Data Social Media

Anurag Singh

****, ********** ******* *****, *** D, Charlotte, NC 28262, USA

+1-980-***-**** adhp4a@r.postjobfree.com www.linkedin.com/in/anurag-singh-68810710b EDUCATION:

University of North Carolina at Charlotte, Charlotte, NC [Dec 2020] MS in Information Technology (Advanced Data Science & Knowledge Discovery Concentration) University of Mumbai, Mumbai, India [May 2016]

BE in Electronics & Telecommunication Engineering

Data Science/ Data Engineering Skills & Certification: Data Engineering/Data Scientist Platform: Python, R, Big Data, MATLAB, SAS, MySQL, T-SQL. Packages:Numpy, Pandas, Scikit-Learn, Keras, TensorFlow, PySpark, PyTorch, Matplotlib, Seaborn, SpaCy, NLP, MxNet. Machine Learning Skills: Classification, Regression, Clustering, Association Rule Mining, Data Warehousing. Data Science Tools: Tableau, Amazon Macie, Microsoft Power BI, Alteryx, Microsoft Office. Big Data & Cloud: Linux, PuTTy, Spark, MapReduce, Hadoop, Hive, HDFS, AWS SageMaker, Google Analytics. Data Maturity Efforts: Data Mining, Data Wrangling, Data Ingestion, Data Modeling, Data Profiling, Data Visualization. Certification: Comcast NBCUniversal Virtual Development Experience WORK EXPERIENCE:

Graduate Teaching Assistant, University of North Carolina (Charlotte, USA) [September 2020 – Present]

Working with Big Data managed over various cloud platforms such as Amazon AWS S3/ Microsoft Azure/ Google Cloud Platform to Ingest, extract value from data & Analyze social media feeds that potentially impact business decisions.

Transforming high volumes of data into advanced analytic solutions for ETL development process using SSIS. Managing the data over Microsoft SQL Server Management Studio and offloading computation from the main SQL Server instance to standalone Machine Learning Server using Machine Learning Library revoscalepy. System Data Engineer, Infosys Private Limited (Pune, India) [Mar 2017 – July 2019]

Extract, Load, Clean & Transformed big data for predictive analytics. Built Machine Learning model to analyze the customer behavior & build a predictive model that would help in predicting whether user transaction is legit or fraudulent.

Reported business requirements for Bank of America & developed Technical Design Documents to ensure all system support & parallelly worked extensively using Tableau. Extracted data in form of XML, Excel, CSV & JSON

(Semi-Supervised data) to do big data preparation and analysis.

Prepared data for the downstream Hadoop and improved performance by writing performance-tuned ETL jobs using Teradata. Evaluate Strategies using A/B testing & Performed user acceptance testing for stewardship owned projects. Associate Technical Engineer, Altisource Business Solutions (Mumbai, India) [June 2016 – Feb 2017]

Used Machine Learning to design a classification model that will help with predicting the sales of the computer within the organization using predictive models & market basket analysis.

Automated nightly job in python. The code was written to check file validations & to move files to the destination. ACADEMIC PROJECTS:

Airbnb Price Prediction (Machine Learning using Linear Regression Model, Sentimental Analysis with Deep Learning)

Built a predictive model that help to predict the prices in San Diego, California. Used Linear Regression Model and used different Machine learning algorithms such as XGBoost & Random Forest. Used MSE & Root MSE as our evaluation metrics along with python library Scikit-Learn.

Used Recurrent Neural Network(RNN) with frameworks such as Keras & Tensorflow to do Sentimental analysis on Room Reviews Feature and used to Analyze user behavior to customize Airbnb Rooms experience.

Image Classification & Augmentation for Data (Machine Learning, Deep Learning- Neural Network, CNN)

Built a Deep Learning model using Neural Network, CNN & Transfer Learning which helped in the classification of the test images & Altered training data to provide more variation of training data to make our model more robust using ImageDataGenerator provided by Keras framework.

Walmart Sales Reporting (Data Warehousing, Data Visualization, Machine Learning, Deep Learning)

Developed Supervised Learning model which helped us in predicting the upcoming month sales. Using a Machine learning algorithm built an Ensemble Method which provided a greater range of accuracy using a bootstrapping algorithm.

Used deep learning frameworks such as Keras, Tensorflow to built a classification model for products using Tableau and identified appropriate categories for products.

Contact this candidate