Data Scientist Resume

PROFESSIONAL SUMMARY:

3+ years of experience in Machine learning and deep learning techniques
12+ Years of experience in software engineering to create Enterprise application using different platforms.
Experience in implementation of NLP applications to achieve semantic similarity, sentiment analysis, text summarization, tfidf, key phrase extraction tasks.
Experience in implementation of advance deep learning algorithms such as Universal Sentence Encoder, BERT for NLP applications such as Semantic Similarity and Question Answering system.
Achieved time and cost saving by automating report generation, implementing NLP based intelligent system.
Achieved 15% improvement in order invoice system by implementing order optimization system in heavy machinery organization.
Achieved 5% increase in sales volume and help client to sell their new and not moving old products by implementing recommendation engine.
Successfully design and architected data science system.
Undertakes machine learning, deep learning R & D on different tasks as per client requirement to achieve their goals.
Create POC using different Analytic platforms to acquire new clients.
Apply advanced analytics solutions to enable data - driven decision.
Team handling, task allocation, task tracking, prepare Technical & Functional documents.
Client communications, understand system requirements.

TECHNICAL SKILLS:

Languages: Python, R, c#, core java.

Tools: Microsoft Azure ML Studio, R Studio, Jupyter Notebook, Qlik Sense, pyCharm.

Machine Learning Algorithms: NLP, Non/linear regression, Random Forest, Ensemble techniques, Support Vector Machine, KMeans, Naive Bayes.

NLP: Semantic similarities, word embedding, sentence embedding, polarity analysis, text classification, text summarization, BOW, tfidf, unigram, n - grams.

Python Library: Pandas, Scikit-learn, NumPy, NLTK, Keras, Tensorflow, spacy, seaborn, matlabs

R Library: Caret, KMeans, Plumber, Shiny, RODBC, ggplot2,rCharts, dplr, Reshape2, devtools, data.table,, mice, parallel

Visualization Tools: Qlik Sense

Cloud Services: Microsoft Azure ML, Google Cloud.

Deep Learning: MLP, CNN, RNN, LSTM, Autoencoder, Transformer, Annotation.

Database: MSSQL, MySQL, DB2, SQLite

WORK EXPERIENCE:

Data Scientist

Confidential

Responsibilities:

Requirement gathering & understanding.
Data Understanding, Data Cleansing, Data Processing.
Design and architected system.
Implementation of deep learning and machine learning algorithms to create models.
Implemented USE, BERT advance deep learning algorithms.
API creation.

Environment: Python 3.6.

Library: tensorflow, scikit-learn, NLTK, spacy, genism, flusk, matlab.

Database: SQLite 3.26.0

Data Scientist

Confidential

Responsibilities:

Requirement gathering & understanding.
Data Understanding, Data Cleansing, Data Processing.
Creation of dashboard.
Finding interesting insights from data.
KPI creation

Environment: Qlik-Sense desktop.

Database: MSSQL-2000.

Data Scientist

Confidential

Responsibilities:

Requirement gathering & understanding.
Data Understanding, Data Cleansing, Data Processing.
Implementation of market basket machine learning algorithm.

Environment: Python on window platform.

Package: Market Basket Analysis.

Data Scientist

Confidential

Responsibilities:

Requirement gathering & understanding.
Data Understanding, Data Cleansing, Data Processing.
Creation of dashboard.
KPI creation

Environment: Qlik-Sense desktop.

Database: MySQL.

Data Scientist

Confidential

Responsibilities:

Requirement gathering & understanding.
Data Understanding, Data Cleansing, Data Processing.
ETL service creation.
Machine learning (model creation)
API creation.
Dashboard Creation.

Environment: R on window platform.

ETL: c#.net

Package: KMean, dplry, plumber.

Visualization Tool: Qlik Sense.

Project Lead

Confidential Service Pvt Ltd

Customer Churn (POC)

The aim of this project is to help client by providing insights in their customers who are likely to leave () their services. Unsupervised machine learning technique is implemented in this POC.

Environment: R.

Package: Caret, Shiny, RODBC, ggplot2, dplr, Reshape2.

Algorithm used: Logistic Regression, Radom forest, KMean.

Project Lead

Confidential

Responsibilities:

Fetching data from their retail site using web scrapping.
Analysis of extracted data by using Natural language processing (NLTK).

Environment: Python.

Package: NLTK, beautiful soup

Project Lead

Confidential

Environment: R.

Library: Shiny, RODBC, ggplot2, dplr, Reshape2.

Project Lead

Confidential

Responsibilities: Client communication, Task allocation, Issue management, Root Cause Analysis.

Environment: C#, Asp.Net, WCF, Oracle 11G, Subversion (SVN).

We provide IT Staff Augmentation Services!

We'd love your feedback!

Resume Categories

Client Services

Job Seekers

Visa Sponsorship