The main objective of this group is to eliminate pain points for end-users throughout the enterprise. This role requires the use of AI and Machine Learning to drive the Operational Data Science team’s objective of supporting the organization’s initiatives to drive high application availability through data-driven automation. Building out Machine Learning solutions for anomaly detection within end-user’s internal applications. • Conceptualized transactions as statistical metrics as the key indicator of failures to test various hypotheses. • Build machine learning models through all phases of development, from design through training, evaluation, validation, and implementation.• Build models using customer transaction data to make more accurate, real-time, and fluid decisions.• Formulate context-relevant questions and hypotheses to foster data-driven research and decision-making. • Evaluated various tracking matrices in data projects and improved overall accuracy of models from 69 to 84%. • Ad Hoc queries, analyses, and segmentation studies that combine multiple tools and data sources and types to extract insights from various A/B and multivariate tests Environment: Natural Language Processing, Word2vec, Bag-of-words, Gradient Boosting, Classification, A/B Testing

• Performed Data Collection, Data Cleaning and Data Visualization using RStudio, Deep Feature Synthesis and extracted key statistical findings to develop business strategies. • Initiated various pre-processing phases of text like Tokenizing, Stemming & Lemmatization and converting the raw text to structured data. • Constructed new vocabulary to encode the variables in a machine-readable format using Bag of words and TF-IDF. • Implemented sampling, PCA and LDA for high dimensional data and drew visual statistical conclusions as well as statistical inferences. • Employed NLP to classify text within the dataset. Categorization involved labeling natural language texts with relevant categories from a predefined set. • Analyzed and grouped products into different clusters based on product description, purchase and historic data using techniques such as k-means clustering. • Employed auto-classification of products based on customer database by drawing inferences from products ordered together. This assisted in creation of cohorts. • A gradient boosted Decision Tree Classifier was trained using Extreme Gradient Boosting to identify whether a cohort was a promoter or detractor. • Optimized the performance of the neural network using the regularization and choosing the right number of hidden layers and neurons per layer. • The NLP text analysis monitored, tracked and classified user discussion about product and service in online discussion. (ScraPy and BeautifulSoup). Tools and Environment: R, Tableau, Python – NLTK, SpaCy, Sci-Kit learn.

• Used Python to develop different models & algorithms to predict the probability of customer subscribing for premium using different variables. • Built a classification model to classify customers for promotional deals to increase likelihood of subscription using Logistic Regression and Decision Tree Classifier. • Developed and implemented predictive models like Decision Tree, Support Vector Machine and Logistic Regression to predict the probability of enrollment. • Picked the final model based on ROC & AUC and fine-tuned the hyper parameters of the above models using Grid Search to find the optimum model. Environment: R, Tableau, Python – NLTK, SpaCy, Sci-Kit learn,SQL .

• Designed algorithms to identify and extract income from demographics of data which has 34 variables and more than 1 million observations. Developed a model to business team to help design them the income of employees.• Performed Exploratory Data Analysis and Data Visualizations using Python to identify related variables for initial inspection and performed univariate and bi-variate analysis to understand the intrinsic effect/combined to select features for modelling to reduce them from 34 variables to 13 variables. • Processing, cleansing, and verifying the integrity (Missing value imputation) of data to accommodate for better performance and accuracy of the model by imputing based on the domain knowledge and regression.• Analyzed and processed complex data sets using advanced querying, visualization, and analytics tools.• Identified, measured and recommended improvement strategies for KPIs across all business areas.• Built a framework in python with Machine learning algorithms like Regressions (linear, logistic etc..), SVM, Random Forest, Decision trees to predict the income of a given person, Clustering and classification of data for organizing the data to feed machine learning models and obtained AUC up to 0.86.• Created and presented models for potential holdings to fund managers. Acheived 25% better than traditional figures.Environment: R, Tableau, Python – NLTK, SpaCy, Sci-Kit learn, SQL .

• Interacted with Business team to gather requirements. Extensive experience with AWS services like S3, ELB, EBS, Auto-Scaling, Route53, Storefront, IAM, Cloud Watch, RDS etc.• Performed Data analysis for the existing Data warehouse and changed the internal schema for performance.• Used SDLC (System Development Life Cycle) methodologies like RUP and Agile methodology.• Proficient in writing SQL Queries, Stored procedures, functions, packages, tables, views, triggers using relational databases like Oracle, MySQL and MSSQL Server. • Tested ETL, ELT, and ECTL processes with source systems as varied as oracle RDBMS, DB2, and flat files. • Developed the batch scripts to fetch the data from AWS S3 storage and do required transformations in Scala using the Spark framework.• Developed Spark, Python for regular expression (regex) project in the Hadoop/Hive environment with Linux/Windows for big data resources.• Dynamic deployment of Data Platform for a Verizon Artificial Intelligence system. Some of the results were are impressive.• AWS Glue for cataloging S3 bucket (Data Lake) and loading it in Athena. • Worked on OS like Microsoft Windows / where Apache is the Web server and MySQL handles the database components, while PHP, Python, or PERL represents the dynamic scripting languages.• Used AWS Glue and Redshift Spectrum for ETL and querying semi-structured data from S3 respectively. • Useed AutoML to use the best possible algorithm and hyperparameters reduced the error rate of the previous hand-tuned model.• Created MySQL queue using AWS SNS, SQS, and Golang (Go), to concurrently process SQL queries in the background and Built a Golang web server to host multiple tools so another has http access to them.• Implement CI/CD pipelines using GitHub, Docker, Kubernetes and Python .• Utilized Apache Spark with Python to develop and execute Big Data Analytics and Machine learning.

• Used PySpark to expose Spark API to Python. Work on different data formats such as JSON, XML and applied automated machine learning (AutoML) algo in Python.• Used AWS EC2, REDSHIFT, DEVBOX, DBA and implemented various work environment.• Cost analyzing to use AWS service like data pipeline, Kinesis firehose, lambda, SQS (Queues), scala spark S3Distcp etc.• Developed a Machine Learning application to predict disease medication based on demographic and medical history.• Worked on setting up EC2 instances, security groups and Setting up databases in AWS using S3bucket and configuring instance backups to S3 bucket.• Have used Python libraries like NumPy/SciPy, Pandas for market analysis and done some machine learning using Python.• Used the RegEx, JSON and Avro for serialization and de-serialization packaged with Hive to parse the contents of streamed log data.• Worked on splunk logs in order to monitor the issues in all the environments. • Developed various Python scripts to find vulnerabilities with SQL Queries by doing SQL injection, permission checks and performance analysis. • Develop ETL software to automate the extraction of information from NetApp filer and consolidate the data into our data warehouse • Golang and Java were used as a backend REST service while AngularJS was used for the user interface.• Implemented and modified various SQL queries and Functions, Cursors and Triggers as per the client requirements. • Extensively used AWS Redshift, S3, Spectrum and Athena services to query large amount data stored on S3 to create a Virtual Data Lake. Worked with AWS Data Migration Services and Schema Conversion Tool along with Matillion ETL tool. • Played key role in Data movement to the cloud (Oracle OBIEE to AWS Redshift) by being a part of HR Data management team.