Got MSE =14.79, & Variance =0.82 via Decision Tree Performance & MSE = 7.54 & Variance = 0.91 via AdaBoost

A/B Testing:

Created and implemented two variations of Correlation heat maps which signifies the degree of Correlation

Analysed with the Product Manager in the creation of variations mTAB for the official website via Optimizely



Contact this candidate