Resume

Sign in

Data Sales

Location:
Charlotte, North Carolina, United States
Salary:
95000
Posted:
February 05, 2018

Contact this candidate

Resume:

The information is correct to the best of my knowledge Date: 31-Jan-18 OPT-EAD Open to Relocation NILANJAN CHATTERJEE

Phone: 1-704-***-**** E-mail: ac4cco@r.postjobfree.com LinkedIn: https://www.linkedin.com/in/nil68657 GitHub: https://github.com/nil68657 SAS certified polyglot programmer with 4+ years of work experience in Data Science, Machine Learning Consulting with good problem solving skills that has proven ability to optimize business processes to save cost and improve ROI, looking for Full-Time roles. Education

BS in Electronics & Communication Engg. – West Bengal University Of Technology, India 2009-2013, GPA-3.7/4.0

MS in Computer Science - The University of North Carolina at Charlotte,NC, USA 2016-2017, GPA -3.8/4.0 Certifications

Oracle Certified Associate – 11g

SAS Certified Data Scientist, SAS Certified Base Programmer Technical Skills

Languages: C, C++, R (advanced), Java, Python (numpy, pandas, scipy, sklearn, matplotlib, Seaborn, PyTorch, Keras, TensorFlow, Caffe, Theano), SAS(Base, E-miner, Predictive Modeler), Orange, WEKA, F#, Scala, Erlang, Rust, Octave, Julia, LISP.

Platforms : Windows, Linux(Debian, CentOS, RHEL), AWS(EC2, S3,Route 53, Dynamo DB, Aurora,EBS,EFS, Lambda, Lex, Kinesis)

Databases : Microsoft SQL, MYSQL, Oracle, Mongo DB, Cassandra, Redis, DynamoDB, HBase

Tools : SAS 9.4, SPSS, OpenCV, Qlikview,Tableau Studio, Eclipse, Jupyter, TFS, Jenkins, SAS Eminer,Git,VS 2015

Data Science: Classification, Regression, Feature Engineering, Clustering, Data Mining, Predictive Modelling, Deep Learning,

Statistics : Time Series forecasting, Hypothesis testing, PCA, Dimensionality reduction, ANOVA, Recommender systems EXPERIENCE ~~ 4 years

IBM Corporation- Data Science Intern - Research Triangle Park, NC, USA June 2017- December 2017

Developing solutions for BlueMix team by feature engineering of usage pattern data/ customer churn & developing algorithms like PCA, SVD, Market Basket Analysis, kNN, GBM, Hierarchical Clustering, Logistic Regression with Bayesian Belief, MCMC.

Have designed model deployment and optimization strategy using CPLEX, Gurobi, LAPack for Spark MLib platform.

Have created visualizations using Python (Matplotlib, Seaborn), R(ggplot2) and effective roll out and pilot testing strategy with Sales team based on model performance and iteration strategies for A/B testing. Hewlett Packard R&D Labs – Senior Data Engineer- Bangalore, India Apr 2016- August 2016

Led a team of three towards implementing statistical tests, linear contrasts, RFM, Random forests, Monte Carlo for HP devices.

Have worked on Time series modelling for sales/demand forecasting implementing ARIMA, GARCH models with smoothing.

Have cleaned huge petabytes and gigabytes of data using R, OpenRefine, Paxata, Trifacta to enable ML algorithm development.

Developed predictive models using R, Python, Scala and presented on scrum meetings for consumer analytics. Had setup 10 node SAS SPD/Spark cluster for stream analytics of pilot phase using Spark, Mahout, Impala, HBase, Oozie, Flume, Zookeeper.

Worked on Azure and AWS for cloud integration, model deployment to SaaS using RedShift, Lambda, Lex following CRISP-DM. Cognizant Technology Solutions – Programmer Analyst- Bangalore, India July 2013- April 2016

Qualitative data and sentiment analysis using Topic modelling & build NLP models and visualizations using SAS, Tableau, Qlik.

Worked with HR Analytics team implemented RNN and RBM algorithms to predict employee attrition rate and identify them.

Have migrated DW’s and data lakes to 20-25 node Hadoop cluster with Pig, Hive, HBase, Impala, Oozie, Flume, Ambari, Mahout.

Worked on database development for DW integration and management using Erwin Data Modeler, MSSQL, Power BI, Pentaho, Cognos, UNIX. Have experience managing lifecycle of application deployment by technologies like SQL Server, SSMS, Toad, Unix

Have written efficient advanced SQL queries and cubes using SSIS, SSAS, SSRS, PlSQL & T-SQL, with Microstrategy MDX query Coursework Projects:

Spam filtering Engine using R - Developed a SVM for supervised Machine Learning for the engine to classify emails as spam or non-spam. I have developed Bagging and k-means clustering, PCA with one-hot encoding for feature engineering. o Technologies: R, dplyr, Python, pandas, numpy, scikit-learn, shiny, caret, ggplot2, kernlab, doMc.

Quora Duplicate question using Python - Developed a character based RNN implementation using neural networks and SVM as Word2Vec, Bag Of Words models with fine tuning via scikit-learn GridSearchCV, Keras, Caffe, Tensorflow, PyTorch. o Technologies: Python, pandas, numpy, scikit-learn, Word2Vec, GridSearchCV, Caffe, Tensor Flow, Glove..

Live data stream sentiment analysis and Blockchain implementation - Created and maintained 10 node Spark cluster for process live stream running k-NN and Bayesian learning to perform sentiment analysis using Kafka streaming and Druid. o Technologies: Python, Java, MySQL, Netezza, Apache Spark, Storm, Hadoop, Sqoop, Flume, Oozie, Pig, SAS.,

Image segregation algorithm for classifying different types - Developed an algorithm to classify different types of images from a broad category into classes and label them using PyTorch, WEKA and Orange extensions. o Technologies: NLTK, Stanford-NLP, Tensorflow, Caffe, Apache Solr, HDFS, Hive, Kafka, Druid, HBase.

Efficient resource allocation and attrition analysis for Daimler Trucks - Developed an analytics dashboard using Tableau and D3.js using statistical and analysis methods on dataset provided by Daimler Trucks North America. Worked directly with the client manager in setting benchmark rules and visualizations. o Technologies: HTML, CSS, SVG, WebGL, D3.js, Tableau 10.1, Qliksense, Trifacta, OpenRefine.

Android App using Raspberry Pi for Room Control - An Android app for controlling room temperature that connects with the Raspberry pi via Java and uses PHP for fetching information and storing data on MySQL using socket programming. o Technologies: Java, Android Studio, OpenCV, MATLAB, Raspberry Pi, PHP, MySQL, NMAP, Kali Linux.

Clothing Closet implementation - Developed an online website using PHP and MySQL as a part of Master’s coursework. The information is correct to the best of my knowledge Date: 31-Jan-18 OPT-EAD Open to Relocation o Technologies: PHP (Yii framework), JavaScript (Angular, Bootstrap), MySQL, MariaDB.



Contact this candidate